mirror of
https://github.com/github/awesome-copilot.git
synced 2026-08-08 18:19:14 +00:00
chore: publish from main
This commit is contained in:
github-actions[bot]
@@ -0,0 +1,85 @@
|
||||
---
|
||||
title: "Lección 0 - Requisitos previos"
|
||||
description: "Prepara el entorno para las lecciones de la aplicación GitHub Copilot: instala Node.js para el proyecto Tailspin Toys y crea tu propia copia del repositorio a partir de la plantilla."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
La aplicación GitHub Copilot es una aplicación de escritorio que actúa como centro de operaciones tanto para Copilot como para GitHub. Proporciona acceso rápido a incidencias y solicitudes de incorporación de cambios y, por supuesto, permite desarrollar con GitHub Copilot. Durante este taller trabajarás en local con la aplicación Tailspin Toys, creada con Astro, y con la aplicación GitHub Copilot. Antes de empezar, vamos a comprobar que Node.js esté instalado en local y, después, instalaremos la aplicación Copilot.
|
||||
|
||||
En esta lección:
|
||||
|
||||
- instalarás Node.js para poder ejecutar las pruebas del proyecto en tu equipo.
|
||||
- crearás tu propia copia del proyecto Tailspin Toys a partir de la plantilla.
|
||||
|
||||
## Instalar Node.js
|
||||
|
||||
En varias lecciones se pide a un agente que desarrolle funcionalidades y ejecute en local el conjunto de pruebas de Tailspin Toys, para lo que se necesita [**Node.js**][nodejs], el único entorno de ejecución que requiere el proyecto. Instala la versión **22 o posterior**; la versión **LTS** actual es una opción segura.
|
||||
|
||||
La opción más sencilla en cualquier plataforma es usar el instalador oficial:
|
||||
|
||||
1. En el sistema operativo, abre una ventana de terminal con Windows Terminal, Terminal de macOS o la aplicación que utilices habitualmente.
|
||||
2. Ejecuta el comando siguiente para confirmar que tienes instalada la versión 22 de Node.js o una posterior:
|
||||
|
||||
```shell
|
||||
node --version
|
||||
```
|
||||
|
||||
3. Si aparece `v22` o un número superior, puedes pasar a la sección siguiente.
|
||||
|
||||
> [!TIP]
|
||||
> Solo tienes que completar estos pasos si no tienes Node instalado o si necesitas actualizarlo.
|
||||
|
||||
4. Abre la [página de descarga de Node.js][node-download].
|
||||
5. Descarga la versión **LTS** correspondiente a tu sistema operativo.
|
||||
6. Ejecuta el instalador y acepta las opciones predeterminadas. En Windows, mantén seleccionada la opción **Add to PATH**.
|
||||
7. Después de instalarlo, abre una nueva ventana de terminal.
|
||||
8. Confirma la instalación en la nueva ventana de terminal mediante el comando siguiente:
|
||||
|
||||
```bash
|
||||
node --version
|
||||
```
|
||||
|
||||
9. Debería aparecer `v22.x.x` o una versión posterior.
|
||||
|
||||
> [!TIP]
|
||||
> ¿Prefieres usar contenedores? Si tienes [**Docker**][docker], puedes utilizar el [contenedor de desarrollo][dev-containers] del repositorio en lugar de instalar Node.js en local; el contenedor ya incluye Node. No necesitas ambas opciones.
|
||||
|
||||
## Configurar el repositorio del laboratorio
|
||||
|
||||
Trabajarás con tu propia copia del proyecto Tailspin Toys. Créala ahora a partir del [repositorio de plantilla][template-repository]. El nuevo repositorio contiene todos los archivos necesarios para el laboratorio y lo conectarás a la aplicación en la siguiente lección.
|
||||
|
||||
1. En una nueva ventana del navegador, ve al repositorio de GitHub de este laboratorio: `https://github.com/github-samples/tailspin-toys`.
|
||||
2. Para crear tu propia copia del repositorio, selecciona el botón **Use this template** en la página del repositorio del laboratorio. A continuación, selecciona **Create a new repository**.
|
||||
|
||||
|
||||
|
||||
3. Si realizas el taller como parte de un evento dirigido por GitHub o Microsoft, sigue las instrucciones de los mentores. De lo contrario, puedes crear el nuevo repositorio en una organización en la que tengas acceso a GitHub Copilot.
|
||||
|
||||
|
||||
|
||||
4. Anota la ruta del repositorio que has creado (**organization-or-user-name/repository-name**), ya que la utilizarás más adelante en el laboratorio.
|
||||
|
||||
> [!NOTE]
|
||||
> Al crear el repositorio a partir de la plantilla, se genera automáticamente una lista de incidencias de trabajo pendiente. Trabajarás con estas incidencias durante todo el taller; no necesitas crear ninguna.
|
||||
|
||||
## Resumen y pasos siguientes
|
||||
|
||||
Ya tienes el entorno preparado. Has instalado Node.js para poder compilar y probar el proyecto en tu equipo y has creado tu propia copia del repositorio Tailspin Toys a partir de la plantilla.
|
||||
|
||||
A continuación, instalarás la aplicación GitHub Copilot, conectarás el repositorio que acabas de crear y conocerás el espacio de trabajo. Continúa con la [Lección 1 - Instalar la aplicación GitHub Copilot][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Descargar Node.js][node-download]
|
||||
- [Crear un repositorio a partir de una plantilla][template-repository]
|
||||
- [Acerca de la aplicación GitHub Copilot][about-copilot-app]
|
||||
|
||||
[next-lesson]: /es-es/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[nodejs]: https://nodejs.org/
|
||||
[node-download]: https://nodejs.org/en/download
|
||||
[docker]: https://www.docker.com/products/docker-desktop/
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
+100
@@ -0,0 +1,100 @@
|
||||
---
|
||||
title: "Lección 1 - Instalar la aplicación GitHub Copilot"
|
||||
description: "Instala la aplicación GitHub Copilot, conecta el repositorio que has creado a partir de la plantilla, familiarízate con el espacio de trabajo y prueba un chat rápido."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
La [**aplicación GitHub Copilot**][about-copilot-app] es una aplicación de escritorio para el desarrollo dirigido por agentes. Se basa en GitHub Copilot CLI y se integra de forma nativa con GitHub, por lo que los repositorios, las ramas y las canalizaciones de CI funcionan sin configuración adicional. Está diseñada para flujos de trabajo en los que diriges varios agentes en paralelo, cada uno en su propio espacio de trabajo aislado, en lugar de realizar todo el trabajo y automatizar las tareas repetitivas por tu cuenta. Con Node.js instalado y tu copia del proyecto preparada, el siguiente paso es instalar la aplicación y conectar ese repositorio.
|
||||
|
||||
En esta lección:
|
||||
|
||||
- instalarás la aplicación GitHub Copilot e iniciarás sesión.
|
||||
- añadirás el proyecto a la aplicación desde su repositorio de GitHub.
|
||||
- conocerás el espacio de trabajo, incluida la lista de trabajo pendiente que la plantilla ha creado para ti.
|
||||
- probarás un chat rápido para obtener información sobre la propia aplicación.
|
||||
|
||||
## Escenario
|
||||
|
||||
Tu equipo está adoptando agentes de IA para abordar una lista creciente de trabajo pendiente. La aplicación Copilot ofrece un único lugar desde el que dirigir ese trabajo: seleccionar incidencias, ejecutar agentes, revisar cambios y combinar solicitudes de incorporación de cambios. En esta lección instalarás y conectarás la aplicación, y aprenderás a iniciar una conversación sobre el proyecto.
|
||||
|
||||
> [!NOTE]
|
||||
> Se requiere un plan de Copilot válido: Copilot Student o cualquier plan de pago (Pro, Pro+, Business o Enterprise). Si utilizas Copilot Business o Copilot Enterprise, el administrador debe habilitar la directiva **Copilot CLI** para que la aplicación funcione.
|
||||
|
||||
## Instalar y configurar la aplicación GitHub Copilot
|
||||
|
||||
Como cabe esperar, el primer paso para utilizar la aplicación GitHub Copilot es instalarla. Hay versiones disponibles para Windows, macOS y Linux. Vamos a instalar la aplicación, autenticarnos y añadir a ella nuestro repositorio de Tailspin Toys.
|
||||
|
||||
1. En un navegador, abre la [página de inicio de la aplicación GitHub Copilot][download-app].
|
||||
2. Descarga la aplicación para tu plataforma e instálala siguiendo las instrucciones de la página.
|
||||
3. Abre la aplicación después de instalarla.
|
||||
4. Selecciona **Sign in to GitHub** y sigue las indicaciones para autenticarte. Si utilizas GitHub Enterprise Server, elige **Use GitHub Enterprise** e introduce la dirección del servidor cuando se solicite.
|
||||
5. Después de autenticarte, se te pedirá que conectes los repositorios. Selecciona el repositorio de Tailspin Toys que acabas de crear, cuyo nombre debería ser `<YOUR_GITHUB_HANDLE>/tailspin-toys`.
|
||||
6. Selecciona **Continue** para continuar con la incorporación.
|
||||
7. Cuando se te pida que elijas un tema, selecciona el que más te guste y, después, selecciona **Finish**.
|
||||
|
||||
> [!NOTE]
|
||||
> Si tu copia de Tailspin Toys no aparece automáticamente en la lista, puedes añadirla tras completar el proceso de incorporación en la aplicación. Al finalizar, la aplicación Copilot mostrará la pantalla de inicio. Desde allí, selecciona **Choose from GitHub**, busca el repositorio por su nombre (\<YOUR_GITHUB_HANDLE\>/tailspin-toys) y selecciónalo. El repositorio se añadirá a la aplicación Copilot.
|
||||
|
||||
## Familiarizarse con el espacio de trabajo
|
||||
|
||||
Con el proyecto conectado, dedica un momento a conocer el espacio de trabajo. La aplicación organiza todo en varias áreas de la barra lateral:
|
||||
|
||||
- **Sessions**: donde los agentes realizan su trabajo. Cada sesión se ejecuta en su propio espacio de trabajo aislado, por lo que puedes ejecutar varias a la vez sin que sus cambios entren en conflicto. Iniciarás tu primera sesión en la siguiente lección.
|
||||
- **Quick chats**: conversaciones ligeras para preguntas y lluvias de ideas que no necesitan una rama ni un espacio de trabajo propios. Probarás una al final de esta lección.
|
||||
- **My work**: tus incidencias y solicitudes de incorporación de cambios, disponibles mediante la **integración nativa con GitHub** de la aplicación. Desde aquí puedes examinar y filtrar incidencias y solicitudes de incorporación de cambios, comprobar el estado de CI, iniciar una sesión a partir de una incidencia y revisar solicitudes de incorporación de cambios, todo ello sin salir de la aplicación.
|
||||
- **Automations**: tareas de agente guardadas que se ejecutan según una programación o bajo demanda. Crearás una casi al final de este recorrido.
|
||||
|
||||
### Localizar la lista de trabajo pendiente inicial
|
||||
|
||||
Como la aplicación se integra de forma nativa con GitHub, el trabajo pendiente del repositorio aparece directamente en ella. Cuando creaste el repositorio a partir de la plantilla, se generó una lista de incidencias. Vamos a comprobar que esté disponible.
|
||||
|
||||
1. Selecciona **My work** en la barra lateral.
|
||||
2. La plantilla ha creado ocho incidencias en tu lista de trabajo pendiente. Este módulo se centra en las tres siguientes; confirma que puedes verlas:
|
||||
|
||||
- Allow users to filter games by category and publisher
|
||||
- Update our repository coding standards
|
||||
- Implement pagination on the game list page
|
||||
|
||||
3. Selecciona una incidencia para leer sus detalles. Cada incidencia también sirve como punto de partida para una sesión de agente. Más adelante iniciarás el trabajo desde estas incidencias.
|
||||
|
||||
> [!NOTE]
|
||||
> La lista de elementos de **My work** se filtra automáticamente para mostrar solo los elementos de los repositorios que has añadido a la aplicación Copilot. Para ver elementos de trabajo de otros repositorios, añádelos a la aplicación.
|
||||
|
||||
## Probar un chat rápido
|
||||
|
||||
Una buena forma de familiarizarse con la aplicación es utilizarla para conocer la *propia aplicación*, y un **chat rápido** es la herramienta adecuada. Los chats rápidos permiten formular una pregunta o plantear ideas sin crear una rama ni un árbol de trabajo, por lo que son perfectos para una consulta rápida y desechable que no requiere una sesión.
|
||||
|
||||
1. En la barra lateral, selecciona **+** junto a **Quick chats** para abrir un chat nuevo.
|
||||
2. Pregunta a la aplicación cómo funcionan sus sesiones:
|
||||
|
||||
```plaintext
|
||||
How does the GitHub Copilot app use worktrees?
|
||||
```
|
||||
|
||||
3. Lee la respuesta en la vista de conversación. Verás que cada sesión se ejecuta en su propio árbol de trabajo de Git aislado, lo que permite ejecutar varios agentes en paralelo sin que sus cambios entren en conflicto. Puedes continuar la conversación o iniciar un chat nuevo en cualquier momento.
|
||||
|
||||
## Resumen y pasos siguientes
|
||||
|
||||
Has instalado la aplicación GitHub Copilot, conectado el proyecto y explorado el espacio de trabajo. Has aprendido a:
|
||||
|
||||
- instalar la aplicación e iniciar sesión en GitHub.
|
||||
- añadir un proyecto desde su repositorio de GitHub.
|
||||
- familiarizarte con el espacio de trabajo y localizar la lista de trabajo pendiente inicial en **My work**.
|
||||
- utilizar un chat rápido para formular una pregunta breve y desechable.
|
||||
|
||||
A continuación, iniciarás tu primera sesión de agente y realizarás el primer cambio en el proyecto: mostrar una valoración por estrellas en las tarjetas de los juegos. Continúa con la [Lección 2 - Ejecutar tu primera sesión de agente][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Acerca de la aplicación GitHub Copilot][about-copilot-app]
|
||||
- [Introducción a la aplicación GitHub Copilot][getting-started]
|
||||
- [Trabajar con sesiones de agente en la aplicación GitHub Copilot][agent-sessions]
|
||||
|
||||
[ex0]: /es-es/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[next-lesson]: /es-es/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[download-app]: https://gh.io/app
|
||||
+135
@@ -0,0 +1,135 @@
|
||||
---
|
||||
title: "Lección 2 - Ejecutar tu primera sesión de agente"
|
||||
description: "Inicia tu primera sesión de agente en la aplicación GitHub Copilot, realiza un pequeño cambio en las tarjetas de los juegos y combínalo como tu primera solicitud de incorporación de cambios."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
En la lección anterior recorriste el espacio de trabajo y utilizaste un chat rápido. Ahora es el momento de iniciar una **sesión de agente** y realizar el primer cambio en el proyecto. Será un cambio pequeño: los juegos ya tienen una valoración por estrellas en sus datos, pero las tarjetas de la página de inicio todavía no la muestran. Pedirás al agente que la muestre, revisarás el cambio y lo combinarás como tu primera solicitud de incorporación de cambios.
|
||||
|
||||
En esta lección:
|
||||
|
||||
- iniciarás una sesión de agente y aprenderás cómo se estructura.
|
||||
- pedirás al agente que realice un cambio pequeño y específico en el proyecto.
|
||||
- revisarás el cambio en la vista de diferencias del espacio de trabajo.
|
||||
- ejecutarás la aplicación en local para confirmar el cambio en el navegador.
|
||||
- abrirás y combinarás tu primera solicitud de incorporación de cambios.
|
||||
|
||||
## Escenario
|
||||
|
||||
Cada juego de Tailspin Toys puede tener una valoración por estrellas, que ya aparece en la página de detalles del juego. Sin embargo, las tarjetas de los juegos de la página de inicio solo muestran el título, la categoría, el editor y la descripción. Como ejercicio inicial, pedirás al agente que muestre la valoración existente en cada tarjeta. Es un cambio pequeño y autocontenido, perfecto para tu primera sesión.
|
||||
|
||||
## Anatomía de una sesión
|
||||
|
||||
Una **sesión** es una conversación con un agente que se ejecuta en su propio espacio de trabajo aislado. Cada sesión recibe un **árbol de trabajo y una rama de Git dedicados**, lo que permite ejecutar varias sesiones a la vez, por ejemplo, una para añadir una funcionalidad y otra para corregir un error, sin que sus cambios entren en conflicto. Las sesiones aparecen en la barra lateral agrupadas por repositorio; selecciona cualquiera de ellas para cambiar de sesión.
|
||||
|
||||
Dentro de una sesión verás tres elementos: la **conversación** con el agente, la **actividad de las herramientas** del agente mientras explora y edita archivos, y la lista de **archivos modificados** con sus diferencias.
|
||||
|
||||
## Iniciar una sesión y solicitar el cambio
|
||||
|
||||
Vamos a iniciar una sesión nueva para comenzar a explorar el proyecto e implementar la funcionalidad. En una [lección anterior][prior-lesson] añadiste el proyecto desde su repositorio de GitHub. Crearemos una sesión nueva para ese repositorio y solicitaremos el cambio.
|
||||
|
||||
1. Vuelve a la aplicación GitHub Copilot o ábrela.
|
||||
2. Selecciona **Home screen**.
|
||||
3. Comprueba que `tailspin-toys` esté seleccionado como repositorio.
|
||||
|
||||
|
||||
|
||||
4. Utiliza la indicación siguiente para solicitar el cambio:
|
||||
|
||||
```plaintext
|
||||
On the game cards, show each game's star rating. The Game type already includes a starRating field — it's a number out of 5, or null when a game hasn't been rated yet. Display it on each card in src/components/GameCard.astro, and when starRating is null show "No rating yet" instead. Keep the change small and don't restructure the card layout.
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> Observa que la indicación contiene el nombre del archivo que Copilot debe actualizar. Aunque no es necesario especificar los archivos que Copilot debe incluir en su trabajo, orientarlo ayuda a que genere el código con rapidez y reduzca el uso de tokens.
|
||||
|
||||
5. Selecciona <kbd>Enter</kbd> para enviar la indicación a Copilot.
|
||||
|
||||
La aplicación Copilot comienza por crear un árbol de trabajo nuevo, una copia aislada del proyecto. Después explora el proyecto, localiza los archivos que debe actualizar para añadir la funcionalidad y crea el código necesario. Ya has añadido una nueva funcionalidad con la aplicación Copilot.
|
||||
|
||||
## Revisar las diferencias
|
||||
|
||||
Todos los cambios generados por IA deben revisarse antes de combinarlos, incluso los más pequeños. Vamos a explorar los cambios directamente en la aplicación Copilot.
|
||||
|
||||
1. En la esquina superior derecha de la aplicación, selecciona **Toggle review panel**. Se abrirá la pantalla de diferencias con todos los cambios pendientes realizados por Copilot.
|
||||
|
||||
|
||||
|
||||
2. Deberías observar código añadido a `GameCard.astro`, el archivo principal que se utiliza para mostrar los detalles de los juegos. Debería ser similar al siguiente: un pequeño bloque que representa la valoración cuando existe y muestra "No rating yet" cuando `starRating` es `null`:
|
||||
|
||||
```astro
|
||||
{game.starRating !== null ? (
|
||||
<span class="text-xs font-medium px-2.5 py-0.5 rounded bg-amber-900/60 text-amber-300" data-testid="game-rating">
|
||||
★ {game.starRating} / 5
|
||||
</span>
|
||||
) : (
|
||||
<span class="text-xs font-medium text-slate-500" data-testid="game-rating-empty">
|
||||
No rating yet
|
||||
</span>
|
||||
)}
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> Como Copilot, al igual que todas las herramientas de IA generativa, es probabilístico y no determinista, el código exacto puede variar respecto al ejemplo anterior. No obstante, debería ser relativamente parecido.
|
||||
|
||||
## Comprobar los cambios
|
||||
|
||||
No debemos limitarnos a leer el código y dar por hecho que funciona. También debemos probarlo visualmente. Para ello, iniciaremos la aplicación desde la terminal y confirmaremos que todo funciona. La aplicación Copilot incluye una terminal integrada.
|
||||
|
||||
1. En el panel de revisión situado a la derecha de la aplicación Copilot, selecciona **Terminal**. Si no aparece el botón **Terminal**, selecciona **+** (con la etiqueta **Open in panel**) y, después, **Terminal**.
|
||||
|
||||
|
||||
|
||||
2. Introduce el comando siguiente en la ventana de terminal para iniciar el servidor de desarrollo de la aplicación web:
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
3. Cuando se inicie el servidor, lo que solo tardará un momento, abre una ventana del navegador.
|
||||
4. Ve a http://localhost:4321.
|
||||
5. Ahora deberías ver valoraciones por estrellas en todos los juegos de la página de inicio.
|
||||
6. Vuelve a la ventana de terminal.
|
||||
7. Selecciona <kbd>Ctrl</kbd>+<kbd>C</kbd> para detener el servidor de desarrollo.
|
||||
|
||||
## Abrir y combinar tu primera solicitud de incorporación de cambios
|
||||
|
||||
El cambio tiene buen aspecto; ha llegado el momento de publicarlo. Pedirás al agente que abra una solicitud de incorporación de cambios y, después, la revisarás y combinarás en github.com. Por ahora, gestionarás este proceso de forma manual. En una próxima lección descubrirás cómo Copilot puede encargarse automáticamente de parte del trabajo.
|
||||
|
||||
1. En la esquina superior derecha, selecciona **Create PR**.
|
||||
2. Si se solicita, selecciona **Sign in with your browser** y sigue las indicaciones para autenticarte.
|
||||
3. Copilot comenzará a crear la solicitud de incorporación de cambios.
|
||||
|
||||
Una vez creada, Copilot supervisará los flujos de trabajo del repositorio que deban ejecutarse. Después de unos instantes, el botón de la esquina superior derecha cambiará a **Ready to merge**. Esto indica que la solicitud está lista para combinarse.
|
||||
|
||||
4. Selecciona la burbuja **PR** situada justo encima del chat para abrir la solicitud en el panel de revisión. Puedes revisarla aquí según sea necesario.
|
||||
5. Cuando esté lista, selecciona **Ready to merge**.
|
||||
6. Selecciona **Merge pull request** en el nuevo cuadro de diálogo para combinar la solicitud.
|
||||
|
||||
Ya has publicado una nueva funcionalidad en el sitio web.
|
||||
|
||||
## Resumen y pasos siguientes
|
||||
|
||||
Has iniciado tu primera sesión de agente y publicado tu primer cambio. En concreto:
|
||||
|
||||
- has iniciado una sesión de agente y aprendido cómo se estructuran las sesiones.
|
||||
- has indicado al agente que realice un cambio pequeño y específico en las tarjetas de los juegos.
|
||||
- has revisado el cambio en la vista de diferencias del espacio de trabajo.
|
||||
- has ejecutado la aplicación en local para confirmar la valoración por estrellas en el navegador.
|
||||
- has abierto una solicitud de incorporación de cambios y la has combinado personalmente en github.com.
|
||||
|
||||
A continuación, utilizarás la aplicación para añadir al repositorio un estándar de instrucciones personalizadas a partir de una de las incidencias de la lista de trabajo pendiente. Continúa con la [Lección 3 - Guiar a Copilot con instrucciones personalizadas][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Trabajar con sesiones de agente en la aplicación GitHub Copilot][agent-sessions]
|
||||
- [Acerca de la aplicación GitHub Copilot][about-copilot-app]
|
||||
- [Gestionar incidencias y solicitudes de incorporación de cambios con la aplicación GitHub Copilot][managing-issues-prs]
|
||||
|
||||
[prior-lesson]: /es-es/learning-hub/copilot-workshops/app/1-install-copilot-app/#instalar-y-configurar-la-aplicacion-github-copilot
|
||||
[next-lesson]: /es-es/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+165
@@ -0,0 +1,165 @@
|
||||
---
|
||||
title: "Lección 3 - Guiar a Copilot con instrucciones personalizadas"
|
||||
description: "Utiliza la aplicación GitHub Copilot para añadir al repositorio un estándar de instrucciones personalizadas a partir de una incidencia de la lista de trabajo pendiente y combina el cambio como una solicitud de incorporación de cambios."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
El contexto es fundamental al trabajar con IA generativa. Si una tarea debe realizarse de una forma concreta o Copilot necesita conocer información de fondo, conviene que ese contexto esté disponible. Una de las herramientas más potentes para proporcionarlo son los [archivos de instrucciones][instruction-files], que describen no solo *qué* código quieres, sino también *cómo* debe estructurarse. En esta lección añadirás un estándar de documentación al repositorio y lo harás como realizarás la mayor parte del trabajo a partir de ahora: comenzarás desde una incidencia de la lista de trabajo pendiente y dejarás que el agente realice el cambio.
|
||||
|
||||
En esta lección:
|
||||
|
||||
- explorarás cómo llegan al agente las instrucciones del repositorio y los archivos de instrucciones limitados por ruta.
|
||||
- iniciarás una sesión desde la incidencia sobre instrucciones de la lista de trabajo pendiente.
|
||||
- pedirás al agente que añada un estándar de documentación a `.github/copilot-instructions.md`.
|
||||
- revisarás el cambio y lo combinarás como una solicitud de incorporación de cambios.
|
||||
|
||||
## Escenario
|
||||
|
||||
Como cualquier buen equipo de desarrollo, Tailspin Toys dispone de directrices y requisitos para las prácticas de desarrollo. Entre ellos se incluyen:
|
||||
|
||||
- Se debe añadir documentación al código mediante comentarios de documentación TSDoc.
|
||||
- El formato se debe documentar y aplicar mediante linting.
|
||||
|
||||
Mediante los archivos de instrucciones, garantizarás que Copilot disponga de la información adecuada para realizar las tareas conforme a estas prácticas.
|
||||
|
||||
## Archivos de instrucciones
|
||||
|
||||
Las instrucciones personalizadas permiten proporcionar contexto y preferencias a Copilot para que comprenda mejor el estilo y los requisitos de programación. Esta potente funcionalidad ayuda a orientar a Copilot para obtener sugerencias y fragmentos de código más pertinentes. Puedes especificar las convenciones de programación, las bibliotecas e incluso los tipos de comentarios que prefieres incluir en el código. También puedes crear instrucciones para todo el repositorio o para tipos de archivo concretos, con contexto específico para una tarea.
|
||||
|
||||
Hay dos tipos de archivos de instrucciones:
|
||||
|
||||
- `.github/copilot-instructions.md`, un único archivo de instrucciones que se envía a Copilot con **cada** solicitud del repositorio. Debe contener información del proyecto que sea pertinente para la mayoría de las solicitudes de chat o CLI enviadas a Copilot, como la pila tecnológica, una descripción general de lo que se está creando, procedimientos recomendados y otras directrices globales.
|
||||
- Los archivos `.github/instructions/*.instructions.md` se pueden crear para tareas o tipos de archivo concretos. Puedes utilizarlos para proporcionar directrices para lenguajes específicos, como TypeScript o Astro, o para tareas como crear un componente de interfaz de usuario o un nuevo conjunto de pruebas unitarias.
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot admite otros estándares para incorporar instrucciones mediante AGENTS.md, CLAUDE.md y GEMINI.md, de modo que siempre disponga del contexto adecuado.
|
||||
|
||||
### Procedimientos recomendados para gestionar archivos de instrucciones
|
||||
|
||||
Una explicación completa sobre la creación de archivos de instrucciones queda fuera del alcance del taller. No obstante, los ejemplos del proyecto de muestra presentan un enfoque representativo. En términos generales:
|
||||
|
||||
- Mantén las instrucciones de `copilot-instructions.md` centradas en directrices de ámbito de proyecto, como una descripción de lo que se está creando, la estructura del proyecto y los estándares globales de programación.
|
||||
- Utiliza archivos `*.instructions.md` para proporcionar instrucciones específicas para tipos de archivo, como pruebas unitarias, componentes de Astro o la capa de datos, o para tareas concretas.
|
||||
- Utiliza lenguaje natural. Redacta directrices claras. Proporciona ejemplos de cómo debe y no debe ser el código.
|
||||
|
||||
No existe una única forma de crear archivos de instrucciones, del mismo modo que no existe una única forma de utilizar la IA. La experimentación te permitirá descubrir qué funciona mejor para tu proyecto.
|
||||
|
||||
> [!TIP]
|
||||
> Todos los proyectos que utilicen GitHub Copilot deberían disponer de una colección sólida de archivos de instrucciones. Al explorar los de este proyecto, observarás que hay archivos de instrucciones para muchos tipos de archivos de código.
|
||||
>
|
||||
> ¿Buscas plantillas o un punto de partida? Explora [Awesome Copilot][awesome-copilot], un repositorio repleto de archivos de instrucciones, agentes personalizados y otros recursos.
|
||||
|
||||
## Explorar los archivos de instrucciones personalizadas del proyecto
|
||||
|
||||
Dedica un momento a leer los archivos de instrucciones incluidos en este repositorio: hay un archivo principal `copilot-instructions.md` y una colección de archivos `*.instructions.md` para distintas tareas. Ábrelos en el editor o en la interfaz web de GitHub.
|
||||
|
||||
1. Si el panel de revisión aún no está visible, selecciona **Toggle review panel** en la esquina superior derecha para abrirlo.
|
||||
|
||||
|
||||
|
||||
2. Selecciona **+** para añadir un elemento nuevo al panel de revisión.
|
||||
3. Selecciona **File**.
|
||||
4. Busca `copilot-instructions.md`.
|
||||
5. Selecciona `copilot-instructions.md` en la lista de archivos para abrirlo.
|
||||
6. Explora el archivo. Observa la breve descripción del proyecto y secciones como **Agent notes**, **Code standards**, **Scripts** y **Repository Structure**. En **Code standards**, fíjate en las directrices anidadas de **GitHub Actions Workflows**. Se aplican a cualquier interacción con Copilot.
|
||||
7. Selecciona **Show folder view** para abrir el navegador de carpetas.
|
||||
|
||||
|
||||
|
||||
8. Ve a la carpeta `.github/instructions` y explora los archivos. Observa que hay instrucciones para archivos de Astro, la capa de datos de Drizzle, pruebas y otros elementos.
|
||||
9. Abre `.github/instructions/unit-tests.instructions.md`. Observa el campo `applyTo` de la parte superior: establece un patrón glob, relativo a la raíz del repositorio, que determina a qué archivos se aplican las instrucciones. En este caso, coincidirá cualquier archivo de prueba de TypeScript, por ejemplo, uno que cumpla `**/*.test.ts`.
|
||||
10. Examina las instrucciones específicas para crear pruebas unitarias en este proyecto.
|
||||
11. Por último, abre `.github/instructions/drizzle.instructions.md` y desplázate hasta el final. Observa los vínculos a otros archivos de instrucciones, como `unit-tests.instructions.md`, y a archivos existentes del proyecto. De este modo puedes dividir conjuntos de instrucciones grandes en archivos más pequeños y reutilizables, y señalar a Copilot ejemplos que debe seguir al generar código. Las rutas son relativas al archivo de instrucciones, no a la raíz del repositorio.
|
||||
|
||||
> [!NOTE]
|
||||
> La sección **Code formatting requirements** de `copilot-instructions.md` documenta los estándares de programación del proyecto, pero todavía no exige documentación dentro del código. En los pasos siguientes añadirás reglas para comentarios de documentación TSDoc y comentarios de cabecera de archivo.
|
||||
|
||||
## Empezar desde la incidencia sobre instrucciones
|
||||
|
||||
En la lección anterior iniciaste una sesión con una indicación directa. Sin embargo, la mayor parte del trabajo comienza con una incidencia. Vamos a crear una sesión basada en una incidencia presentada para actualizar los archivos de instrucciones y, después, solicitaremos la actualización.
|
||||
|
||||
> [!NOTE]
|
||||
> Como los archivos de instrucciones influyen mucho en el código que genera Copilot, debes asegurarte de que lo orienten con claridad. Pedir a Copilot que cree una primera versión, como harás en esta lección, es un buen enfoque, siempre que después la revises para confirmar que las actualizaciones cumplen tus requisitos.
|
||||
|
||||
1. Selecciona **My work** en la barra lateral.
|
||||
2. Selecciona la incidencia titulada **Update our repository coding standards** para abrirla.
|
||||
3. Selecciona **New session** en la esquina superior derecha para iniciar una sesión basada en la incidencia.
|
||||
|
||||
|
||||
|
||||
4. Utiliza la indicación siguiente para pedir a Copilot que actualice los archivos de instrucciones de acuerdo con los requisitos documentados en la incidencia:
|
||||
|
||||
```plaintext
|
||||
Following this issue, make the updates to the instructions files in this project to meet the requirements documented. Don't create the PR quite yet!
|
||||
```
|
||||
|
||||
Copilot realizará las actualizaciones.
|
||||
|
||||
## Revisar el cambio
|
||||
|
||||
Vamos a leer las actualizaciones de Copilot y también a pedirle un ejemplo del código que generará a partir de las instrucciones actualizadas.
|
||||
|
||||
1. Selecciona **Changes** en la esquina superior derecha para abrir los cambios de código.
|
||||
|
||||
|
||||
|
||||
2. Revisa el archivo de instrucciones actualizado. Confirma que contiene las directrices para añadir documentación y comentarios al código.
|
||||
|
||||
> [!NOTE]
|
||||
> Como la IA es probabilística y no determinista, el texto exacto puede variar.
|
||||
|
||||
3. Utiliza la indicación siguiente para pedir a Copilot que cree un ejemplo del código que generará ahora:
|
||||
|
||||
```plaintext
|
||||
Do not make any updates, but show me what the code would look like. Based on the new instructions, if I asked Copilot to create a new library component to return all Publishers what would that code look like?
|
||||
```
|
||||
|
||||
4. Revisa el código que propone Copilot. Observa los comentarios de documentación TSDoc y el comentario de cabecera de archivo que incluye, exactamente lo que solicitan las instrucciones actualizadas.
|
||||
|
||||
Ya has actualizado los archivos de instrucciones del proyecto y has comprobado el efecto que tendrán.
|
||||
|
||||
## Abrir y combinar la solicitud de incorporación de cambios
|
||||
|
||||
Los archivos de instrucciones pasan a ser recursos del repositorio y, por tanto, se comparten con el resto del equipo. Vamos a crear una solicitud de incorporación de cambios con nuestro trabajo, igual que haríamos con cualquier otro recurso.
|
||||
|
||||
1. En la esquina superior derecha, selecciona **Create PR**.
|
||||
2. Si se solicita, selecciona **Sign in with your browser** y sigue las indicaciones para autenticarte.
|
||||
3. Copilot comenzará a crear la solicitud de incorporación de cambios.
|
||||
|
||||
Una vez creada, Copilot supervisará los flujos de trabajo del repositorio que deban ejecutarse. Después de unos instantes, el botón de la esquina superior derecha cambiará a **Ready to merge**. Esto indica que la solicitud está lista para combinarse.
|
||||
|
||||
4. Selecciona **Ready to merge**.
|
||||
5. Selecciona **Merge pull request** en el nuevo cuadro de diálogo para combinar la solicitud.
|
||||
|
||||
> [!NOTE]
|
||||
> Una vez combinado el estándar en la rama predeterminada, pasa a formar parte del proyecto para todo el equipo y para cada sesión nueva. Cuando inicies la sesión de filtrado de la siguiente lección desde una rama predeterminada actualizada, el agente seguirá este estándar automáticamente. Verás que el código TypeScript que genera incluye comentarios de documentación TSDoc sin que se lo pidas: una demostración pequeña pero real de cómo las instrucciones determinan el código generado.
|
||||
|
||||
## Resumen y pasos siguientes
|
||||
|
||||
Has explorado cómo la aplicación obtiene contexto de los archivos de instrucciones y, después, has utilizado una sesión para añadir y combinar un estándar para todo el repositorio. En concreto:
|
||||
|
||||
- has explorado el archivo `copilot-instructions.md` del repositorio y los archivos `*.instructions.md` limitados por ruta.
|
||||
- has iniciado una sesión desde la incidencia sobre instrucciones de la lista de trabajo pendiente.
|
||||
- has pedido al agente que añada un estándar de documentación a `.github/copilot-instructions.md`.
|
||||
- has revisado el cambio y lo has combinado como una solicitud de incorporación de cambios.
|
||||
|
||||
A continuación, crearás la funcionalidad de filtrado en una sesión nueva y comprobarás cómo adopta el estándar que acabas de combinar. Continúa con la [Lección 4 - Crear una funcionalidad con Autopilot][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Archivos de instrucciones para personalizar GitHub Copilot][instruction-files]
|
||||
- [Personalizar la aplicación GitHub Copilot][customize-app]
|
||||
- [Procedimientos recomendados para crear instrucciones personalizadas][instructions-best-practices]
|
||||
- [Awesome Copilot: colección de archivos de instrucciones y otros recursos][awesome-copilot]
|
||||
|
||||
[next-lesson]: /es-es/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[instruction-files]: https://docs.github.com/copilot/customizing-copilot/about-customizing-github-copilot-chat-responses
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[awesome-copilot]: https://awesome-copilot.github.com/
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+186
@@ -0,0 +1,186 @@
|
||||
---
|
||||
title: "Lección 4 - Crear una funcionalidad con Autopilot"
|
||||
description: "Utiliza los modos Plan y Autopilot de la aplicación GitHub Copilot para crear una funcionalidad de filtrado estática en el cliente, comprobar que hereda el estándar de documentación y verificarla con una habilidad de agente."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Hasta ahora hemos realizado un par de pequeñas actualizaciones en el proyecto. Sin embargo, los cambios más amplios requieren un proceso más sólido. La aplicación GitHub Copilot está diseñada para integrarse en nuestro flujo actual y garantizar que creemos lo correcto de la forma adecuada. Esta es la primera de tres lecciones en las que seguirás un proceso de desarrollo habitual: empezarás por utilizar una incidencia para generar una funcionalidad nueva y una habilidad de agente para ejecutar las pruebas de validación y los linters.
|
||||
|
||||
En esta lección:
|
||||
|
||||
- iniciarás una sesión nueva desde la incidencia sobre filtrado.
|
||||
- utilizarás el modo **Plan** para planificar la funcionalidad y, después, **Autopilot** para crearla.
|
||||
- confirmarás que el código generado sigue el estándar de documentación que combinaste anteriormente.
|
||||
- verificarás el trabajo con la habilidad `quality-checks` del proyecto.
|
||||
|
||||
## Escenario
|
||||
|
||||
La página de inicio muestra todos los juegos, pero los visitantes no pueden restringir la lista. La incidencia sobre filtrado solicita que puedan filtrar los juegos por **categoría** y **editor**. Vamos a utilizar Copilot para implementar esta funcionalidad.
|
||||
|
||||
## Contexto
|
||||
|
||||
Introducir agentes de programación con IA en el flujo de desarrollo no cambia los principios fundamentales. De hecho, adquieren aún más importancia. La mayoría de los desarrolladores siguen un flujo similar al siguiente:
|
||||
|
||||
1. Abrir una incidencia que detalle lo que debe hacerse.
|
||||
2. Crear un plan de lo que debe desarrollarse.
|
||||
3. Crear y revisar el código.
|
||||
4. Ejecutar las pruebas para validar el código.
|
||||
5. Validar manualmente la nueva funcionalidad.
|
||||
6. Crear una solicitud de incorporación de cambios (PR).
|
||||
7. Una vez revisado el código y completado correctamente el proceso de integración continua, combinarlo.
|
||||
|
||||
> [!NOTE]
|
||||
> Los detalles concretos variarán según el equipo y la organización, pero la mayoría de los procesos serán una variante del flujo anterior.
|
||||
|
||||
Al mantener este enfoque estándar, te aseguras de que el código generado por IA cumpla los requisitos establecidos y pase por el mismo proceso de validación que el código escrito manualmente.
|
||||
|
||||
## Modos de sesión
|
||||
|
||||
El **modo de sesión** controla el grado de autonomía del agente. Puedes establecerlo en el menú desplegable situado debajo del campo de indicaciones y cambiarlo en cualquier momento:
|
||||
|
||||
- **Interactive**: trabajas junto con el agente. El agente sugiere cambios y espera tus indicaciones antes de continuar.
|
||||
- **Plan**: el agente crea primero un plan. Revisas y apruebas el plan antes de que el agente lo ejecute.
|
||||
- **Autopilot**: el agente trabaja de forma totalmente autónoma, escribe código, ejecuta pruebas e itera sin esperar indicaciones.
|
||||
|
||||
## Planificar la funcionalidad de filtrado
|
||||
|
||||
El mejor momento para detectar un posible problema es antes de escribir código, y una breve planificación previa es la mejor forma de hacerlo. Al planificar con Copilot, le pedirás que genere una serie de pasos y documente el enfoque que seguirá. Después podrás revisar el plan y proponer mejoras antes de permitir que Copilot genere el código a partir de él.
|
||||
|
||||
Vamos a abrir la incidencia, iniciar una sesión nueva y crear un plan. Para ello, cambiaremos al modo Plan y enviaremos la solicitud.
|
||||
|
||||
1. Selecciona **My work** en la pestaña de navegación.
|
||||
2. Selecciona la incidencia titulada **Allow users to filter games by category and publisher**.
|
||||
3. Selecciona **New session** en la esquina superior derecha.
|
||||
|
||||
|
||||
|
||||
4. Selecciona <kbd>Shift</kbd>+<kbd>Tab</kbd> hasta que el modo muestre **Plan**.
|
||||
|
||||
|
||||
|
||||
5. Envía la indicación siguiente. La incidencia sobre filtrado ya está en el contexto de esta sesión porque la has iniciado desde ella:
|
||||
|
||||
```plaintext
|
||||
Plan the work based on the requirements documented in the issue. Please ask any clarifying questions you might have as you build the plan.
|
||||
```
|
||||
|
||||
6. El agente puede plantear preguntas de seguimiento mientras crea el plan. Respóndelas según cómo desarrollarías la funcionalidad.
|
||||
|
||||
> [!NOTE]
|
||||
> Como Copilot es probabilístico, las preguntas de seguimiento exactas pueden variar. Incluso es posible que no formule ninguna. Es completamente normal.
|
||||
|
||||
7. Cuando termine, Copilot ofrecerá un resumen del plan. Revísalo. Debería proponer crear consultas, añadir controles de filtrado y, por supuesto, pruebas. Si quieres, proporciona comentarios para perfeccionarlo; el agente incorporará las sugerencias en una versión nueva.
|
||||
|
||||
## Crear la funcionalidad con Autopilot
|
||||
|
||||
Con el plan preparado, vamos a dejar que Copilot cree la implementación.
|
||||
|
||||
1. En la lista de opciones del cuadro de diálogo **Plan summary**, selecciona la opción más parecida a **Approve and implement with autopilot**.
|
||||
|
||||
Copilot comenzará a trabajar en la implementación.
|
||||
|
||||
> [!NOTE]
|
||||
> Si Copilot no empieza a crear automáticamente el código necesario, puedes pedírselo con una indicación como "Go ahead and start building out the plan!".
|
||||
>
|
||||
> Las actualizaciones necesarias tardarán varios minutos. El agente edita y crea archivos, escribe y ejecuta pruebas e itera. Es un buen momento para repasar lo que has explorado hasta ahora o tomar algo.
|
||||
|
||||
## Revisar los cambios
|
||||
|
||||
Todo el código generado por IA debe revisarse antes de combinarlo. Vamos a revisar el código y ejecutar el sitio para comprobar que todo funciona correctamente.
|
||||
|
||||
1. Selecciona **Changes** en la esquina superior derecha para abrir los cambios de código.
|
||||
|
||||
|
||||
|
||||
2. Revisa los cambios. Deberías ver nuevos archivos de TypeScript y Astro, además de archivos de prueba. Observa que las nuevas funciones auxiliares incluyen comentarios de documentación TSDoc y un comentario de cabecera de archivo: el estándar de documentación que combinaste en la Lección 3, aplicado automáticamente sin solicitarlo.
|
||||
3. En el panel de revisión situado a la derecha de la aplicación Copilot, selecciona **Terminal**. Si no aparece el botón **Terminal**, selecciona **+** (con la etiqueta **Open in panel**) y, después, **Terminal**.
|
||||
|
||||
|
||||
|
||||
4. Introduce el comando siguiente en la ventana de terminal para iniciar el servidor de desarrollo de la aplicación web:
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
5. Cuando se inicie el servidor, lo que solo tardará un momento, abre una ventana del navegador.
|
||||
6. Ve a http://localhost:4321.
|
||||
7. Ahora deberías ver filtros en la página de inicio.
|
||||
8. Si algo no parece correcto, puedes pedir a Copilot que lo actualice.
|
||||
9. Cuando estés conforme, vuelve a la ventana de terminal.
|
||||
10. Selecciona <kbd>Ctrl</kbd>+<kbd>C</kbd> para detener el servidor de desarrollo.
|
||||
|
||||
## Verificar el trabajo con la habilidad quality-checks
|
||||
|
||||
Podrías revisar visualmente las diferencias y dar el trabajo por terminado, pero el equipo ha definido un nivel de calidad y una forma repetible de comprobarlo.
|
||||
|
||||
Las **habilidades de agente** permiten proporcionar a Copilot directrices para realizar tareas repetibles, como ejecutar pruebas, generar compilaciones o crear solicitudes de incorporación de cambios. Una habilidad es una carpeta con instrucciones, scripts y recursos que el agente puede cargar bajo demanda. [Agent Skills es un estándar abierto][agent-skills-repo] que utilizan distintos agentes, por lo que la misma habilidad funciona en Copilot Chat en modo agente, el agente en la nube de Copilot, Copilot CLI y la aplicación GitHub Copilot.
|
||||
|
||||
Las habilidades se almacenan en la carpeta `.github/skills` de un proyecto o de forma global en `~/.copilot/skills`. Cada habilidad es una carpeta que contiene un archivo `SKILL.md` con frontmatter YAML, formado por un `name` y una `description`, seguido de las instrucciones en Markdown:
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: quality-checks
|
||||
description: Run the project's test suites and linter to verify code changes are ready to commit, push, or merge.
|
||||
---
|
||||
```
|
||||
|
||||
Las habilidades también pueden incluir subcarpetas con scripts, recursos y material de referencia. La estructura completa se describe en la [especificación de habilidades de agente][agent-skills-spec].
|
||||
|
||||
> [!TIP]
|
||||
> Las habilidades se cargan de forma dinámica. El agente decide cuál se aplica según el campo `description`; una descripción clara y específica del escenario marca la diferencia entre una habilidad que se utiliza y otra que se ignora.
|
||||
|
||||
## Explorar la habilidad quality-checks
|
||||
|
||||
Vamos a explorar la habilidad para ver qué hace.
|
||||
|
||||
1. Si el panel de revisión aún no está visible, selecciona **Toggle review panel** en la esquina superior derecha para abrirlo.
|
||||
|
||||
|
||||
|
||||
2. Selecciona **+** para añadir un elemento nuevo al panel de revisión.
|
||||
3. Selecciona **File**.
|
||||
4. Busca `SKILL.md`.
|
||||
5. Selecciona `SKILL.md .github/skills/quality-checks` en la lista de archivos para abrirlo.
|
||||
6. Observa los campos `name` y `description`. La descripción indica al agente *cuándo* debe utilizar la habilidad: siempre que sea necesario probar, analizar con un linter o verificar cambios de código antes de una confirmación, un envío o una combinación.
|
||||
7. Lee la habilidad. Observa que documenta qué script ejecuta cada conjunto de pruebas, como las pruebas unitarias, las pruebas de un extremo a otro de Playwright y ESLint, en qué orden y cómo depurar errores habituales. Así, el agente ejecuta las comprobaciones según el proceso del equipo en lugar de adivinarlo.
|
||||
|
||||
## Ejecutar las comprobaciones
|
||||
|
||||
En la misma sesión de filtrado, pide al agente que verifique el trabajo. No mencionarás el nombre de la habilidad; el agente la identificará a partir de la solicitud.
|
||||
|
||||
1. Vuelve a la aplicación Copilot.
|
||||
2. Llama directamente a la habilidad mediante el comando de barra diagonal `/quality-checks` y selecciona <kbd>Enter</kbd>.
|
||||
3. Siguiendo la habilidad, el agente ejecutará las pruebas unitarias, el linter y las pruebas de un extremo a otro, y comunicará los resultados. Si algo falla, pídele que corrija el problema y vuelva a ejecutar las comprobaciones hasta que todo se complete correctamente.
|
||||
4. **Mantén abierta esta sesión.** En la siguiente lección añadirás el servidor MCP de Playwright y lo utilizarás para comprobar la funcionalidad de filtrado en un navegador real.
|
||||
|
||||
## Resumen y pasos siguientes
|
||||
|
||||
Has creado una funcionalidad real de principio a fin y la has verificado según el nivel de calidad del equipo. En concreto:
|
||||
|
||||
- has iniciado una sesión nueva desde la incidencia sobre filtrado en un proyecto actualizado.
|
||||
- has utilizado el modo Plan para planificar la funcionalidad y Autopilot para crearla.
|
||||
- has confirmado que la función auxiliar generada sigue el estándar de documentación que combinaste en la Lección 3.
|
||||
- has verificado el trabajo con la habilidad `quality-checks`.
|
||||
|
||||
A continuación, conectarás el servidor MCP de Playwright y pedirás al agente que explore la funcionalidad de filtrado en un navegador real. Continúa con la [Lección 5 - Realizar pruebas con el servidor MCP de Playwright][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Trabajar con sesiones de agente en la aplicación GitHub Copilot][agent-sessions]
|
||||
- [Acerca de Agent Skills][about-agent-skills]
|
||||
- [Personalizar la aplicación GitHub Copilot][customize-app]
|
||||
- [Acerca de los entornos aislados locales y en la nube para GitHub Copilot][sandboxes]
|
||||
|
||||
[ex0]: /es-es/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex2]: /es-es/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /es-es/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[next-lesson]: /es-es/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-agent-skills]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[agent-skills-repo]: https://github.com/agentskills/agentskills
|
||||
[agent-skills-spec]: https://agentskills.io/specification
|
||||
@@ -0,0 +1,86 @@
|
||||
---
|
||||
title: "Lección 5 - Realizar pruebas con el servidor MCP de Playwright"
|
||||
description: "Añade el servidor MCP de Playwright a la aplicación GitHub Copilot y pide al agente que pruebe manualmente la funcionalidad de filtrado en un navegador real."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
En la lección anterior creaste y verificaste la funcionalidad de filtrado con el conjunto de pruebas automatizadas del proyecto. Las pruebas automatizan la validación del código, pero permitir que el agente confirme el comportamiento también resulta muy útil. Así puede responder a los problemas que detecte en la interfaz de usuario que está creando. Vamos a explorar cómo MCP proporciona a los agentes de IA acceso a capacidades externas y a añadir el servidor MCP de Playwright para que Copilot pueda interactuar directamente con el sitio que estás desarrollando.
|
||||
|
||||
En esta lección:
|
||||
|
||||
- comprenderás qué es Model Context Protocol (MCP) y cómo lo utiliza la aplicación GitHub Copilot.
|
||||
- añadirás el servidor MCP de Playwright desde la configuración de la aplicación.
|
||||
- pedirás al agente que controle un navegador y explore la funcionalidad de filtrado.
|
||||
|
||||
## Escenario
|
||||
|
||||
Aunque las pruebas unitarias y de un extremo a otro son importantes, validar las actualizaciones de la interfaz de usuario requiere interactuar con ella. Quieres que Copilot pueda utilizar el sitio web en el que trabajas como lo haría un usuario para automatizar aún más los cambios y aumentar la confianza en que las actualizaciones funcionan según lo previsto.
|
||||
|
||||
## ¿Qué es Model Context Protocol (MCP)?
|
||||
|
||||
[Model Context Protocol (MCP)][mcp-blog-post] proporciona a los agentes de IA una forma de comunicarse con herramientas y servicios externos. Mediante MCP, los agentes de IA pueden comunicarse con ellos en tiempo real. Esto les permite acceder a información actualizada mediante recursos y realizar acciones en tu nombre mediante herramientas.
|
||||
|
||||
Se accede a estas herramientas y recursos a través de un servidor MCP, que actúa como puente entre el agente de IA y las herramientas y servicios externos. El servidor MCP gestiona la comunicación entre el agente de IA y las herramientas externas, como API existentes o herramientas locales, por ejemplo, paquetes NPM. Cada servidor MCP representa un conjunto diferente de herramientas y recursos a los que puede acceder el agente de IA.
|
||||
|
||||
Dos servidores MCP populares son:
|
||||
|
||||
- [**GitHub MCP Server**](https://github.com/github/github-mcp-server): proporciona acceso a un conjunto de API para gestionar repositorios de GitHub. Permite al agente de IA realizar acciones como crear repositorios, actualizar los existentes y gestionar incidencias y solicitudes de incorporación de cambios.
|
||||
- [**Playwright MCP Server**][playwright-mcp-server]: proporciona capacidades de automatización del navegador mediante Playwright. Permite al agente de IA realizar acciones como visitar páginas web, completar formularios y seleccionar botones.
|
||||
|
||||
Hay muchos otros servidores MCP que proporcionan acceso a distintas herramientas y recursos. GitHub aloja un [registro de MCP](https://github.com/mcp) para facilitar su descubrimiento y las contribuciones al ecosistema.
|
||||
|
||||
> [!CAUTION]
|
||||
> Trata los servidores MCP como cualquier otra dependencia del proyecto. Antes de utilizar uno, revisa atentamente su código fuente, verifica el editor y considera las implicaciones de seguridad. Utiliza únicamente servidores MCP de confianza y ten cuidado al conceder acceso a recursos u operaciones confidenciales.
|
||||
|
||||
## Añadir el servidor MCP de Playwright
|
||||
|
||||
Los servidores MCP se añaden y gestionan desde la configuración de la aplicación. La aplicación incluye un catálogo de servidores populares, por lo que el [servidor MCP de Playwright][playwright-mcp-server] está a solo un par de selecciones.
|
||||
|
||||
1. Selecciona <kbd>Ctrl</kbd>+<kbd>,</kbd> para abrir la página de configuración de la aplicación Copilot.
|
||||
2. Selecciona **MCP servers**.
|
||||
3. En el cuadro de búsqueda, escribe `Playwright`.
|
||||
4. Selecciona **Playwright** en la lista de **Popular MCP servers**.
|
||||
5. Selecciona **Add server** para añadirlo a la lista de servidores MCP disponibles.
|
||||
6. Selecciona <kbd>Esc</kbd> para cerrar el cuadro de diálogo de configuración.
|
||||
|
||||
Ya has añadido el servidor MCP de Playwright.
|
||||
|
||||
## Pedir a Copilot que explore la funcionalidad mediante Playwright
|
||||
|
||||
Vamos a pedir a Copilot que pruebe manualmente la funcionalidad mediante el servidor MCP de Playwright.
|
||||
|
||||
1. Utiliza la indicación siguiente para pedir a Copilot que valide la nueva funcionalidad:
|
||||
|
||||
```plaintext
|
||||
Start the dev server then use the Playwright MCP server to validate the functionality you just added exists. Use the details in the issue to ensure the newly added behavior matches the specs.
|
||||
```
|
||||
|
||||
Copilot iniciará un navegador mediante el servidor MCP de Playwright, recorrerá cada paso y comunicará lo que encuentre. Verás cómo abre un navegador en el sistema para realizar las tareas.
|
||||
|
||||
2. Compara el resumen con los criterios de aceptación de la incidencia. Si algo no parece correcto, formula preguntas de seguimiento o pide al agente que corrija el código antes de abrir una solicitud de incorporación de cambios.
|
||||
3. Mantén abierta esta sesión, ya que la completaremos en la siguiente lección.
|
||||
|
||||
Copilot también ha validado la funcionalidad en el navegador mediante la exploración de la característica como lo haría un usuario.
|
||||
|
||||
## Resumen y pasos siguientes
|
||||
|
||||
Has utilizado el servidor MCP de Playwright para explorar la funcionalidad en un navegador real desde la aplicación GitHub Copilot. En resumen:
|
||||
|
||||
- has aprendido qué es Model Context Protocol (MCP) y cómo la aplicación pone a disposición las herramientas MCP.
|
||||
- has añadido el servidor MCP de Playwright desde la configuración de la aplicación.
|
||||
- has pedido al agente que controle un navegador y explore la funcionalidad de filtrado.
|
||||
|
||||
La funcionalidad está creada, verificada y en funcionamiento. Ahora toca publicarla mediante **Agent Merge**, que abrirá y combinará la solicitud de incorporación de cambios. Continúa con la [Lección 6 - Combinar cambios con Agent Merge][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [¿Qué es MCP y por qué todo el mundo habla de él?][mcp-blog-post]
|
||||
- [Servidor MCP de Playwright de Microsoft][playwright-mcp-server]
|
||||
- [Configurar servidores MCP en la aplicación GitHub Copilot][customize-app]
|
||||
|
||||
[next-lesson]: /es-es/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[mcp-blog-post]: https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/
|
||||
[playwright-mcp-server]: https://github.com/microsoft/playwright-mcp
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
@@ -0,0 +1,67 @@
|
||||
---
|
||||
title: "Lección 6 - Combinar cambios con Agent Merge"
|
||||
description: "Abre la solicitud de incorporación de cambios del filtrado, revísala en My work y deja que Agent Merge corrija los bloqueos y la combine por ti, el nivel más alto de la automatización de combinaciones."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
La funcionalidad de filtrado está creada, verificada y en funcionamiento en un navegador. El último paso es combinarla. Ya has combinado dos cambios en este recorrido; en ambos casos abriste la solicitud de incorporación de cambios y la combinaste personalmente en github.com. Esta vez dejarás que la aplicación se encargue del trabajo con **Agent Merge**, que guía una solicitud durante todo su ciclo de vida desde la aplicación.
|
||||
|
||||
En esta lección:
|
||||
|
||||
- aprenderás qué es Agent Merge y cómo automatiza el ciclo de vida de una combinación.
|
||||
- habilitarás Agent Merge en la sesión de filtrado.
|
||||
- observarás cómo crea la solicitud de incorporación de cambios, ejecuta CI y la combina cuando todo se completa correctamente.
|
||||
|
||||
## Escenario
|
||||
|
||||
En los últimos módulos has explorado distintos niveles de automatización, desde crear código hasta permitir que Copilot valide directamente una interfaz de usuario. Para acelerar aún más el desarrollo, Tailspin Toys quiere averiguar si las solicitudes de incorporación de cambios que ya se han revisado y validado pueden combinarse automáticamente.
|
||||
|
||||
## Introducción a Agent Merge
|
||||
|
||||
**Agent Merge** permite automatizar el último tramo de la incorporación de una solicitud de cambios mediante la aplicación Copilot. Al habilitarlo, la sesión de la aplicación lee la solicitud y resuelve lo que la bloquea: corrige comprobaciones de CI con errores, responde a comentarios de revisión y reorganiza la base cuando es necesario. Después la combina en cuanto GitHub lo permite. Se ejecuta en segundo plano, continúa tras reiniciar la aplicación y se desactiva cuando se combina la solicitud.
|
||||
|
||||
Hasta ahora, tú seleccionabas **Merge pull request** en github.com. Agent Merge transfiere esa responsabilidad al agente para que puedas pasar a la siguiente tarea mientras este guía la solicitud hasta completarla. Sigues revisando y aprobando el trabajo; el agente se ocupa del proceso mecánico final.
|
||||
|
||||
## Utilizar Agent Merge para gestionar la solicitud
|
||||
|
||||
Has revisado el código manualmente, ejecutado pruebas e incluso permitido que Copilot valide la interfaz de usuario. Ha llegado el momento de combinar el código nuevo con el código base. Vamos a permitir que Agent Merge guíe la solicitud durante la integración continua (CI) y la combine.
|
||||
|
||||
1. Vuelve a la sesión que mantuviste abierta en el módulo anterior mientras añadías la funcionalidad de filtrado.
|
||||
2. En la esquina superior derecha, selecciona el menú desplegable situado junto a **Create PR**.
|
||||
3. Selecciona **Agent merge** para habilitar Agent Merge.
|
||||
|
||||
|
||||
|
||||
4. El texto del botón cambia a **Agent merge**.
|
||||
5. Selecciona el botón **Agent merge** para iniciar el proceso.
|
||||
|
||||
La aplicación Copilot comenzará a crear y gestionar la solicitud. Primero explora el proyecto para determinar la mejor forma de crearla y, después, genera la nueva solicitud.
|
||||
|
||||
Transcurridos unos instantes, observarás que Copilot vuelve a trabajar y examina las condiciones de la solicitud, incluido el proceso de CI que ejecuta todas las pruebas del repositorio. Comunicará el estado de las revisiones de otros miembros del equipo, las comprobaciones que deben ejecutarse y si la solicitud puede combinarse.
|
||||
|
||||
6. Permite que Agent Merge combine la solicitud seleccionando el menú desplegable situado junto a **Agent merge** y, después, **Merge pull request**.
|
||||
|
||||
|
||||
|
||||
7. Cuando todos los procesos de CI estén en verde, lo que significa que las pruebas han finalizado correctamente, Copilot combinará la solicitud.
|
||||
|
||||
## Resumen y pasos siguientes
|
||||
|
||||
Has automatizado varias partes del proceso de desarrollo, como la generación, las pruebas y la validación de código, y ahora también el proceso de solicitud de incorporación de cambios. En concreto:
|
||||
|
||||
- has aprendido qué es Agent Merge y cómo automatiza el ciclo de vida de una combinación.
|
||||
- has habilitado Agent Merge en la sesión de filtrado.
|
||||
- has observado cómo crea la solicitud de incorporación de cambios, ejecuta CI y la combina cuando todo se completa correctamente.
|
||||
|
||||
A continuación, explorarás los **lienzos**, una forma más completa de planificar y visualizar el trabajo con el agente. Continúa con la [Lección 7 - Planificar con lienzos][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Gestionar incidencias y solicitudes de incorporación de cambios con la aplicación GitHub Copilot][managing-issues-prs]
|
||||
- [Acerca de la aplicación GitHub Copilot][about-copilot-app]
|
||||
|
||||
[next-lesson]: /es-es/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,127 @@
|
||||
---
|
||||
title: "Lección 7 - Planificar con lienzos"
|
||||
description: "Crea un lienzo compartido y dirigido por agentes en la aplicación GitHub Copilot para planificar y realizar el seguimiento del trabajo junto con el agente."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Hasta ahora has dirigido a los agentes mediante el chat. Sin embargo, gran parte del trabajo no reside en una conversación, sino en un tablero, un documento o una lista de comprobación. Los **lienzos** ofrecen al agente y a ti una superficie compartida para ese tipo de trabajo, directamente en la aplicación. En esta lección crearás un lienzo sencillo para planificar y realizar el seguimiento de la lista de trabajo pendiente que has estado abordando.
|
||||
|
||||
En esta lección:
|
||||
|
||||
- comprenderás qué es un lienzo y cuándo utilizarlo.
|
||||
- crearás un lienzo compartido con un tablero Kanban para clasificar la lista de trabajo pendiente.
|
||||
- guardarás el lienzo en el repositorio y lo combinarás para el equipo.
|
||||
- abrirás el lienzo en una sesión nueva y empezarás a trabajar desde él.
|
||||
|
||||
## Escenario
|
||||
|
||||
Examinar una lista de incidencias puede resultar abrumador, incluso en las mejores circunstancias. Los desarrolladores de Tailspin Toys buscan una herramienta que les permita clasificar las incidencias con rapidez y empezar a trabajar en ellas desde la aplicación Copilot.
|
||||
|
||||
## ¿Qué es un lienzo?
|
||||
|
||||
Un [lienzo][canvas-docs] es una superficie interactiva y compartida para un recurso de trabajo, como un plan, un tablero de clasificación, una lista de comprobación de versiones, un panel o un documento. Aunque el chat resulta adecuado para describir intenciones y razonar sobre ambigüedades, la mayor parte del trabajo se realiza en una *superficie*. Los lienzos permiten colaborar con el agente directamente sobre ella.
|
||||
|
||||
Los lienzos son **bidireccionales**: el agente puede actualizar el lienzo mientras trabaja y tú puedes editar la misma superficie. Cuando creas un lienzo, el agente lo genera a partir de la indicación y el flujo de trabajo, y puedes pedirle que añada, elimine o revise capacidades a medida que avanzas. Una vez creado, el lienzo se abre en el panel derecho de la aplicación.
|
||||
|
||||
Algunos ejemplos habituales son:
|
||||
|
||||
- **Lienzos de Markdown** para planificar el día y priorizar incidencias y solicitudes de incorporación de cambios.
|
||||
- **Tableros Kanban con agentes** en los que las personas y los agentes añaden tarjetas y desplazan el trabajo entre columnas.
|
||||
- **Tableros de clasificación de incidencias** que resumen las incidencias principales y los temas recurrentes de un repositorio.
|
||||
|
||||
## ¿Por qué utilizar un lienzo?
|
||||
|
||||
Utiliza un lienzo cuando una tarea requiera estructura, iteración y verificación, y un chat no sea suficiente. Un lienzo permite:
|
||||
|
||||
- basar el trabajo del agente en un recurso real que se adapte al flujo de trabajo.
|
||||
- orientar o corregir el trabajo directamente en la superficie compartida y, después, permitir que el agente continúe a partir de los cambios.
|
||||
- inspeccionar el progreso como cambios visibles en un recurso, no solo como respuestas del chat.
|
||||
|
||||
## Crear un lienzo para realizar el seguimiento del trabajo
|
||||
|
||||
Has publicado numerosos cambios: la valoración por estrellas, el estándar de documentación y la funcionalidad de filtrado ya están combinados. Sin embargo, todavía quedan elementos en la lista de trabajo pendiente. Vamos a crear el lienzo para clasificar el trabajo con rapidez.
|
||||
|
||||
1. Vuelve a la aplicación GitHub Copilot o ábrela.
|
||||
2. Selecciona **Home screen**.
|
||||
3. Comprueba que `tailspin-toys` esté seleccionado como repositorio.
|
||||
4. En el cuadro de indicaciones, utiliza la indicación siguiente para crear un lienzo que satisfaga nuestras necesidades:
|
||||
|
||||
```plaintext
|
||||
Create a basic Kanban board canvas that allows me to quickly triage work. Highlight the three issues which are most likely to need attention right now, with the remainder in a second section down below. The top three cards should include a description of the issue's content and a justification of why they're at the top of the list. Each issue should have a button that allows me to add it to the current context for the current session so I can get to work on it straightaway.
|
||||
```
|
||||
|
||||
Copilot comenzará a crear el lienzo.
|
||||
|
||||
> [!NOTE]
|
||||
> La creación tardará unos minutos. Como se trata de una tarea compleja, es posible que la primera versión no te satisfaga. Puedes seguir enviando indicaciones hasta crear la herramienta que necesitas.
|
||||
|
||||
## Guardar el lienzo y combinarlo con el repositorio
|
||||
|
||||
Los lienzos pueden convertirse en recursos del repositorio, al igual que los archivos de instrucciones y las habilidades. Vamos a pedir a Copilot que lo añada al repositorio y lo combine para que pueda utilizarlo todo el equipo.
|
||||
|
||||
1. En la misma sesión, pide a Copilot que guarde el lienzo en el repositorio mediante la indicación siguiente:
|
||||
|
||||
```plaintext
|
||||
Let's save this canvas definition to the repository so I can share it with my development team
|
||||
```
|
||||
|
||||
2. Cuando Copilot haya guardado los archivos del lienzo, selecciona el menú desplegable situado junto a **Create PR** en la esquina superior derecha.
|
||||
3. Selecciona **Agent merge** para habilitar Agent Merge.
|
||||
|
||||
|
||||
|
||||
4. El texto del botón cambia a **Agent merge**.
|
||||
5. Selecciona el botón **Agent merge** para iniciar el proceso.
|
||||
|
||||
La aplicación Copilot comenzará a crear y gestionar la solicitud. Primero explora el proyecto para determinar la mejor forma de crearla y, después, la genera.
|
||||
|
||||
Transcurridos unos instantes, observarás que Copilot vuelve a trabajar y examina las condiciones de la solicitud, incluido el proceso de CI que ejecuta todas las pruebas del repositorio. Comunicará el estado de las revisiones de otros miembros del equipo, las comprobaciones que deben ejecutarse y si la solicitud puede combinarse.
|
||||
|
||||
6. Permite que Agent Merge combine la solicitud seleccionando el menú desplegable situado junto a **Agent merge** y, después, **Merge pull request**.
|
||||
|
||||
|
||||
|
||||
7. Espera a que todos los procesos de CI se completen correctamente y se muestren en verde. Cuando terminen, Copilot combinará automáticamente la solicitud.
|
||||
|
||||
Ya has creado un lienzo compartido para el equipo.
|
||||
|
||||
## Trabajar en el lienzo
|
||||
|
||||
Con el lienzo creado, vamos a iniciar una sesión nueva y utilizarlo.
|
||||
|
||||
1. En la aplicación Copilot, selecciona **New session** junto a **tailspin-toys** para iniciar una sesión nueva.
|
||||
2. Pide a Copilot que abra el lienzo de clasificación mediante la indicación siguiente:
|
||||
|
||||
```plaintext
|
||||
Open the triage issues canvas
|
||||
```
|
||||
|
||||
3. El lienzo que has creado debería abrirse en la sesión nueva.
|
||||
4. Selecciona **Add to current context** en una de las incidencias que más te interese.
|
||||
5. Copilot empezará a trabajar en la incidencia.
|
||||
|
||||
Has utilizado un lienzo creado por ti para agilizar el proceso de desarrollo.
|
||||
|
||||
## Resumen y pasos siguientes
|
||||
|
||||
Has creado una superficie compartida en la que puedes colaborar con el agente. En concreto:
|
||||
|
||||
- has aprendido qué son los lienzos y cuándo utilizarlos.
|
||||
- has creado con el agente un lienzo compartido con un tablero Kanban para clasificar incidencias.
|
||||
- has guardado y combinado el lienzo con el repositorio mediante Agent Merge.
|
||||
- has abierto el lienzo en una sesión nueva y lo has utilizado para empezar a trabajar.
|
||||
|
||||
Con la lista de trabajo pendiente organizada, da un paso atrás para revisar todo lo que has creado y descubrir cómo continuar. Continúa con la [Lección 8 - Repaso y pasos siguientes][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Trabajar con extensiones de lienzo en la aplicación GitHub Copilot][canvas-docs]
|
||||
- [Lienzos en Awesome Copilot][awesome-copilot-canvases]
|
||||
- [Acerca de la aplicación GitHub Copilot][about-copilot-app]
|
||||
|
||||
[next-lesson]: /es-es/learning-hub/copilot-workshops/app/8-review/
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[awesome-copilot-canvases]: https://awesome-copilot.github.com/extensions/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,83 @@
|
||||
---
|
||||
title: "Lección 8 - Repaso y pasos siguientes"
|
||||
description: "Repasa el recorrido de la aplicación GitHub Copilot, automatiza el trabajo recurrente y descubre cómo continuar."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Durante las últimas lecciones, has llevado una funcionalidad desde la idea hasta la combinación mediante la aplicación GitHub Copilot. Entre otras cosas, has aprendido a:
|
||||
|
||||
- conectar un repositorio y familiarizarte con el espacio de trabajo de la aplicación y la lista de trabajo pendiente inicial.
|
||||
- iniciar sesiones desde una tarea directa y desde incidencias, y utilizar los modos Plan y Autopilot para controlar cómo trabaja el agente.
|
||||
- orientar al agente con instrucciones personalizadas y una habilidad reutilizable.
|
||||
- probar el trabajo con el servidor MCP de Playwright en un navegador real.
|
||||
- colaborar con el agente en un lienzo compartido.
|
||||
- publicar cambios con niveles crecientes de automatización de combinaciones, desde combinarlos personalmente en github.com hasta permitir que **Agent Merge** incorpore una solicitud de cambios.
|
||||
|
||||
Vamos a automatizar parte del trabajo recurrente, comentar procedimientos recomendados y descubrir cómo continuar.
|
||||
|
||||
## Automatizar el trabajo recurrente
|
||||
|
||||
La aplicación puede ejecutar agentes según una programación o bajo demanda mediante **automatizaciones**, una opción muy útil para tareas rutinarias como clasificar incidencias nuevas o resumir la actividad reciente. Vamos a crear una automatización sencilla y no destructiva.
|
||||
|
||||
1. Selecciona **Automations** en la barra lateral y, después, **New automation**.
|
||||
2. Asigna un nombre, como `Recap my recent work`.
|
||||
3. Elige un desencadenador. **Manual** permite ejecutarla bajo demanda; **On a schedule** la ejecuta automáticamente; **When an issue is created** responde a incidencias nuevas. Para esta lección, elige **Manual**.
|
||||
4. Introduce una indicación de solo lectura para que la automatización no pueda modificar nada, por ejemplo:
|
||||
|
||||
```plaintext
|
||||
Summarize the pull requests merged in this repository over the last week, and list any issues still open in the backlog.
|
||||
```
|
||||
|
||||
5. Elige el proyecto, tu repositorio de Tailspin Toys, y crea la automatización.
|
||||
6. Ejecútala bajo demanda para ver el resultado.
|
||||
|
||||
> [!TIP]
|
||||
> Las automatizaciones pueden ejecutarse en local o en la nube. Habilita **Run in the cloud** y elige las **Tools** que puede utilizar una automatización cuando quieras que se ejecute sin supervisión según una programación. Mantén las automatizaciones programadas bien delimitadas y sin acciones destructivas hasta que confíes en sus resultados.
|
||||
|
||||
## Procedimientos recomendados
|
||||
|
||||
Al utilizar cualquier herramienta de IA, la infraestructura que la rodea determina la calidad de los resultados. Los archivos de instrucciones, las habilidades y los agentes personalizados han contribuido al trabajo de este taller. Invierte en ellos y reutilízalos entre sesiones.
|
||||
|
||||
Adapta el **modo y el modelo** a la tarea. Utiliza **Plan** para razonar sobre un enfoque antes de desarrollar, **Interactive** para mantener el control durante cambios concretos y **Autopilot** solo para tareas aisladas y bien delimitadas. Elige un modelo más rápido para las modificaciones rutinarias y otro más capaz, con mayor esfuerzo de razonamiento, para el trabajo complejo.
|
||||
|
||||
El contexto sigue siendo tan importante como la infraestructura. Describir con claridad *qué* quieres crear, *por qué* y *cómo* cambia sustancialmente el resultado. Los chats rápidos son un buen lugar para delimitar una idea antes de dedicarle una sesión completa.
|
||||
|
||||
## Más opciones para explorar
|
||||
|
||||
Ya conoces el flujo de trabajo principal. Estas son algunas funcionalidades adicionales que merece la pena explorar:
|
||||
|
||||
- **Quick chats** para preguntas rápidas y desechables que no necesitan una sesión completa.
|
||||
- **Rubber duck** para razonar sobre un problema y obtener comentarios pertinentes antes de desarrollar.
|
||||
- [**Agentes personalizados**][custom-agents] para encapsular un rol, sus herramientas y sus instrucciones con el fin de realizar trabajo especializado y repetible.
|
||||
- [`/chronicle`][chronicle] para generar una narración de lo sucedido en una sesión.
|
||||
- [Usar tu propia clave (BYOK)][byok] para utilizar modelos de tu propio proveedor, incluidos modelos locales mediante Ollama, Foundry Local o LM Studio.
|
||||
- [Entornos aislados en la nube][sandboxes] para ejecutar sesiones en un entorno aislado hospedado en GitHub.
|
||||
- [Vínculos profundos][deep-links] para abrir la aplicación directamente en un repositorio, una sesión o una indicación.
|
||||
|
||||
## Pasos siguientes
|
||||
|
||||
La mejor forma de mejorar con cualquier herramienta es seguir utilizándola. Úsala para código de producción, proyectos personales o esa pequeña aplicación que llevas años pensando en crear. Comparte lo que aprendas con el equipo y aprende de sus experiencias. Y, como siempre, consulta la documentación.
|
||||
|
||||
Para explorar más elementos del ecosistema de GitHub Copilot, consulta el [recorrido de VS Code](/es-es/learning-hub/copilot-workshops/vscode/), el [recorrido de Copilot CLI](/es-es/learning-hub/copilot-workshops/cli/) o el [recorrido del agente en la nube](/es-es/learning-hub/copilot-workshops/cloud/).
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Acerca de la aplicación GitHub Copilot][about-copilot-app]
|
||||
- [Introducción a la aplicación GitHub Copilot][getting-started]
|
||||
- [Personalizar la aplicación GitHub Copilot][customize]
|
||||
- [Utilizar automatizaciones][using-automations]
|
||||
- [Trabajar con extensiones de lienzo][canvas-docs]
|
||||
- [Acerca de los entornos aislados locales y en la nube][sandboxes]
|
||||
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[customize]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[using-automations]: https://docs.github.com/copilot/how-tos/github-copilot-app/using-automations
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[chronicle]: https://docs.github.com/copilot/how-tos/copilot-cli/use-copilot-cli/chronicle
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[byok]: https://docs.github.com/copilot/how-tos/github-copilot-app/use-byok-models
|
||||
[deep-links]: https://docs.github.com/copilot/how-tos/github-copilot-app/open-with-deep-links
|
||||
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: "Aplicación GitHub Copilot"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
La [**aplicación GitHub Copilot**](https://docs.github.com/copilot/concepts/agents/github-copilot-app) es una aplicación de escritorio basada en Copilot CLI que reúne el desarrollo dirigido por agentes en un único espacio de trabajo específico. Añade sesiones de agente en paralelo, modos de sesión intercambiables, lienzos compartidos y gestión nativa de incidencias y solicitudes de incorporación de cambios de GitHub, incluido **Agent Merge**, que guía una solicitud durante reorganizaciones de base, comentarios de revisión, correcciones de CI y la combinación.
|
||||
|
||||
A lo largo de estas lecciones instalarás la aplicación y configurarás el proyecto. Después, conocerás el espacio de trabajo de la aplicación y la lista de trabajo pendiente que la plantilla ha creado para ti. Empezarás con un cambio pequeño, añadir una valoración por estrellas, y luego añadirás desde una incidencia un estándar de instrucciones personalizadas, crearás una funcionalidad de filtrado en una sesión de agente aislada y la verificarás con una habilidad reutilizable. Añadirás el servidor MCP de Playwright para explorar la funcionalidad en un navegador real y avanzarás por niveles crecientes de automatización de combinaciones hasta que **Agent Merge** incorpore la solicitud. Por último, colaborarás en un lienzo compartido y automatizarás el trabajo recurrente: un ciclo completo desde la idea hasta una funcionalidad combinada.
|
||||
|
||||
## Lecciones
|
||||
|
||||
| Lección | Tema | Descripción |
|
||||
|--------|-------|-------------|
|
||||
| [0. Requisitos previos][ex0] | Configuración | Instala Node.js y crea tu copia del proyecto Tailspin Toys |
|
||||
| [1. Instalar la aplicación Copilot][ex1] | Configuración | Instala la aplicación, conecta el proyecto y familiarízate con el espacio de trabajo |
|
||||
| [2. Ejecutar tu primera sesión de agente][ex2] | Primer cambio | Inicia una sesión y publica un pequeño cambio como tu primera solicitud de incorporación de cambios |
|
||||
| [3. Guiar a Copilot con instrucciones personalizadas][ex3] | Contexto | Añade un estándar de documentación desde una incidencia y combínalo |
|
||||
| [4. Crear una funcionalidad con Autopilot][ex4] | Funcionalidad principal | Utiliza Plan y Autopilot para crear el filtrado y verifícalo con una habilidad |
|
||||
| [5. Realizar pruebas con MCP de Playwright][ex5] | Herramientas externas | Añade el servidor MCP de Playwright y explora la funcionalidad en un navegador |
|
||||
| [6. Combinar cambios con Agent Merge][ex6] | Combinación | Deja que Agent Merge corrija e incorpore la solicitud de filtrado |
|
||||
| [7. Planificar con lienzos][ex7] | Colaboración | Crea un lienzo compartido para planificar y realizar el seguimiento del trabajo |
|
||||
| [8. Repaso y pasos siguientes][ex8] | Resumen | Automatiza tareas recurrentes y descubre cómo continuar |
|
||||
|
||||
## Requisitos previos
|
||||
|
||||
Antes de asistir a este taller, asegúrate de disponer de:
|
||||
|
||||
- [ ] Una cuenta de GitHub con un plan **Copilot Student, Pro, Pro+, Business o Enterprise** activo
|
||||
- [ ] Un ordenador con **macOS, Linux o Windows**
|
||||
- [ ] [Git instalado][install-git] en el ordenador
|
||||
|
||||
> [!TIP]
|
||||
> ¿No tienes un plan de pago? Los estudiantes verificados pueden obtener GitHub Copilot gratis mediante [GitHub Education][callout-student-plan-education]. El plan **Copilot Student** incluye el agente, MCP, la revisión de código y las funcionalidades de Copilot CLI que se utilizan en este taller, por lo que permite completar todos los recorridos.
|
||||
|
||||
> [!NOTE]
|
||||
> Como la aplicación Copilot se ejecuta en tu propio equipo y no en un codespace, la [Lección 0][ex0] explica cómo instalar Node.js y crear tu copia del proyecto antes de instalar la aplicación.
|
||||
|
||||
> [!NOTE]
|
||||
> Si utilizas Copilot Business o Copilot Enterprise, el administrador debe habilitar la directiva **Copilot CLI** para que puedas utilizar la aplicación.
|
||||
|
||||
## Comenzar
|
||||
|
||||
[**Empieza por la Lección 0: Requisitos previos →**][ex0]
|
||||
|
||||
[ex0]: /es-es/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex1]: /es-es/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[ex2]: /es-es/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /es-es/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[ex4]: /es-es/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[ex5]: /es-es/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[ex6]: /es-es/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[ex7]: /es-es/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[ex8]: /es-es/learning-hub/copilot-workshops/app/8-review/
|
||||
[install-git]: https://github.com/git-guides/install-git
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
@@ -0,0 +1,41 @@
|
||||
---
|
||||
title: "Manos a la obra con los agentes de GitHub Copilot"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Las recientes ampliaciones de las capacidades de GitHub Copilot ofrecen a los desarrolladores herramientas potentes para todo el ciclo de vida del desarrollo de software (SDLC). Estas capacidades incluyen trabajar con incidencias y solicitudes de incorporación de cambios en GitHub, interactuar con servicios externos y, por supuesto, crear código. En este laboratorio se exploran estas funciones mediante casos de uso reales y consejos para aprovechar al máximo las herramientas.
|
||||
|
||||
> [!CAUTION]
|
||||
> Como GitHub Copilot es probabilístico y no determinista, el código exacto, los archivos modificados y otros elementos pueden variar. Por este motivo, es posible que observes pequeñas diferencias entre las capturas de pantalla y los fragmentos de código del laboratorio y lo que tú ves. Es algo normal y forma parte de trabajar con este tipo de herramientas.
|
||||
>
|
||||
> Si algo parece no funcionar o no se ejecuta correctamente, ¡pide ayuda a un mentor!
|
||||
|
||||
## Elige tu entorno
|
||||
|
||||
GitHub Copilot te acompaña allí donde trabajes. Elige el entorno que se ajuste a tu forma de desarrollar y completa sus ejercicios con el trabajo pendiente compartido de Tailspin Toys. Cada entorno comienza con su propia configuración para que puedas empezar directamente con el que elijas.
|
||||
|
||||
### 🖥️ [VS Code](/es-es/learning-hub/copilot-workshops/vscode/)
|
||||
|
||||
GitHub Copilot dentro de **Visual Studio Code** y GitHub Codespaces. Trabaja con el modo agente de Copilot Chat, servidores MCP y agentes personalizados sin salir del editor que ya utilizas. Es ideal si quieres integrar la asistencia de IA directamente en el IDE.
|
||||
|
||||
### 💻 [Copilot CLI](/es-es/learning-hub/copilot-workshops/cli/)
|
||||
|
||||
**GitHub Copilot CLI** es un asistente basado en agentes que se ejecuta en el terminal. Instálalo, conecta servidores MCP, genera código con el modo de planificación y crea tus propias skills, agentes personalizados y comandos con barra diagonal, todo desde la línea de comandos.
|
||||
|
||||
### 🤖 [Copilot App](/es-es/learning-hub/copilot-workshops/app/)
|
||||
|
||||
La **aplicación GitHub Copilot** es una aplicación de escritorio basada en Copilot CLI. Ejecuta sesiones de agentes en paralelo, cambia el modo de las sesiones, colabora en lienzos y gestiona incidencias y solicitudes de incorporación de cambios de GitHub de forma nativa. También incluye **Agent Merge**, que guía una solicitud de incorporación de cambios durante los cambios de base, los comentarios de revisión, las correcciones de integración continua y la combinación.
|
||||
|
||||
### ☁️ [Copilot Cloud Agent](/es-es/learning-hub/copilot-workshops/cloud/)
|
||||
|
||||
El **agente de Copilot en la nube** es un compañero de programación asíncrono que trabaja en segundo plano en las incidencias de GitHub. Asígnale trabajo, guíalo con agentes personalizados, supervisa el progreso desde el panel de agentes y revisa las solicitudes de incorporación de cambios que abre.
|
||||
|
||||
## Escenario
|
||||
|
||||
Acabas de incorporarte como desarrollador a Tailspin Toys, una empresa ficticia que ofrece financiación colectiva para juegos de mesa de temática tecnológica: ¡un mercado enorme! El trabajo pendiente del equipo ya está registrado como incidencias de GitHub para que puedas comenzar. Incluye tanto funcionalidades, como el filtrado y la paginación, como mejoras de calidad, como la accesibilidad y los estándares de programación. Trabajarás de forma iterativa para completar las tareas mientras exploras el sitio y las capacidades de Copilot.
|
||||
|
||||
## Primeros pasos
|
||||
|
||||
Elige uno de los entornos anteriores para empezar. Cada uno comienza con la configuración necesaria para que puedas ponerte manos a la obra.
|
||||
@@ -0,0 +1,85 @@
|
||||
---
|
||||
title: "レッスン 0 - 前提条件"
|
||||
description: "GitHub Copilot app のレッスンに向けて、Tailspin Toys プロジェクト用の Node.js をインストールし、テンプレートからリポジトリの自分用コピーを作成します。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
GitHub Copilot app は、Copilot と GitHub の両方を一元的に扱うデスクトップアプリです。Issue や pull request にすばやくアクセスでき、もちろん GitHub Copilot を使った開発も可能です。このワークショップでは、Astro で構築された Tailspin Toys アプリと GitHub Copilot app を使い、ローカル環境で作業します。始める前に、Node.js がローカルにインストールされていることを確認してから、Copilot app をインストールします。
|
||||
|
||||
このレッスンでは、次の内容を学習します。
|
||||
|
||||
- プロジェクトのテストを実行できるよう Node.js をインストールする。
|
||||
- テンプレートから Tailspin Toys プロジェクトの自分用コピーを作成する。
|
||||
|
||||
## Node.js をインストールする
|
||||
|
||||
いくつかのレッスンでは、エージェントに機能を構築させ、Tailspin Toys のテストスイートをローカルで実行します。そのためには [**Node.js**][nodejs] (プロジェクトに必要な唯一のランタイム) が必要です。バージョン **22 以降**をインストールしてください。現在の **LTS** リリースを選ぶと安心です。
|
||||
|
||||
どのプラットフォームでも、公式インストーラーを使うのが最も簡単です。
|
||||
|
||||
1. Windows Terminal、macOS のターミナル、または普段使用しているターミナルを開きます。
|
||||
2. 次のコマンドを実行し、Node.js 22 以降がインストールされていることを確認します。
|
||||
|
||||
```shell
|
||||
node --version
|
||||
```
|
||||
|
||||
3. `v22` 以上のバージョン番号が表示された場合は、次のセクションに進めます。
|
||||
|
||||
> [!TIP]
|
||||
> Node.js がインストールされていない場合、または更新が必要な場合にのみ、以降の手順を実行してください。
|
||||
|
||||
4. [Node.js のダウンロードページ][node-download]を開きます。
|
||||
5. 使用しているオペレーティングシステム向けの **LTS** ビルドをダウンロードします。
|
||||
6. インストーラーを実行し、既定の設定を選択します。Windows では、**Add to PATH** を選択したままにします。
|
||||
7. インストールが完了したら、新しいターミナルを開きます。
|
||||
8. 新しいターミナルで次のコマンドを実行し、インストールを確認します。
|
||||
|
||||
```bash
|
||||
node --version
|
||||
```
|
||||
|
||||
9. `v22.x.x` 以上が表示されることを確認します。
|
||||
|
||||
> [!TIP]
|
||||
> コンテナーを使用する場合、[**Docker**][docker] があれば、Node.js をローカルにインストールする代わりにリポジトリの [dev container][dev-containers] を使用できます。dev container には Node.js が含まれているため、両方を用意する必要はありません。
|
||||
|
||||
## ラボ用リポジトリを設定する
|
||||
|
||||
Tailspin Toys プロジェクトの自分用コピーを使って作業します。[テンプレートリポジトリ][template-repository]からコピーを作成してください。新しいリポジトリにはラボに必要なすべてのファイルが含まれています。次のレッスンで、このリポジトリをアプリに接続します。
|
||||
|
||||
1. 新しいブラウザーウィンドウで、このラボの GitHub リポジトリ `https://github.com/github-samples/tailspin-toys` を開きます。
|
||||
2. ラボ用リポジトリのページで **Use this template** ボタンを選択し、**Create a new repository** を選択して、リポジトリの自分用コピーを作成します。
|
||||
|
||||
|
||||
|
||||
3. GitHub または Microsoft が主催するイベントの一環としてワークショップに参加している場合は、メンターの指示に従ってください。それ以外の場合は、GitHub Copilot を利用できる Organization に新しいリポジトリを作成できます。
|
||||
|
||||
|
||||
|
||||
4. 作成したリポジトリのパス (**organization-or-user-name/repository-name**) を記録します。このラボで後ほど使用します。
|
||||
|
||||
> [!NOTE]
|
||||
> テンプレートからリポジトリを作成すると、GitHub Issue のバックログが自動的に作成されます。ワークショップ全体を通してこれらの Issue を使用するため、自分で作成する必要はありません。
|
||||
|
||||
## まとめと次のステップ
|
||||
|
||||
準備が整いました。プロジェクトをコンピューター上でビルドしてテストできるように Node.js をインストールし、テンプレートから Tailspin Toys リポジトリの自分用コピーを作成しました。
|
||||
|
||||
次は GitHub Copilot app をインストールし、作成したリポジトリを接続して、ワークスペースを確認します。[レッスン 1「GitHub Copilot app のインストール」][next-lesson]に進んでください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [Node.js のダウンロード][node-download]
|
||||
- [テンプレートからのリポジトリの作成][template-repository]
|
||||
- [GitHub Copilot app について][about-copilot-app]
|
||||
|
||||
[next-lesson]: /ja-jp/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[nodejs]: https://nodejs.org/
|
||||
[node-download]: https://nodejs.org/en/download
|
||||
[docker]: https://www.docker.com/products/docker-desktop/
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
+100
@@ -0,0 +1,100 @@
|
||||
---
|
||||
title: "レッスン 1 - GitHub Copilot app のインストール"
|
||||
description: "GitHub Copilot app をインストールし、テンプレートから作成したリポジトリを接続して、ワークスペースを確認し、クイックチャットを試します。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[**GitHub Copilot app**][about-copilot-app] は、エージェント主導の開発に使用するデスクトップアプリケーションです。GitHub Copilot CLI を基盤とし、GitHub とネイティブに統合されているため、リポジトリ、ブランチ、CI パイプラインをすぐに利用できます。すべての作業を自分で行うのではなく、複数のエージェントをそれぞれ分離されたワークスペースで並列に指示し、繰り返し発生するタスクを自動化するワークフロー向けに設計されています。Node.js のインストールとプロジェクトのコピーが完了したので、次はアプリをインストールして、そのリポジトリを接続します。
|
||||
|
||||
このレッスンでは、次の内容を学習します。
|
||||
|
||||
- GitHub Copilot app をインストールしてサインインする。
|
||||
- GitHub リポジトリからプロジェクトをアプリに追加する。
|
||||
- テンプレートによって用意されたバックログを含め、ワークスペースを確認する。
|
||||
- クイックチャットを試して、アプリ自体について学ぶ。
|
||||
|
||||
## シナリオ
|
||||
|
||||
チームは、増え続けるバックログに対応するために AI エージェントを導入しています。Copilot app では、Issue の選択、エージェントの実行、変更のレビュー、pull request のマージを一か所から指示できます。このレッスンでは、アプリをインストールして接続し、プロジェクトについての会話を始められるようにします。
|
||||
|
||||
> [!NOTE]
|
||||
> 対象となる Copilot プランが必要です。Copilot Student またはいずれかの有料プラン (Pro、Pro+、Business、Enterprise) を利用してください。Copilot Business または Copilot Enterprise を使用している場合、アプリを動作させるには管理者が **Copilot CLI** ポリシーを有効にする必要があります。
|
||||
|
||||
## GitHub Copilot app をインストールして構成する
|
||||
|
||||
GitHub Copilot app を使用するには、まずアプリをインストールします。Windows、macOS、Linux 向けのバージョンが用意されています。アプリをインストールして認証し、Tailspin Toys リポジトリを追加します。
|
||||
|
||||
1. ブラウザーで [GitHub Copilot app のランディングページ][download-app]を開きます。
|
||||
2. 使用しているプラットフォーム向けのアプリをダウンロードし、ランディングページの手順に従ってインストールします。
|
||||
3. インストールが完了したら、アプリを開きます。
|
||||
4. **Sign in to GitHub** を選択し、画面の指示に従って認証します。GitHub Enterprise Server を使用している場合は **Use GitHub Enterprise** を選択し、求められたらサーバーアドレスを入力します。
|
||||
5. 認証後、リポジトリを接続するよう求められます。先ほど作成した `<YOUR_GITHUB_HANDLE>/tailspin-toys` という名前の Tailspin Toys リポジトリを選択します。
|
||||
6. **Continue** を選択してオンボーディングを続けます。
|
||||
7. テーマの選択を求められたら、最も好みのものを選び、**Finish** を選択します。
|
||||
|
||||
> [!NOTE]
|
||||
> Tailspin Toys のコピーが一覧に自動的に表示されなかった場合は、アプリのオンボーディングを完了した後に追加できます。完了すると、Copilot app のホーム画面が表示されます。そこで **Choose from GitHub** を選択し、リポジトリ名 (\<YOUR_GITHUB_HANDLE\>/tailspin-toys) で検索して選択します。これでリポジトリが Copilot app に追加されます。
|
||||
|
||||
## ワークスペースを確認する
|
||||
|
||||
プロジェクトを接続したら、各領域を確認します。アプリのサイドバーは、主に次の領域で構成されています。
|
||||
|
||||
- **Sessions** - エージェントが作業する場所です。各セッションは分離された独自のワークスペースで実行されるため、変更が競合することなく複数のセッションを同時に実行できます。次のレッスンで最初のセッションを開始します。
|
||||
- **Quick chats** - 独自のブランチやワークスペースを必要としない、質問やブレインストーミング向けの簡易的な会話です。このレッスンの最後に試します。
|
||||
- **My work** - アプリの **GitHub ネイティブ統合**を通じて表示される Issue と pull request です。アプリを離れずに、Issue と pull request の参照や絞り込み、CI ステータスの確認、Issue からのセッション開始、pull request のレビューを行えます。
|
||||
- **Automations** - スケジュールまたはオンデマンドで実行する、保存済みのエージェントタスクです。ハーネスの終盤で作成します。
|
||||
|
||||
### 用意されたバックログを確認する
|
||||
|
||||
アプリは GitHub とネイティブに統合されているため、リポジトリで待機中の作業がアプリ内に表示されます。テンプレートからリポジトリを作成したときに、バックログとなる Issue が用意されています。表示されていることを確認します。
|
||||
|
||||
1. サイドバーで **My work** を選択します。
|
||||
2. テンプレートはバックログに 8 件の Issue を用意しています。このハーネスでは次の 3 件に焦点を当てます。表示されていることを確認してください。
|
||||
|
||||
- Allow users to filter games by category and publisher
|
||||
- Update our repository coding standards
|
||||
- Implement pagination on the game list page
|
||||
|
||||
3. Issue を選択して詳細を読みます。各 Issue はエージェントセッションの開始点にもなります。ハーネスの後半では、これらの Issue から作業を開始します。
|
||||
|
||||
> [!NOTE]
|
||||
> My work の項目一覧は自動的に絞り込まれ、Copilot app に追加したリポジトリの項目だけが表示されます。ほかのリポジトリの作業項目を表示するには、そのリポジトリをアプリに追加してください。
|
||||
|
||||
## クイックチャットを試す
|
||||
|
||||
アプリに慣れるには、アプリ自体について質問するのが効果的です。その用途には **quick chat** が適しています。Quick chats ではブランチや worktree を作成せずに質問やブレインストーミングができるため、セッションを必要としない、その場限りの簡単な質問に最適です。
|
||||
|
||||
1. サイドバーで **Quick chats** の横にある **+** を選択し、新しいチャットを開きます。
|
||||
2. アプリのセッションがどのように動作するかを尋ねます。
|
||||
|
||||
```plaintext
|
||||
How does the GitHub Copilot app use worktrees?
|
||||
```
|
||||
|
||||
3. 会話ビューで回答を読みます。各セッションが分離された独自の git worktree で実行されるため、変更が競合することなく複数のエージェントを並列実行できることがわかります。会話はいつでも継続でき、新しいチャットも開始できます。
|
||||
|
||||
## まとめと次のステップ
|
||||
|
||||
GitHub Copilot app をインストールし、プロジェクトを接続して、ワークスペースを確認しました。学習した内容は次のとおりです。
|
||||
|
||||
- アプリをインストールして GitHub にサインインする。
|
||||
- GitHub リポジトリからプロジェクトを追加する。
|
||||
- ワークスペースを確認し、**My work** で用意されたバックログを見つける。
|
||||
- クイックチャットを使って、その場限りの簡単な質問をする。
|
||||
|
||||
次は、最初のエージェントセッションを開始し、ゲームカードに星評価を表示する最初の変更をプロジェクトに加えます。[レッスン 2「最初のエージェントセッションの実行」][next-lesson]に進んでください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [GitHub Copilot app について][about-copilot-app]
|
||||
- [GitHub Copilot app の概要][getting-started]
|
||||
- [GitHub Copilot app でのエージェントセッションの操作][agent-sessions]
|
||||
|
||||
[ex0]: /ja-jp/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[next-lesson]: /ja-jp/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[download-app]: https://gh.io/app
|
||||
+135
@@ -0,0 +1,135 @@
|
||||
---
|
||||
title: "レッスン 2 - 最初のエージェントセッションの実行"
|
||||
description: "GitHub Copilot app で最初のエージェントセッションを開始し、ゲームカードに小さな変更を加えて、最初の pull request としてマージします。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
前のレッスンでは、ワークスペースを確認し、クイックチャットを使いました。ここでは、**エージェントセッション**を開始し、プロジェクトに最初の変更を加えます。変更は小規模なものにします。ゲームのデータにはすでに星評価が含まれていますが、ホームページのゲームカードにはまだ表示されていません。エージェントに表示を依頼し、変更をレビューして、最初の pull request としてマージします。
|
||||
|
||||
このレッスンでは、次の内容を学習します。
|
||||
|
||||
- エージェントセッションを開始し、セッションの構成を理解する。
|
||||
- プロジェクトに小規模で対象を絞った変更を加えるようエージェントに依頼する。
|
||||
- ワークスペースの差分ビューで変更をレビューする。
|
||||
- アプリをローカルで実行し、ブラウザーで変更を確認する。
|
||||
- 最初の pull request を作成してマージする。
|
||||
|
||||
## シナリオ
|
||||
|
||||
Tailspin Toys の各ゲームには星評価を設定でき、ゲーム詳細ページにはすでに表示されています。一方、ホームページのゲームカードには、タイトル、カテゴリー、パブリッシャー、説明だけが表示されています。最初のセッションの準備運動として、各カードに既存の評価を表示するようエージェントに依頼します。小規模で自己完結した、最初のセッションに最適な変更です。
|
||||
|
||||
## セッションの構造
|
||||
|
||||
**セッション**とは、分離された独自のワークスペースで実行されるエージェントとの会話です。すべてのセッションに**専用の git worktree とブランチ**が割り当てられます。そのため、一方では機能を追加し、もう一方ではバグを修正するなど、変更を競合させずに複数のセッションを同時に実行できます。セッションはリポジトリごとにグループ化されてサイドバーに表示され、選択すると切り替えられます。
|
||||
|
||||
セッション内には、エージェントとの**会話**、ファイルを調査および編集するときのエージェントの**ツールアクティビティ**、差分付きの**変更済みファイル**一覧という3つの要素が表示されます。
|
||||
|
||||
## セッションを開始して変更を依頼する
|
||||
|
||||
新しいセッションを開始し、プロジェクトの調査と機能の実装に取りかかります。[前のレッスン][prior-lesson]では、GitHub リポジトリからプロジェクトを追加しました。そのリポジトリ用の新しいセッションを作成し、変更を依頼します。
|
||||
|
||||
1. GitHub Copilot app に戻ります。アプリを閉じている場合は開きます。
|
||||
2. **Home screen** を選択します。
|
||||
3. リポジトリに `tailspin-toys` が選択されていることを確認します。
|
||||
|
||||
|
||||
|
||||
4. 次のプロンプトを使って変更を依頼します。
|
||||
|
||||
```plaintext
|
||||
On the game cards, show each game's star rating. The Game type already includes a starRating field — it's a number out of 5, or null when a game hasn't been rated yet. Display it on each card in src/components/GameCard.astro, and when starRating is null show "No rating yet" instead. Keep the change small and don't restructure the card layout.
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> プロンプトに、Copilot が更新するファイル名が含まれていることに注目してください。Copilot が作業に含めるファイルを指定する必要はありませんが、方向性を示すことで、コードをすばやく生成し、トークン使用量を削減できます。
|
||||
|
||||
5. <kbd>Enter</kbd> を選択して、プロンプトを Copilot に送信します。
|
||||
|
||||
Copilot app は、最初にプロジェクトの分離されたコピーである新しい worktree を作成して作業を開始します。次にプロジェクトを調査し、新機能の追加に必要な更新対象ファイルを見つけて、必要なコードを作成します。これで Copilot app を使って新機能を追加できました。
|
||||
|
||||
## 差分をレビューする
|
||||
|
||||
AI が生成したすべての変更は、どれほど小さくてもマージ前にレビューする必要があります。Copilot app 内で変更を確認します。
|
||||
|
||||
1. アプリの右上隅にある **Toggle review panel** を選択します。Copilot が行った未処理の変更がすべて表示される差分画面が開きます。
|
||||
|
||||
|
||||
|
||||
2. ゲームの詳細表示に使用される中心的なファイル `GameCard.astro` にコードが追加されていることを確認します。次のような小さなブロックが追加されているはずです。評価がある場合は表示し、`starRating` が `null` の場合は "No rating yet" を表示します。
|
||||
|
||||
```astro
|
||||
{game.starRating !== null ? (
|
||||
<span class="text-xs font-medium px-2.5 py-0.5 rounded bg-amber-900/60 text-amber-300" data-testid="game-rating">
|
||||
★ {game.starRating} / 5
|
||||
</span>
|
||||
) : (
|
||||
<span class="text-xs font-medium text-slate-500" data-testid="game-rating-empty">
|
||||
No rating yet
|
||||
</span>
|
||||
)}
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot は、すべての生成 AI ツールと同様に決定論的ではなく確率的に動作するため、実際のコードは上記と異なる場合があります。ただし、比較的よく似たものになります。
|
||||
|
||||
## 変更を確認する
|
||||
|
||||
コードを読むだけで動作すると判断せず、視覚的にもテストします。そのためには、ターミナルからアプリを起動して、すべてが動作することを確認する必要があります。Copilot app にはターミナルが組み込まれています。
|
||||
|
||||
1. Copilot app の右側にあるレビューパネルで **Terminal** を選択します。**Terminal** ボタンがない場合は、**+** (**Open in panel** というラベルが付いています) を選択してから **Terminal** を選択します。
|
||||
|
||||
|
||||
|
||||
2. ターミナルウィンドウに次のコマンドを入力し、Web アプリの開発サーバーを起動します。
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
3. サーバーが起動したら、ブラウザーウィンドウを開きます。起動には少し時間がかかります。
|
||||
4. http://localhost:4321 に移動します。
|
||||
5. ランディングページのすべてのゲームに星評価が表示されていることを確認します。
|
||||
6. ターミナルウィンドウに戻ります。
|
||||
7. <kbd>Ctrl</kbd>+<kbd>C</kbd> を選択して開発サーバーを停止します。
|
||||
|
||||
## 最初の pull request を作成してマージする
|
||||
|
||||
変更に問題がないことを確認できたので、リリースします。エージェントに pull request の作成を依頼し、github.com で自分でレビューしてマージします。今回は手動で管理します。後のレッスンでは、Copilot でこの作業の一部を自動的に処理する方法を確認します。
|
||||
|
||||
1. 右上隅にある **Create PR** を選択します。
|
||||
2. 求められた場合は **Sign in with your browser** を選択し、画面の指示に従って認証します。
|
||||
3. Copilot が PR の作成を開始します。
|
||||
|
||||
PR が作成されると、Copilot はリポジトリで実行する必要があるワークフローを監視します。しばらくすると、右上のボタンが **Ready to merge** に変わります。これは PR をマージする準備が整ったことを示します。
|
||||
|
||||
4. チャットのすぐ上にある **PR** バブルを選択し、レビューペインで PR を開いて pull request を確認します。必要に応じて、ここで PR をレビューできます。
|
||||
5. 準備ができたら **Ready to merge** を選択します。
|
||||
6. 新しいダイアログウィンドウで **Merge pull request** を選択し、pull request をマージします。
|
||||
|
||||
これで Web サイトに新機能を反映できました。
|
||||
|
||||
## まとめと次のステップ
|
||||
|
||||
最初のエージェントセッションを開始し、最初の変更をリリースしました。具体的には、次の作業を行いました。
|
||||
|
||||
- エージェントセッションを開始し、セッションの構成を学習した。
|
||||
- ゲームカードに小規模で対象を絞った変更を加えるようエージェントに指示した。
|
||||
- ワークスペースの差分ビューで変更をレビューした。
|
||||
- アプリをローカルで実行し、ブラウザーで星評価を確認した。
|
||||
- pull request を作成し、github.com で自分でマージした。
|
||||
|
||||
次は、アプリを使ってリポジトリにカスタム指示の標準を追加します。バックログ内の Issue の1つから作業を開始します。[レッスン 3「カスタム指示による Copilot のガイド」][next-lesson]に進んでください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [GitHub Copilot app でのエージェントセッションの操作][agent-sessions]
|
||||
- [GitHub Copilot app について][about-copilot-app]
|
||||
- [GitHub Copilot app での Issue と pull request の管理][managing-issues-prs]
|
||||
|
||||
[prior-lesson]: /ja-jp/learning-hub/copilot-workshops/app/1-install-copilot-app/#github-copilot-app-をインストールして構成する
|
||||
[next-lesson]: /ja-jp/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+165
@@ -0,0 +1,165 @@
|
||||
---
|
||||
title: "レッスン 3 - カスタム指示による Copilot のガイド"
|
||||
description: "GitHub Copilot app を使い、バックログの Issue から始めてカスタム指示の標準をリポジトリに追加し、変更を pull request としてマージします。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
生成 AI を扱うとき、コンテキストは重要です。タスクを特定の方法で実行する必要がある場合や、Copilot が把握しておくべき背景情報がある場合は、そのコンテキストを利用できるようにします。特に強力なツールの1つが[指示ファイル][instruction-files]です。指示ファイルには、必要なコードの内容だけでなく、その構成方法も記述します。このレッスンでは、リポジトリにドキュメント標準を追加します。ここから先の多くの作業と同様に、バックログの Issue から開始し、エージェントに変更を行わせます。
|
||||
|
||||
このレッスンでは、次の内容を学習します。
|
||||
|
||||
- リポジトリ指示とパス固有の指示ファイルがエージェントにどのように渡されるかを確認する。
|
||||
- バックログ内の指示に関する Issue からセッションを開始する。
|
||||
- `.github/copilot-instructions.md` にドキュメント標準を追加するようエージェントに依頼する。
|
||||
- 変更をレビューし、pull request としてマージする。
|
||||
|
||||
## シナリオ
|
||||
|
||||
優れた開発組織と同様に、Tailspin Toys にも開発プラクティスのガイドラインと要件があります。内容は次のとおりです。
|
||||
|
||||
- TSDoc doc comment の形式でコードにドキュメントを追加する。
|
||||
- フォーマット方法を文書化し、lint によって適用する。
|
||||
|
||||
指示ファイルを使用すると、示されたプラクティスに沿ってタスクを実行するために必要な情報を Copilot に提供できます。
|
||||
|
||||
## 指示ファイル
|
||||
|
||||
カスタム指示を使うと、Copilot にコンテキストと設定を提供でき、コーディングスタイルや要件をより正確に理解させることができます。Copilot をガイドし、より関連性の高い提案やコードスニペットを得るための強力な機能です。希望するコーディング規約、ライブラリ、コードに含めるコメントの種類まで指定できます。リポジトリ全体に適用する指示や、タスクレベルのコンテキストとして特定のファイル種類に適用する指示を作成できます。
|
||||
|
||||
指示ファイルには2つの種類があります。
|
||||
|
||||
- `.github/copilot-instructions.md` は、リポジトリに対する**すべての**リクエストで Copilot に送信される単一の指示ファイルです。このファイルには、Copilot に送信するほとんどのチャットまたは CLI リクエストに関係する、プロジェクトレベルの情報を記載します。使用する技術スタック、構築するものの概要、ベストプラクティスなど、全体に適用するガイダンスを含められます。
|
||||
- `.github/instructions/*.instructions.md` ファイルは、特定のタスクやファイル種類向けに作成できます。特定の言語 (TypeScript や Astro など) や、UI コンポーネントまたは新しい単体テスト一式の作成といったタスクに関するガイドラインを提供できます。
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot は AGENTS.md、CLAUDE.md、GEMINI.md を通じて指示のガイダンスを取り込むほかの標準もサポートしており、常に適切なコンテキストを提供できます。
|
||||
|
||||
### 指示ファイルを管理するためのベストプラクティス
|
||||
|
||||
指示ファイルの作成方法を詳しく説明することは、このワークショップの範囲外です。ただし、サンプルプロジェクトに含まれる例は、代表的なアプローチを示しています。概要は次のとおりです。
|
||||
|
||||
- `copilot-instructions.md` の指示は、構築するものの説明、プロジェクトの構造、全体的なコーディング標準など、プロジェクトレベルのガイダンスに絞ります。
|
||||
- `*.instructions.md` ファイルは、ファイル種類 (単体テスト、Astro コンポーネント、データレイヤー) または特定のタスクに固有の指示を提供するために使用します。
|
||||
- 自然言語を使います。ガイダンスは明確にし、コードの適切な例と不適切な例を提示します。
|
||||
|
||||
AI の使い方に唯一の方法がないのと同様に、指示ファイルの作成方法にも唯一の正解はありません。プロジェクトに最適な方法は、試行を重ねることで見つけられます。
|
||||
|
||||
> [!TIP]
|
||||
> GitHub Copilot を使用するすべてのプロジェクトには、充実した指示ファイル一式を用意することをお勧めします。このプロジェクトのファイルを確認すると、多くのコードファイル種類に対応する指示ファイルがあることがわかります。
|
||||
>
|
||||
> テンプレートや出発点が必要な場合は、指示ファイル、カスタムエージェントなどのリソースが揃ったリポジトリ [awesome-copilot][awesome-copilot] を確認してください。
|
||||
|
||||
## このプロジェクトのカスタム指示ファイルを確認する
|
||||
|
||||
このリポジトリに含まれる指示ファイルを確認します。中心となる `copilot-instructions.md` が1つと、さまざまなタスクに対応する `*.instructions.md` ファイル一式があります。エディターまたは GitHub Web UI で開いてください。
|
||||
|
||||
1. レビューパネルが表示されていない場合は、右上の **Toggle review panel** を選択して開きます。
|
||||
|
||||
|
||||
|
||||
2. **+** を選択し、レビューパネルに新しい項目を追加します。
|
||||
3. **File** を選択します。
|
||||
4. `copilot-instructions.md` を検索します。
|
||||
5. ファイル一覧から `copilot-instructions.md` を選択して開きます。
|
||||
6. ファイルを確認します。プロジェクトの簡単な説明に加えて、**Agent notes**、**Code standards**、**Scripts**、**Repository Structure** などのセクションがあります。**Code standards** の下には、ネストされた **GitHub Actions Workflows** のガイダンスがあります。これらは Copilot とのすべてのやり取りに適用されます。
|
||||
7. **Show folder view** を選択して、フォルダーナビゲーターを開きます。
|
||||
|
||||
|
||||
|
||||
8. `.github/instructions` フォルダーに移動し、ファイルを確認します。Astro ファイル、Drizzle データレイヤー、テストなどに対応する指示があります。
|
||||
9. `.github/instructions/unit-tests.instructions.md` を開きます。先頭の `applyTo` フィールドに注目してください。これはリポジトリのルートを基準とする glob で、指示を適用するファイルを決定します。ここでは、TypeScript のテストファイル (`**/*.test.ts` に一致するファイルなど) が対象になります。
|
||||
10. このプロジェクトで単体テストを作成するための固有の指示を確認します。
|
||||
11. 最後に `.github/instructions/drizzle.instructions.md` を開き、末尾まで移動します。ほかの指示ファイル (`unit-tests.instructions.md` など) と、プロジェクト内の既存ファイルへのリンクに注目してください。これにより、大きな指示セットを小さく再利用可能なファイルに分割し、コード生成時に参照する例を Copilot に提示できます。そこに記載されたパスは、リポジトリのルートではなく指示ファイルを基準とします。
|
||||
|
||||
> [!NOTE]
|
||||
> `copilot-instructions.md` の **Code formatting requirements** セクションにはプロジェクトのコーディング標準が記載されていますが、コード内のドキュメントはまだ必須ではありません。次の手順で、TSDoc doc comment とファイルコメントヘッダーの規則を追加します。
|
||||
|
||||
## 指示に関する Issue から開始する
|
||||
|
||||
前のレッスンでは、直接入力したプロンプトからセッションを開始しました。しかし、多くの作業は Issue から始まります。指示ファイルを更新するために登録された Issue に基づいて新しいセッションを作成し、更新を依頼します。
|
||||
|
||||
> [!NOTE]
|
||||
> 指示ファイルは Copilot が生成するコードに大きな影響を与えるため、Copilot を明確にガイドする内容になっていることを慎重に確認してください。このレッスンのように、Copilot で最初のバージョンを作成した後、自分でレビューして更新内容が要件を満たすことを確認する方法が効果的です。
|
||||
|
||||
1. サイドバーで **My work** を選択します。
|
||||
2. **Update our repository coding standards** というタイトルの Issue を選択して開きます。
|
||||
3. 右上の **New session** を選択し、Issue に基づく新しいセッションを開始します。
|
||||
|
||||
|
||||
|
||||
4. 次のプロンプトを使い、Issue に記載された要件を満たすように指示ファイルを更新することを Copilot に依頼します。
|
||||
|
||||
```plaintext
|
||||
Following this issue, make the updates to the instructions files in this project to meet the requirements documented. Don't create the PR quite yet!
|
||||
```
|
||||
|
||||
Copilot が更新を行います。
|
||||
|
||||
## 変更をレビューする
|
||||
|
||||
Copilot が行った更新を読み、更新された指示に基づいて生成するコード例も提示させます。
|
||||
|
||||
1. 右上の **Changes** を選択してコードの変更を開きます。
|
||||
|
||||
|
||||
|
||||
2. 更新された指示ファイルをレビューします。コードにドキュメントとコメントを追加するためのガイドラインが含まれていることを確認します。
|
||||
|
||||
> [!NOTE]
|
||||
> AI は決定論的ではなく確率的に動作するため、実際のテキストは異なります。
|
||||
|
||||
3. 次のプロンプトを使い、Copilot が今後生成するコード例を作成するよう依頼します。
|
||||
|
||||
```plaintext
|
||||
Do not make any updates, but show me what the code would look like. Based on the new instructions, if I asked Copilot to create a new library component to return all Publishers what would that code look like?
|
||||
```
|
||||
|
||||
4. Copilot が提案するコードをレビューします。更新された指示で求めたとおり、TSDoc doc comment とファイルヘッダーコメントが含まれていることを確認します。
|
||||
|
||||
これでプロジェクトの指示ファイルを更新し、その効果を確認できました。
|
||||
|
||||
## pull request を作成してマージする
|
||||
|
||||
指示ファイルはリポジトリのアセットとなり、チームのほかのメンバーと共有されます。ほかのアセットと同様に、作業内容を含む PR を作成します。
|
||||
|
||||
1. 右上隅にある **Create PR** を選択します。
|
||||
2. 求められた場合は **Sign in with your browser** を選択し、画面の指示に従って認証します。
|
||||
3. Copilot が PR の作成を開始します。
|
||||
|
||||
PR が作成されると、Copilot はリポジトリで実行する必要があるワークフローを監視します。しばらくすると、右上のボタンが **Ready to merge** に変わります。これは PR をマージする準備が整ったことを示します。
|
||||
|
||||
4. **Ready to merge** を選択します。
|
||||
5. 新しいダイアログウィンドウで **Merge pull request** を選択し、pull request をマージします。
|
||||
|
||||
> [!NOTE]
|
||||
> 標準がデフォルトブランチにマージされると、すべてのメンバーと新しいセッションでプロジェクトの一部として利用できます。次のレッスンで最新のデフォルトブランチからフィルター機能のセッションを開始すると、エージェントは自動的にこの標準に従います。生成された TypeScript に、依頼していなくても TSDoc doc comment が含まれます。指示が生成コードを形作ることを示す、小さいながらも実際的な例です。
|
||||
|
||||
## まとめと次のステップ
|
||||
|
||||
アプリが指示ファイルからコンテキストを取得する仕組みを確認し、セッションを使ってリポジトリ全体の標準を追加してマージしました。具体的には、次の作業を行いました。
|
||||
|
||||
- リポジトリの `copilot-instructions.md` とパス固有の `*.instructions.md` ファイルを確認した。
|
||||
- バックログ内の指示に関する Issue からセッションを開始した。
|
||||
- `.github/copilot-instructions.md` にドキュメント標準を追加するようエージェントに依頼した。
|
||||
- 変更をレビューし、pull request としてマージした。
|
||||
|
||||
次は、新しいセッションでフィルター機能を構築し、先ほどマージした標準が適用される様子を確認します。[レッスン 4「Autopilot による機能の構築」][next-lesson]に進んでください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [GitHub Copilot をカスタマイズするための指示ファイル][instruction-files]
|
||||
- [GitHub Copilot app のカスタマイズ][customize-app]
|
||||
- [カスタム指示を作成するためのベストプラクティス][instructions-best-practices]
|
||||
- [Awesome Copilot - 指示ファイルなどのリソース集][awesome-copilot]
|
||||
|
||||
[next-lesson]: /ja-jp/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[instruction-files]: https://docs.github.com/copilot/customizing-copilot/about-customizing-github-copilot-chat-responses
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[awesome-copilot]: https://awesome-copilot.github.com/
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+186
@@ -0,0 +1,186 @@
|
||||
---
|
||||
title: "レッスン 4 - Autopilot による機能の構築"
|
||||
description: "GitHub Copilot app の Plan モードと Autopilot モードを使って静的なクライアント側フィルター機能を構築し、ドキュメント標準が継承されることを確認して、エージェントスキルで検証します。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
ここまで、プロジェクトに小さな更新をいくつか加えました。しかし、より本格的な変更には、よりしっかりしたプロセスが必要です。GitHub Copilot app は既存のフローと連携できるように設計されており、適切なものを適切な方法で構築できます。このレッスンから3回にわたり、一般的な開発プロセスに従います。まず Issue を使って新機能を生成し、エージェントスキルで検証テストと linter を実行します。
|
||||
|
||||
このレッスンでは、次の内容を学習します。
|
||||
|
||||
- フィルター機能に関する Issue から新しいセッションを開始する。
|
||||
- **Plan** モードで機能を計画し、**Autopilot** で構築する。
|
||||
- 生成されたコードが、以前マージしたドキュメント標準に従っていることを確認する。
|
||||
- プロジェクトの `quality-checks` スキルで作業を検証する。
|
||||
|
||||
## シナリオ
|
||||
|
||||
ホームページにはすべてのゲームが一覧表示されますが、訪問者は一覧を絞り込めません。フィルター機能に関する Issue では、**カテゴリー**と**パブリッシャー**でゲームを絞り込めるようにすることが求められています。Copilot を使ってこの機能を実装します。
|
||||
|
||||
## 背景
|
||||
|
||||
AI コーディングエージェントを開発フローに導入しても、基本は変わりません。むしろ、基本はさらに重要になります。多くの開発者は、次のようなフローに従います。
|
||||
|
||||
1. 必要な作業の詳細が記載された Issue を開く。
|
||||
2. 構築する内容の計画を作成する。
|
||||
3. コードを構築してレビューする。
|
||||
4. テストを実行してコードを検証する。
|
||||
5. 新機能を手動で検証する。
|
||||
6. pull request (PR) を作成する。
|
||||
7. コードのレビューと継続的インテグレーションプロセスが成功したら、コードをマージする。
|
||||
|
||||
> [!NOTE]
|
||||
> 正確な手順はチームや Organization によって異なりますが、多くの場合は上記の流れを変形したものです。
|
||||
|
||||
この標準的なアプローチを守ることで、AI が生成したコードが定められた要件を満たし、人間が作成したコードと同じ審査プロセスを通るようにできます。
|
||||
|
||||
## セッションモード
|
||||
|
||||
**セッションモード**は、エージェントの自律性を制御します。プロンプトフィールド下のドロップダウンから設定し、いつでも変更できます。
|
||||
|
||||
- **Interactive**: ユーザーとエージェントが共同で作業します。エージェントは変更を提案し、続行前に入力を待ちます。
|
||||
- **Plan**: エージェントが最初に計画を作成します。計画実行前に内容をレビューして承認します。
|
||||
- **Autopilot**: エージェントが完全に自律して作業し、入力を待たずにコードの作成、テストの実行、反復を行います。
|
||||
|
||||
## フィルター機能を計画する
|
||||
|
||||
潜在的な問題を見つける最適なタイミングは、コードを作成する前です。そのためには、事前に少し計画を立てるのが効果的です。Copilot と計画を立てると、一連の手順と採用するアプローチが生成されます。その計画をレビューし、改善案があれば提案してから、計画に基づいて Copilot にコードを生成させることができます。
|
||||
|
||||
Issue を開いて新しいセッションを開始し、Plan モードに切り替えて計画を作成します。
|
||||
|
||||
1. ナビゲーションタブから **My work** を選択します。
|
||||
2. **Allow users to filter games by category and publisher** というタイトルの Issue を選択します。
|
||||
3. 右上の **New session** を選択します。
|
||||
|
||||
|
||||
|
||||
4. モードに **Plan** と表示されるまで <kbd>Shift</kbd>+<kbd>Tab</kbd> を選択します。
|
||||
|
||||
|
||||
|
||||
5. 次のプロンプトを送信します。Issue から開始したため、フィルター機能の Issue はすでにこのセッションのコンテキストに含まれています。
|
||||
|
||||
```plaintext
|
||||
Plan the work based on the requirements documented in the issue. Please ask any clarifying questions you might have as you build the plan.
|
||||
```
|
||||
|
||||
6. 計画の作成中に、エージェントから追加の質問が提示される場合があります。自分で機能を構築するときの方針に基づいて回答します。
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot は確率的に動作するため、追加で尋ねられる質問は異なります。質問がまったくない場合もありますが、問題ありません。
|
||||
|
||||
7. 完了すると、Copilot が計画の概要を提示します。計画をレビューしてください。クエリの構築、フィルターコントロールの追加、テストの作成が提案されているはずです。必要に応じてフィードバックを返して改善できます。エージェントは提案を新しいバージョンに反映します。
|
||||
|
||||
## Autopilot で構築する
|
||||
|
||||
計画が完成したので、Copilot に実装を構築させます。
|
||||
|
||||
1. **Plan summary** ダイアログのオプション一覧で、**Approve and implement with autopilot** に最も近いオプションを選択します。
|
||||
|
||||
Copilot が実装作業を開始します。
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot が必要なコードの作成を自動的に開始しない場合は、"Go ahead and start building out the plan!" のようなプロンプトを使って開始を依頼できます。
|
||||
>
|
||||
> 必要な更新の作成には数分かかります。エージェントはファイルを編集および作成し、テストを作成して実行し、反復します。この時間に、ここまで学習した内容を振り返ったり、飲み物を用意したりできます。
|
||||
|
||||
## 変更をレビューする
|
||||
|
||||
AI が生成したすべてのコードは、マージ前にレビューする必要があります。コードをレビューし、サイトを実行して問題がないことを確認します。
|
||||
|
||||
1. 右上の **Changes** を選択してコードの変更を開きます。
|
||||
|
||||
|
||||
|
||||
2. 変更をレビューします。新しい TypeScript ファイル、Astro ファイル、テストファイルが表示されます。新しいヘルパー関数には、レッスン3でマージしたドキュメント標準に従い、依頼していなくても TSDoc doc comment とファイルヘッダーコメントが含まれていることを確認します。
|
||||
3. Copilot app の右側にあるレビューパネルで **Terminal** を選択します。**Terminal** ボタンがない場合は、**+** (**Open in panel** というラベルが付いています) を選択してから **Terminal** を選択します。
|
||||
|
||||
|
||||
|
||||
4. ターミナルウィンドウに次のコマンドを入力し、Web アプリの開発サーバーを起動します。
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
5. サーバーが起動したら、ブラウザーウィンドウを開きます。起動には少し時間がかかります。
|
||||
6. http://localhost:4321 に移動します。
|
||||
7. ランディングページでフィルターを使用できることを確認します。
|
||||
8. 問題がある場合は、Copilot に更新を依頼できます。
|
||||
9. 問題がなければ、ターミナルウィンドウに戻ります。
|
||||
10. <kbd>Ctrl</kbd>+<kbd>C</kbd> を選択して開発サーバーを停止します。
|
||||
|
||||
## quality-checks スキルで作業を検証する
|
||||
|
||||
差分を目視で確認するだけで完了とすることもできますが、このチームには明確な品質基準と、それを繰り返し確認する方法があります。
|
||||
|
||||
**エージェントスキル**を使うと、テストの実行、ビルドの生成、pull request の作成など、繰り返し発生するタスクの実行方法を Copilot に指示できます。スキルは、エージェントが必要に応じて読み込める指示、スクリプト、リソースのフォルダーです。[Agent Skills はオープン標準][agent-skills-repo]であり、さまざまなエージェントで使用されています。そのため、同じスキルをエージェントモードの Copilot Chat、Copilot cloud agent、Copilot CLI、GitHub Copilot app で使用できます。
|
||||
|
||||
スキルはプロジェクトの `.github/skills` フォルダー、またはグローバルの `~/.copilot/skills` に配置します。各スキルは、YAML frontmatter (`name` と `description`) と、それに続く Markdown の指示が記載された `SKILL.md` ファイルを含むフォルダーです。
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: quality-checks
|
||||
description: Run the project's test suites and linter to verify code changes are ready to commit, push, or merge.
|
||||
---
|
||||
```
|
||||
|
||||
スキルには、スクリプト、アセット、参考資料を含むサブフォルダーも追加できます。完全な構造については、[エージェントスキルの仕様][agent-skills-spec]を参照してください。
|
||||
|
||||
> [!TIP]
|
||||
> スキルは動的に読み込まれます。エージェントは `description` フィールドに基づいて適用するスキルを判断します。明確でシナリオに合った説明を記述することが、スキルが使用されるか無視されるかを左右します。
|
||||
|
||||
## quality-checks スキルを確認する
|
||||
|
||||
スキルの内容を確認します。
|
||||
|
||||
1. レビューパネルが表示されていない場合は、右上の **Toggle review panel** を選択して開きます。
|
||||
|
||||
|
||||
|
||||
2. **+** を選択し、レビューパネルに新しい項目を追加します。
|
||||
3. **File** を選択します。
|
||||
4. `SKILL.md` を検索します。
|
||||
5. ファイル一覧から `SKILL.md .github/skills/quality-checks` を選択して開きます。
|
||||
6. `name` と `description` を確認します。説明は、コード変更を commit、push、merge する前にテスト、lint、検証する必要がある場合に、このスキルを使用することをエージェントに伝えます。
|
||||
7. スキル全体を読みます。単体テスト、Playwright のエンドツーエンドテスト、ESLint の各スイートを実行するスクリプト、実行順序、一般的な失敗のデバッグ方法が記載されています。そのため、エージェントは推測するのではなく、チームの方法でチェックを実行できます。
|
||||
|
||||
## チェックを実行する
|
||||
|
||||
同じフィルター機能のセッションで、エージェントに作業の検証を依頼します。スキル名を説明する必要はありません。エージェントがリクエストに一致するスキルを見つけます。
|
||||
|
||||
1. Copilot app に戻ります。
|
||||
2. スラッシュコマンド `/quality-checks` を使ってスキルを直接呼び出し、<kbd>Enter</kbd> を選択します。
|
||||
3. エージェントはスキルに従って単体テスト、linter、エンドツーエンドテストを実行し、結果を報告します。失敗したものがあれば、問題を修正して、すべて成功するまでチェックを再実行するよう依頼します。
|
||||
4. **このセッションを開いたままにします。** 次のレッスンでは Playwright MCP server を追加し、実際のブラウザーでフィルター機能が動作することを確認します。
|
||||
|
||||
## まとめと次のステップ
|
||||
|
||||
実際の機能をエンドツーエンドで構築し、チームの基準に照らして検証しました。具体的には、次の作業を行いました。
|
||||
|
||||
- 最新のプロジェクトで、フィルター機能に関する Issue から新しいセッションを開始した。
|
||||
- Plan モードで機能を計画し、Autopilot で構築した。
|
||||
- 生成されたヘルパーが、レッスン3でマージしたドキュメント標準に従っていることを確認した。
|
||||
- `quality-checks` スキルで作業を検証した。
|
||||
|
||||
次は Playwright MCP server を接続し、実際のブラウザーでフィルター機能を確認するようエージェントに依頼します。[レッスン 5「Playwright MCP server によるテスト」][next-lesson]に進んでください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [GitHub Copilot app でのエージェントセッションの操作][agent-sessions]
|
||||
- [Agent Skills について][about-agent-skills]
|
||||
- [GitHub Copilot app のカスタマイズ][customize-app]
|
||||
- [GitHub Copilot のクラウドサンドボックスとローカルサンドボックスについて][sandboxes]
|
||||
|
||||
[ex0]: /ja-jp/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex2]: /ja-jp/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /ja-jp/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[next-lesson]: /ja-jp/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-agent-skills]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[agent-skills-repo]: https://github.com/agentskills/agentskills
|
||||
[agent-skills-spec]: https://agentskills.io/specification
|
||||
@@ -0,0 +1,86 @@
|
||||
---
|
||||
title: "レッスン 5 - Playwright MCP server によるテスト"
|
||||
description: "Playwright MCP server を GitHub Copilot app に追加し、実際のブラウザーでフィルター機能を手動テストするようエージェントに依頼します。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
前のレッスンでは、プロジェクトの自動テストスイートを使ってフィルター機能を作成し、検証しました。テストによってコードの検証を自動化できますが、エージェント自身が動作を確認できるようにすることも効果的です。実際に作成している UI で問題を見つけた場合に、エージェントが対応できるようになります。MCP を使って AI エージェントに外部機能へのアクセスを提供する方法を確認し、Copilot が構築中のサイトを直接操作できるように Playwright MCP server を追加します。
|
||||
|
||||
このレッスンでは、次の内容を学習します。
|
||||
|
||||
- Model Context Protocol (MCP) の概要と、GitHub Copilot app での使用方法を理解する。
|
||||
- アプリの設定から Playwright MCP server を追加する。
|
||||
- エージェントにブラウザーを操作させ、フィルター機能を確認する。
|
||||
|
||||
## シナリオ
|
||||
|
||||
単体テストとエンドツーエンドテストは重要ですが、UI の更新を検証するには、実際に UI を操作する必要があります。変更作業をさらに自動化し、更新が期待どおりに動作するという確信を高めるために、ユーザーと同じ方法で Copilot が作業中の Web サイトを使用できるようにします。
|
||||
|
||||
## Model Context Protocol (MCP) とは
|
||||
|
||||
[Model Context Protocol (MCP)][mcp-blog-post] は、AI エージェントが外部のツールやサービスと通信するための手段を提供します。MCP を使うと、AI エージェントは外部のツールやサービスとリアルタイムで通信できます。その結果、最新情報へのアクセス (resources を使用) や、ユーザーに代わる操作 (tools を使用) が可能になります。
|
||||
|
||||
これらの tools と resources には、AI エージェントと外部のツールやサービスをつなぐ MCP server を通じてアクセスします。MCP server は、AI エージェントと外部ツール (既存の API や NPM パッケージなどのローカルツール) 間の通信を管理します。各 MCP server は、AI エージェントがアクセスできる異なる tools と resources のセットを表します。
|
||||
|
||||
よく使われる既存の MCP server には、次のものがあります。
|
||||
|
||||
- [**GitHub MCP Server**](https://github.com/github/github-mcp-server): GitHub リポジトリを管理するための API セットにアクセスできます。AI エージェントは、新しいリポジトリの作成、既存のリポジトリの更新、Issue と pull request の管理などを行えます。
|
||||
- [**Playwright MCP Server**][playwright-mcp-server]: Playwright を使ったブラウザー自動化機能を提供します。AI エージェントは、Web ページへの移動、フォームへの入力、ボタンの選択などを行えます。
|
||||
|
||||
さまざまな tools と resources にアクセスできる MCP server がほかにも多数あります。GitHub は、エコシステム内での発見と貢献を促進するために [MCP registry](https://github.com/mcp) をホストしています。
|
||||
|
||||
> [!CAUTION]
|
||||
> MCP server は、プロジェクト内のほかの依存関係と同様に扱ってください。使用する前にソースコードを慎重に確認し、発行元を検証して、セキュリティ上の影響を考慮します。信頼できる MCP server だけを使用し、機密性の高いリソースや操作へのアクセスを許可するときは注意してください。
|
||||
|
||||
## Playwright MCP server を追加する
|
||||
|
||||
MCP server はアプリの設定から追加して管理します。アプリには一般的なサーバーのカタログが含まれているため、[Playwright MCP server][playwright-mcp-server] は数回の操作で追加できます。
|
||||
|
||||
1. <kbd>Ctrl</kbd>+<kbd>,</kbd> を選択して、Copilot app の設定ページを開きます。
|
||||
2. **MCP servers** を選択します。
|
||||
3. 検索ダイアログに `Playwright` と入力します。
|
||||
4. **Popular MCP servers** の一覧から **Playwright** を選択します。
|
||||
5. **Add server** を選択し、利用可能な MCP server の一覧に追加します。
|
||||
6. <kbd>Esc</kbd> を選択して設定ダイアログを閉じます。
|
||||
|
||||
これで Playwright MCP server を追加できました。
|
||||
|
||||
## Playwright で機能を確認するよう Copilot に依頼する
|
||||
|
||||
Playwright MCP server を使って機能を手動テストするよう Copilot に依頼します。
|
||||
|
||||
1. 次のプロンプトを使い、新しい機能を検証するよう Copilot に依頼します。
|
||||
|
||||
```plaintext
|
||||
Start the dev server then use the Playwright MCP server to validate the functionality you just added exists. Use the details in the issue to ensure the newly added behavior matches the specs.
|
||||
```
|
||||
|
||||
Copilot は Playwright MCP server を通じてブラウザーを起動し、各手順を実行して、確認結果を報告します。タスクの実行中、システム上で実際にブラウザーが開く様子を確認できます。
|
||||
|
||||
2. Issue の受け入れ条件と照らし合わせて概要を読みます。問題がある場合は、pull request を作成する前に追加の質問をするか、コードを修正するよう依頼します。
|
||||
3. 次のレッスンでこの作業を完了するため、セッションを開いたままにします。
|
||||
|
||||
これで Copilot は、ユーザーと同じように機能を確認し、ブラウザーでも動作を検証しました。
|
||||
|
||||
## まとめと次のステップ
|
||||
|
||||
GitHub Copilot app から Playwright MCP server を使い、実際のブラウザーで機能を確認しました。学習した内容は次のとおりです。
|
||||
|
||||
- Model Context Protocol (MCP) の概要と、アプリで MCP tools を利用する仕組みを学習した。
|
||||
- アプリの設定から Playwright MCP server を追加した。
|
||||
- エージェントにブラウザーを操作させ、フィルター機能を確認した。
|
||||
|
||||
機能の構築と検証が完了し、動作することも確認できました。次は、**Agent Merge** を使って pull request の作成とマージをエージェントに任せ、機能をリリースします。[レッスン 6「Agent Merge によるマージ」][next-lesson]に進んでください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [MCP とは何か、なぜ注目されているのか][mcp-blog-post]
|
||||
- [Microsoft Playwright MCP Server][playwright-mcp-server]
|
||||
- [GitHub Copilot app での MCP server の構成][customize-app]
|
||||
|
||||
[next-lesson]: /ja-jp/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[mcp-blog-post]: https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/
|
||||
[playwright-mcp-server]: https://github.com/microsoft/playwright-mcp
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
@@ -0,0 +1,67 @@
|
||||
---
|
||||
title: "レッスン 6 - Agent Merge によるマージ"
|
||||
description: "フィルター機能の pull request を作成して My work でレビューし、マージを妨げる問題の修正とマージを Agent Merge に任せて、段階的なマージ自動化の最上位まで進みます。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
フィルター機能の構築と検証が完了し、ブラウザーで動作することも確認できました。最後のステップはマージです。このハーネスではすでに2回マージしており、どちらも pull request を作成して github.com で自分でマージしました。今回は、pull request のライフサイクル全体をアプリ内から管理する **Agent Merge** に処理を任せます。
|
||||
|
||||
このレッスンでは、次の内容を学習します。
|
||||
|
||||
- Agent Merge の概要と、マージのライフサイクルを自動化する仕組みを学ぶ。
|
||||
- フィルター機能のセッションで Agent Merge を有効にする。
|
||||
- pull request の作成、CI の実行、すべて成功した後のマージを確認する。
|
||||
|
||||
## シナリオ
|
||||
|
||||
ここ数回のモジュールでは、コードの作成から Copilot による UI の直接検証まで、さまざまなレベルの自動化を確認しました。開発をさらに高速化するために、Tailspin Toys は審査および検証済みの pull request を自動的にマージする方法を検討しています。
|
||||
|
||||
## Agent Merge の概要
|
||||
|
||||
**Agent Merge** を使うと、Copilot app で pull request をマージするまでの最終工程を自動化できます。有効にすると、アプリのセッションが pull request を読み取り、失敗した CI チェックの修正、レビューコメントへの対応、必要に応じたリベースなど、マージを妨げる問題に対処します。そして GitHub で許可され次第、pull request をマージします。バックグラウンドで動作し、アプリを再起動しても継続し、pull request がマージされると自動的に無効になります。
|
||||
|
||||
ここまでは、github.com で自分で **Merge pull request** を選択していました。Agent Merge はその責任をエージェントに移すため、エージェントが PR の完了までを管理している間に次のタスクへ進めます。作業のレビューと承認は引き続き自分で行い、エージェントには機械的な最終工程だけを任せます。
|
||||
|
||||
## Agent Merge で PR を管理する
|
||||
|
||||
コードを手動でレビューし、テストを実行し、Copilot による UI の検証も完了しました。新しいコードをコードベースにマージします。Agent Merge に PR を継続的インテグレーション (CI) のプロセスからマージまで管理させます。
|
||||
|
||||
1. 前のモジュールでフィルター機能を追加していたセッションに戻ります。
|
||||
2. 右上隅にある **Create PR** の横のドロップダウンを選択します。
|
||||
3. **Agent merge** を選択して Agent Merge を有効にします。
|
||||
|
||||
|
||||
|
||||
4. ボタンのテキストが **Agent merge** に変わります。
|
||||
5. **Agent merge** ボタンを選択し、Agent Merge のプロセスを開始します。
|
||||
|
||||
Copilot app が PR の作成と管理を開始します。最初にプロジェクトを調査して PR の最適な作成方法を判断し、新しい PR を作成します。
|
||||
|
||||
しばらくすると、Copilot が再び作業を開始し、リポジトリ上ですべてのテストを実行する CI プロセスなど、PR の条件を確認します。ほかのチームメンバーによるレビュー、実行が必要なチェック (CI プロセス)、PR をマージできるかどうかのステータスを報告します。
|
||||
|
||||
6. **Agent merge** の横にあるドロップダウンを選択してから **Merge pull request** を選択し、Agent Merge に pull request のマージを許可します。
|
||||
|
||||
|
||||
|
||||
7. すべての CI プロセスが成功すると、つまりテストに合格すると、Copilot が pull request をマージします。
|
||||
|
||||
## まとめと次のステップ
|
||||
|
||||
コードの生成、テストと検証、pull request のプロセスなど、開発プロセスの複数の部分を自動化しました。具体的には、次の作業を行いました。
|
||||
|
||||
- Agent Merge の概要と、マージのライフサイクルを自動化する仕組みを学習した。
|
||||
- フィルター機能のセッションで Agent Merge を有効にした。
|
||||
- pull request の作成、CI の実行、すべて成功した後のマージを確認した。
|
||||
|
||||
次は、エージェントと一緒に作業を計画して視覚化する、より高度な方法である**キャンバス**を確認します。[レッスン 7「キャンバスを使った計画」][next-lesson]に進んでください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [GitHub Copilot app での Issue と pull request の管理][managing-issues-prs]
|
||||
- [GitHub Copilot app について][about-copilot-app]
|
||||
|
||||
[next-lesson]: /ja-jp/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,127 @@
|
||||
---
|
||||
title: "レッスン 7 - キャンバスを使った計画"
|
||||
description: "GitHub Copilot app でエージェント主導の共有キャンバスを作成し、エージェントと一緒に作業を計画して追跡します。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
ここまでは、チャットを通じてエージェントを指示してきました。しかし、多くの作業は会話の中ではなく、ボード、ドキュメント、チェックリスト上で行われます。**キャンバス**は、まさにそのような作業のために、アプリ内でユーザーとエージェントが共有できる領域です。このレッスンでは、ここまで取り組んできたバックログの計画と追跡に使用する、シンプルなキャンバスを作成します。
|
||||
|
||||
このレッスンでは、次の内容を学習します。
|
||||
|
||||
- キャンバスの概要と使用する場面を理解する。
|
||||
- バックログをトリアージする共有 Kanban ボードのキャンバスを作成する。
|
||||
- キャンバスをリポジトリに保存し、チーム向けにマージする。
|
||||
- 新しいセッションでキャンバスを開き、そこから作業を開始する。
|
||||
|
||||
## シナリオ
|
||||
|
||||
Issue の一覧は、どのような状況でも負担に感じることがあります。Tailspin Toys の開発者は、Issue をすばやくトリアージし、Copilot app で作業を開始できるツールを探しています。
|
||||
|
||||
## キャンバスとは
|
||||
|
||||
[キャンバス][canvas-docs]は、計画、トリアージボード、リリースチェックリスト、ダッシュボード、ドキュメントなどの作業成果物を扱う、共有の対話型領域です。チャットは意図の説明や曖昧さの検討に適していますが、多くの作業は具体的な*領域*上で行われます。キャンバスを使うと、その領域でエージェントと直接共同作業できます。
|
||||
|
||||
キャンバスは**双方向**です。エージェントが作業中にキャンバスを更新できる一方で、ユーザーも同じ領域を編集できます。キャンバスを作成すると、エージェントはプロンプトとワークフローに基づいて内容を構築します。その後も、機能の追加、削除、修正を依頼できます。作成したキャンバスは、アプリの右側のパネルに開きます。
|
||||
|
||||
一般的な例は次のとおりです。
|
||||
|
||||
- 1日の計画を立て、Issue と pull request に優先順位を付けるための **Markdown canvases**。
|
||||
- ユーザーとエージェントがカードを追加し、作業を列間で移動する **Agentic kanban boards**。
|
||||
- リポジトリの重要な Issue と繰り返し現れるテーマをまとめる **Issue triage boards**。
|
||||
|
||||
## キャンバスを使用する理由
|
||||
|
||||
タスクに構造、反復、検証が必要で、チャットだけでは不十分な場合はキャンバスを使用します。キャンバスでは次のことができます。
|
||||
|
||||
- ワークフローに合った実際の成果物に、エージェントの作業を結び付ける。
|
||||
- 共有領域で作業を直接調整または修正し、その変更を基にエージェントに作業を続けさせる。
|
||||
- チャットの応答だけでなく、成果物への目に見える変更として進捗を確認する。
|
||||
|
||||
## 作業を追跡するキャンバスを作成する
|
||||
|
||||
星評価、ドキュメント標準、フィルター機能をすべてマージし、多くの成果をリリースしました。しかし、バックログにはまだ項目が残っています。作業をすばやくトリアージするためのキャンバスを作成します。
|
||||
|
||||
1. GitHub Copilot app に戻ります。アプリを閉じている場合は開きます。
|
||||
2. **Home screen** を選択します。
|
||||
3. リポジトリに `tailspin-toys` が選択されていることを確認します。
|
||||
4. プロンプトボックスで次のプロンプトを使用し、要件を満たすキャンバスを作成します。
|
||||
|
||||
```plaintext
|
||||
Create a basic Kanban board canvas that allows me to quickly triage work. Highlight the three issues which are most likely to need attention right now, with the remainder in a second section down below. The top three cards should include a description of the issue's content and a justification of why they're at the top of the list. Each issue should have a button that allows me to add it to the current context for the current session so I can get to work on it straightaway.
|
||||
```
|
||||
|
||||
Copilot がキャンバスの作成を開始します。
|
||||
|
||||
> [!NOTE]
|
||||
> 作成には数分かかります。複雑なタスクであるため、最初のバージョンでは満足できない場合があります。理想のツールになるまで、プロンプトで構築を続けるよう依頼できます。
|
||||
|
||||
## キャンバスを保存してリポジトリにマージする
|
||||
|
||||
キャンバスは、指示ファイルやスキルと同様に、リポジトリのアセットにできます。Copilot にリポジトリへの追加とマージを依頼し、チーム全体で使用できるようにします。
|
||||
|
||||
1. 同じセッションで、次のプロンプトを使ってキャンバスをリポジトリに保存するよう Copilot に依頼します。
|
||||
|
||||
```plaintext
|
||||
Let's save this canvas definition to the repository so I can share it with my development team
|
||||
```
|
||||
|
||||
2. Copilot がキャンバスファイルを保存したら、右上隅にある **Create PR** の横のドロップダウンを選択します。
|
||||
3. **Agent merge** を選択して Agent Merge を有効にします。
|
||||
|
||||
|
||||
|
||||
4. ボタンのテキストが **Agent merge** に変わります。
|
||||
5. **Agent merge** ボタンを選択し、Agent Merge のプロセスを開始します。
|
||||
|
||||
Copilot app が PR の作成と管理を開始します。最初にプロジェクトを調査して PR の最適な作成方法を判断し、PR を作成します。
|
||||
|
||||
しばらくすると、Copilot が再び作業を開始し、リポジトリ上ですべてのテストを実行する CI プロセスなど、PR の条件を確認します。ほかのチームメンバーによるレビュー、実行が必要なチェック (CI プロセス)、PR をマージできるかどうかのステータスを報告します。
|
||||
|
||||
6. **Agent merge** の横にあるドロップダウンを選択してから **Merge pull request** を選択し、Agent Merge に pull request のマージを許可します。
|
||||
|
||||
|
||||
|
||||
7. すべての CI プロセスが成功するまで待ちます。成功すると、Copilot が pull request を自動的にマージします。
|
||||
|
||||
これでチーム用の新しい共有キャンバスを作成できました。
|
||||
|
||||
## キャンバスで作業する
|
||||
|
||||
キャンバスを作成できたので、新しいセッションを開始して使用します。
|
||||
|
||||
1. Copilot app で **tailspin-toys** の横にある **New session** を選択し、新しいセッションを開始します。
|
||||
2. 次のプロンプトを使い、トリアージ用キャンバスを開くよう Copilot に依頼します。
|
||||
|
||||
```plaintext
|
||||
Open the triage issues canvas
|
||||
```
|
||||
|
||||
3. 作成したキャンバスが新しいセッションで開いたことを確認します。
|
||||
4. 最も関心のある Issue の1つで **Add to current context** を選択します。
|
||||
5. Copilot が Issue の作業を開始します。
|
||||
|
||||
これで、作成したキャンバスを使って開発プロセスを効率化できました。
|
||||
|
||||
## まとめと次のステップ
|
||||
|
||||
ユーザーとエージェントが共同作業できる共有領域を作成しました。具体的には、次の作業を行いました。
|
||||
|
||||
- キャンバスの概要と使用する場面を学習した。
|
||||
- エージェントと共有の Kanban トリアージボードのキャンバスを作成した。
|
||||
- Agent Merge を使ってキャンバスをリポジトリに保存し、マージした。
|
||||
- 新しいセッションでキャンバスを開き、そこから作業を開始した。
|
||||
|
||||
バックログを追跡できるようになったので、ここまで構築した内容と今後の進め方を振り返ります。[レッスン 8「振り返りと次のステップ」][next-lesson]に進んでください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [GitHub Copilot app での canvas extension の操作][canvas-docs]
|
||||
- [Awesome Copilot の Canvases][awesome-copilot-canvases]
|
||||
- [GitHub Copilot app について][about-copilot-app]
|
||||
|
||||
[next-lesson]: /ja-jp/learning-hub/copilot-workshops/app/8-review/
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[awesome-copilot-canvases]: https://awesome-copilot.github.com/extensions/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,83 @@
|
||||
---
|
||||
title: "レッスン 8 - 振り返りと次のステップ"
|
||||
description: "GitHub Copilot app のハーネスを振り返り、繰り返し発生する作業を自動化して、次に学ぶ内容を確認します。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
ここ数回のレッスンでは、GitHub Copilot app を使い、アイデアから機能のマージまでを実践しました。取り組んだ内容は次のとおりです。
|
||||
|
||||
- リポジトリを接続し、アプリのワークスペースと用意されたバックログを確認した。
|
||||
- 直接指定したタスクと Issue からセッションを開始し、Plan モードと Autopilot モードでエージェントの動作を制御した。
|
||||
- カスタム指示と再利用可能なスキルでエージェントをガイドした。
|
||||
- Playwright MCP server を使い、実際のブラウザーで作業をテストした。
|
||||
- 共有キャンバスでエージェントと共同作業した。
|
||||
- github.com で自分でマージする方法から、**Agent Merge** に pull request のマージを任せる方法まで、段階的なマージ自動化を使って変更をリリースした。
|
||||
|
||||
繰り返し発生する作業を自動化し、ベストプラクティスと今後の進め方を確認します。
|
||||
|
||||
## 繰り返し発生する作業を自動化する
|
||||
|
||||
アプリでは、**automations** を使って、スケジュールまたはオンデマンドでエージェントを実行できます。新しい Issue のトリアージや最近のアクティビティの振り返りなど、定型的なタスクに適しています。シンプルで破壊的でない automation を作成します。
|
||||
|
||||
1. サイドバーで **Automations** を選択してから **New automation** を選択します。
|
||||
2. `Recap my recent work` などの名前を付けます。
|
||||
3. トリガーを選択します。**Manual** はオンデマンドで実行し、**On a schedule** は自動的に実行し、**When an issue is created** は新しい Issue に反応します。このレッスンでは **Manual** を選択します。
|
||||
4. automation が何も変更しないように、次の例のような読み取り専用のプロンプトを入力します。
|
||||
|
||||
```plaintext
|
||||
Summarize the pull requests merged in this repository over the last week, and list any issues still open in the backlog.
|
||||
```
|
||||
|
||||
5. プロジェクト (Tailspin Toys リポジトリ) を選択し、automation を作成します。
|
||||
6. オンデマンドで実行し、結果を確認します。
|
||||
|
||||
> [!TIP]
|
||||
> Automations はローカルまたはクラウドで実行できます。スケジュールに従って無人で実行する場合は、**Run in the cloud** を有効にし、automation に使用を許可する **Tools** を選択します。出力を信頼できるようになるまでは、スケジュールされた automations の範囲を限定し、破壊的でないものにしてください。
|
||||
|
||||
## ベストプラクティス
|
||||
|
||||
AI ツールを使用するときは、その周辺の基盤が出力の品質を左右します。このワークショップでは、指示ファイル、スキル、カスタムエージェントがそれぞれ役割を果たしました。これらに投資し、セッション間で再利用してください。
|
||||
|
||||
タスクに合わせて**モードとモデル**を選択します。構築前にアプローチを検討するには **Plan**、対象を絞った変更で作業に関与し続けるには **Interactive**、範囲が明確で分離されたタスクに限って **Autopilot** を使用します。定型的な編集には高速なモデルを選び、複雑な作業には推論能力が高く、より多くの推論を行うモデルを選びます。
|
||||
|
||||
基盤と同じくらい、コンテキストも重要です。何を、なぜ、どのように構築するかを明確に説明すると、出力は大きく変わります。アイデアを本格的なセッションに移す前に範囲を決める場所として、Quick chats が役立ちます。
|
||||
|
||||
## さらに確認する機能
|
||||
|
||||
コアワークフローを学習しました。ほかにも確認する価値がある機能があります。
|
||||
|
||||
- 完全なセッションを必要としない、その場限りの簡単な質問に使用する **Quick chats**。
|
||||
- 構築前に問題について対話し、重要なフィードバックを得るための **Rubber duck**。
|
||||
- ロール、その tools、指示をまとめ、繰り返し使用する専門的な作業に対応する [**Custom agents**][custom-agents]。
|
||||
- セッションで起きたことの記録を生成する [`/chronicle`][chronicle]。
|
||||
- Ollama、Foundry Local、LM Studio を介したローカルモデルなど、独自のプロバイダーのモデルを使用する [Bring your own key (BYOK)][byok]。
|
||||
- GitHub がホストする分離環境でセッションを実行する [Cloud sandboxes][sandboxes]。
|
||||
- アプリを直接リポジトリ、セッション、プロンプトの画面で開く [Deep links][deep-links]。
|
||||
|
||||
## 次のステップ
|
||||
|
||||
ツールを使いこなす最良の方法は、使い続けることです。実稼働コード、趣味のコード、長年構想していながら構築できていなかった小さなアプリなどに活用してください。学んだことをチームと共有し、チームからも学びましょう。そして、引き続きドキュメントを確認してください。
|
||||
|
||||
GitHub Copilot エコシステムをさらに学ぶには、[VS Code ハーネス](/ja-jp/learning-hub/copilot-workshops/vscode/)、[Copilot CLI ハーネス](/ja-jp/learning-hub/copilot-workshops/cli/)、[Cloud agent ハーネス](/ja-jp/learning-hub/copilot-workshops/cloud/)を確認してください。
|
||||
|
||||
## リソース
|
||||
|
||||
- [GitHub Copilot app について][about-copilot-app]
|
||||
- [GitHub Copilot app の概要][getting-started]
|
||||
- [GitHub Copilot app のカスタマイズ][customize]
|
||||
- [Automations の使用][using-automations]
|
||||
- [Canvas extensions の操作][canvas-docs]
|
||||
- [クラウドサンドボックスとローカルサンドボックスについて][sandboxes]
|
||||
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[customize]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[using-automations]: https://docs.github.com/copilot/how-tos/github-copilot-app/using-automations
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[chronicle]: https://docs.github.com/copilot/how-tos/copilot-cli/use-copilot-cli/chronicle
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[byok]: https://docs.github.com/copilot/how-tos/github-copilot-app/use-byok-models
|
||||
[deep-links]: https://docs.github.com/copilot/how-tos/github-copilot-app/open-with-deep-links
|
||||
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: "GitHub Copilot app"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[**GitHub Copilot app**](https://docs.github.com/copilot/concepts/agents/github-copilot-app) は Copilot CLI を基盤とするデスクトップアプリケーションで、エージェント主導の開発を単一の作業用ワークスペースで実現します。並列エージェントセッション、切り替え可能なセッションモード、共有キャンバス、GitHub Issue と pull request のネイティブ管理機能を備えています。さらに、リベース、レビューのフィードバック、CI の修正、マージまで pull request を導く **Agent Merge** も利用できます。
|
||||
|
||||
一連のレッスンでは、アプリをインストールしてプロジェクトを設定した後、アプリのワークスペースと、テンプレートによって用意されたバックログを確認します。まず、星評価を追加する小さな変更に取り組みます。次に、Issue に基づいてカスタム指示の標準を追加し、分離されたエージェントセッションでフィルター機能を構築して、再利用可能なスキルで検証します。Playwright MCP server を追加して実際のブラウザーで機能を確認した後、段階的にマージの自動化を進め、最後は **Agent Merge** で pull request をマージします。最後に、共有キャンバスで共同作業し、繰り返し発生する作業を自動化します。アイデアから機能のマージまで、開発の一連の流れを体験できます。
|
||||
|
||||
## レッスン
|
||||
|
||||
| レッスン | トピック | 説明 |
|
||||
|--------|-------|-------------|
|
||||
| [0. 前提条件][ex0] | セットアップ | Node.js をインストールし、Tailspin Toys プロジェクトの自分用コピーを作成します |
|
||||
| [1. Copilot app のインストール][ex1] | セットアップ | アプリをインストールしてプロジェクトを接続し、ワークスペースを確認します |
|
||||
| [2. 最初のエージェントセッションの実行][ex2] | 最初の変更 | セッションを開始し、最初の pull request として小さな変更をリリースします |
|
||||
| [3. カスタム指示による Copilot のガイド][ex3] | コンテキスト | Issue に基づいてドキュメント標準を追加し、マージします |
|
||||
| [4. Autopilot による機能の構築][ex4] | コア機能 | Plan と Autopilot を使ってフィルター機能を構築し、スキルで検証します |
|
||||
| [5. Playwright MCP によるテスト][ex5] | 外部ツール | Playwright MCP server を追加し、ブラウザーで機能を確認します |
|
||||
| [6. Agent Merge によるマージ][ex6] | マージ | Agent Merge でフィルター機能の pull request を修正してマージします |
|
||||
| [7. キャンバスを使った計画][ex7] | コラボレーション | 共有キャンバスを作成し、作業の計画と追跡に使用します |
|
||||
| [8. 振り返りと次のステップ][ex8] | まとめ | 繰り返し発生するタスクを自動化し、次に学ぶ内容を確認します |
|
||||
|
||||
## 前提条件
|
||||
|
||||
このワークショップに参加する前に、次のものを用意してください。
|
||||
|
||||
- [ ] 有効な **Copilot Student、Pro、Pro+、Business、Enterprise** のいずれかのプランが設定された GitHub アカウント
|
||||
- [ ] **macOS、Linux、Windows** のいずれかを実行するコンピューター
|
||||
- [ ] コンピューターに[インストールされた Git][install-git]
|
||||
|
||||
> [!TIP]
|
||||
> 有料プランを利用していない場合、認証済みの学生は [GitHub Education][callout-student-plan-education] を通じて GitHub Copilot を無料で利用できます。**Copilot Student** プランには、このワークショップで使用するエージェント、MCP、コードレビュー、Copilot CLI の各機能が含まれているため、すべてのハーネスを完了できます。
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot app は codespace ではなく自分のコンピューターで実行するため、[レッスン 0][ex0] では、アプリをインストールする前に Node.js をインストールし、プロジェクトの自分用コピーを作成します。
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot Business または Copilot Enterprise を使用している場合、アプリを使用するには管理者が **Copilot CLI** ポリシーを有効にする必要があります。
|
||||
|
||||
## はじめる
|
||||
|
||||
[**レッスン 0「前提条件」から始める →**][ex0]
|
||||
|
||||
[ex0]: /ja-jp/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex1]: /ja-jp/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[ex2]: /ja-jp/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /ja-jp/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[ex4]: /ja-jp/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[ex5]: /ja-jp/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[ex6]: /ja-jp/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[ex7]: /ja-jp/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[ex8]: /ja-jp/learning-hub/copilot-workshops/app/8-review/
|
||||
[install-git]: https://github.com/git-guides/install-git
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
@@ -0,0 +1,41 @@
|
||||
---
|
||||
title: "GitHub Copilot のエージェントを実践で学ぶ"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
GitHub Copilot に最近追加された機能は、ソフトウェア開発ライフサイクル (SDLC) 全体を通して開発者を支援する強力なツールです。GitHub の Issue や pull request を使った作業、外部サービスとの連携、そしてもちろんコードの作成も含まれます。このラボでは、実際のユースケースを通して機能を試し、ツールを最大限に活用するためのヒントを紹介します。
|
||||
|
||||
> [!CAUTION]
|
||||
> GitHub Copilot は決定論的ではなく確率的に動作するため、生成されるコードや変更されるファイルなどは毎回異なる場合があります。そのため、ラボ内のスクリーンショットやコード スニペットと、実際の結果に多少の違いが生じることがあります。これは想定される動作であり、この種のツールが持つ特性によるものです。
|
||||
>
|
||||
> 何かが壊れているように見える場合や正しく動作しない場合は、メンターに相談してください。
|
||||
|
||||
## 利用環境を選ぶ
|
||||
|
||||
GitHub Copilot は、どの環境で作業していても利用できます。希望する開発方法に合った利用環境を選び、共通の Tailspin Toys バックログに沿って演習を進めます。どの利用環境にも専用のセットアップ手順が用意されているため、選んだものからすぐに始められます。
|
||||
|
||||
### 🖥️ [VS Code](/ja-jp/learning-hub/copilot-workshops/vscode/)
|
||||
|
||||
**Visual Studio Code** と GitHub Codespaces 内で GitHub Copilot を使用します。普段使っているエディターを離れることなく、Copilot Chat のエージェント モード、MCP サーバー、カスタム エージェントを利用できます。AI 支援を IDE に直接組み込んで使いたい場合に最適です。
|
||||
|
||||
### 💻 [Copilot CLI](/ja-jp/learning-hub/copilot-workshops/cli/)
|
||||
|
||||
**GitHub Copilot CLI** は、ターミナルで動作するエージェント型アシスタントです。インストールして MCP サーバーに接続し、プラン モードでコードを生成できます。さらに、独自のスキル、カスタム エージェント、スラッシュ コマンドをすべてコマンド ラインから構築できます。
|
||||
|
||||
### 🤖 [Copilot App](/ja-jp/learning-hub/copilot-workshops/app/)
|
||||
|
||||
**GitHub Copilot app** は、Copilot CLI を基盤とするデスクトップ アプリケーションです。複数のエージェント セッションを並行して実行し、セッション モードの切り替え、キャンバスでの共同作業、GitHub Issue と pull request の管理をアプリ内で行えます。さらに **Agent Merge** を使用すると、リベース、レビュー フィードバックへの対応、CI の修正、マージまで、pull request の一連の作業を進められます。
|
||||
|
||||
### ☁️ [Copilot Cloud Agent](/ja-jp/learning-hub/copilot-workshops/cloud/)
|
||||
|
||||
**Copilot cloud agent** は、GitHub Issue の作業をバックグラウンドで進める非同期のペア プログラマーです。作業の割り当て、カスタム エージェントによる指示、エージェント ダッシュボードでの進捗確認、作成された pull request のレビューを行えます。
|
||||
|
||||
## シナリオ
|
||||
|
||||
架空の企業 Tailspin Toys に新しく参加した開発者として作業します。Tailspin Toys は、開発者をテーマにしたボード ゲームのクラウドファンディングを提供しています。これは巨大な市場です。チームのバックログはすでに GitHub Issue として登録されており、フィルタリングやページネーションなどの機能開発に加えて、アクセシビリティやコーディング規約などの品質改善にもすぐに取り組めます。サイトと Copilot の機能を確認しながら反復的に作業し、タスクを完了させます。
|
||||
|
||||
## はじめる
|
||||
|
||||
上から利用環境を選んで開始します。どの利用環境も、開発に必要なセットアップから始まります。
|
||||
@@ -0,0 +1,85 @@
|
||||
---
|
||||
title: "Lesson 0 - 필수 조건"
|
||||
description: "Tailspin Toys 프로젝트에 필요한 Node.js를 설치하고 템플릿에서 리포지토리 복사본을 만들어 GitHub Copilot app 레슨을 준비합니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
GitHub Copilot app은 Copilot과 GitHub를 모두 사용하는 중앙 허브 역할을 하는 데스크톱 앱입니다. 이 앱에서 이슈와 끌어오기 요청에 빠르게 접근하고 GitHub Copilot을 사용해 빌드할 수 있습니다. 이 워크숍에서는 Astro로 구축된 Tailspin Toys 앱과 GitHub Copilot app을 모두 로컬에서 사용합니다. 시작하기 전에 Node.js가 로컬에 설치되어 있는지 확인한 다음 Copilot app을 설치합니다.
|
||||
|
||||
이 레슨에서는 다음 작업을 수행합니다.
|
||||
|
||||
- 프로젝트 테스트를 컴퓨터에서 실행할 수 있도록 Node.js를 설치합니다.
|
||||
- 템플릿에서 Tailspin Toys 프로젝트의 복사본을 만듭니다.
|
||||
|
||||
## Node.js 설치
|
||||
|
||||
여러 레슨에서 에이전트에게 기능을 구축하고 Tailspin Toys 테스트 도구 모음을 로컬에서 실행하도록 요청합니다. 이 작업에는 프로젝트에 필요한 유일한 런타임인 [**Node.js**][nodejs]가 필요합니다. **22 이상** 버전을 설치합니다. 현재 **LTS** 릴리스가 안전한 선택입니다.
|
||||
|
||||
모든 플랫폼에서 가장 간단한 방법은 공식 설치 프로그램을 사용하는 것입니다.
|
||||
|
||||
1. 운영 체제에서 Windows Terminal, macOS 터미널 또는 평소 사용하는 도구로 터미널 창을 엽니다.
|
||||
2. 다음 명령을 실행하여 Node.js 22 이상이 설치되어 있는지 확인합니다.
|
||||
|
||||
```shell
|
||||
node --version
|
||||
```
|
||||
|
||||
3. `v22` 이상의 숫자가 표시되면 다음 섹션으로 건너뛸 수 있습니다.
|
||||
|
||||
> [!TIP]
|
||||
> Node가 설치되어 있지 않거나 업데이트해야 하는 경우에만 다음 단계를 수행하면 됩니다.
|
||||
|
||||
4. [Node.js 다운로드 페이지][node-download]를 엽니다.
|
||||
5. 운영 체제에 맞는 **LTS** 빌드를 다운로드합니다.
|
||||
6. 설치 프로그램을 실행하고 기본값을 적용합니다. Windows에서는 **Add to PATH** 옵션을 선택한 상태로 유지합니다.
|
||||
7. 설치가 끝나면 새 터미널 창을 엽니다.
|
||||
8. 새 터미널 창에서 다음 명령을 실행하여 설치를 확인합니다.
|
||||
|
||||
```bash
|
||||
node --version
|
||||
```
|
||||
|
||||
9. `v22.x.x` 이상이 표시되어야 합니다.
|
||||
|
||||
> [!TIP]
|
||||
> 컨테이너를 선호합니까? [**Docker**][docker]가 있다면 Node.js를 로컬에 설치하는 대신 리포지토리의 [dev container][dev-containers]를 사용할 수 있습니다. 이 컨테이너에는 Node가 포함되어 있으므로 두 가지가 모두 필요하지는 않습니다.
|
||||
|
||||
## 실습 리포지토리 설정
|
||||
|
||||
Tailspin Toys 프로젝트의 복사본에서 작업합니다. 지금 [템플릿 리포지토리][template-repository]에서 복사본을 만듭니다. 새 리포지토리에는 실습에 필요한 모든 파일이 들어 있으며, 다음 레슨에서 앱에 연결합니다.
|
||||
|
||||
1. 새 브라우저 창에서 이 실습의 GitHub 리포지토리인 `https://github.com/github-samples/tailspin-toys`로 이동합니다.
|
||||
2. 실습 리포지토리 페이지에서 **Use this template** 버튼을 선택한 다음 **Create a new repository**를 선택하여 리포지토리 복사본을 만듭니다.
|
||||
|
||||
|
||||
|
||||
3. GitHub 또는 Microsoft가 진행하는 이벤트에서 워크숍을 수행하는 경우 멘토가 제공한 지침을 따릅니다. 그렇지 않으면 GitHub Copilot에 접근할 수 있는 조직에 새 리포지토리를 만들 수 있습니다.
|
||||
|
||||
|
||||
|
||||
4. 이 실습에서 나중에 참조할 수 있도록 만든 리포지토리 경로(**organization-or-user-name/repository-name**)를 기록합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> 템플릿에서 리포지토리를 만들면 GitHub 이슈 백로그가 자동으로 생성됩니다. 워크숍 전체에서 이 이슈를 사용하므로 직접 등록할 항목은 없습니다.
|
||||
|
||||
## 요약 및 다음 단계
|
||||
|
||||
설정이 완료되었습니다. 프로젝트를 컴퓨터에서 빌드하고 테스트할 수 있도록 Node.js를 설치하고, 템플릿에서 Tailspin Toys 리포지토리의 복사본을 만들었습니다.
|
||||
|
||||
다음으로 GitHub Copilot app을 설치하고, 방금 만든 리포지토리를 연결하고, 워크스페이스를 살펴봅니다. [레슨 1 - GitHub Copilot app 설치][next-lesson]를 계속 진행합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [Node.js 다운로드][node-download]
|
||||
- [템플릿에서 리포지토리 만들기][template-repository]
|
||||
- [GitHub Copilot app 정보][about-copilot-app]
|
||||
|
||||
[next-lesson]: /ko-kr/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[nodejs]: https://nodejs.org/
|
||||
[node-download]: https://nodejs.org/en/download
|
||||
[docker]: https://www.docker.com/products/docker-desktop/
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
+100
@@ -0,0 +1,100 @@
|
||||
---
|
||||
title: "Lesson 1 - GitHub Copilot app 설치"
|
||||
description: "GitHub Copilot app을 설치하고, 템플릿에서 만든 리포지토리를 연결하고, 워크스페이스를 살펴보고, 빠른 채팅을 사용해 봅니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[**GitHub Copilot app**][about-copilot-app]은 에이전트 기반 개발을 위한 데스크톱 애플리케이션입니다. GitHub Copilot CLI를 기반으로 하며 GitHub와 기본적으로 통합되어 리포지토리, 브랜치, CI 파이프라인을 바로 사용할 수 있습니다. 모든 작업을 직접 수행하고 반복 작업을 자동화하는 방식 대신, 각자 격리된 워크스페이스에서 여러 에이전트를 병렬로 지시하는 워크플로를 위해 설계되었습니다. Node.js를 설치하고 프로젝트 복사본을 준비했으므로 이제 앱을 설치하고 해당 리포지토리를 연결합니다.
|
||||
|
||||
이 레슨에서는 다음 작업을 수행합니다.
|
||||
|
||||
- GitHub Copilot app을 설치하고 로그인합니다.
|
||||
- GitHub 리포지토리에서 프로젝트를 앱에 추가합니다.
|
||||
- 템플릿에서 미리 생성한 백로그를 포함하여 워크스페이스를 살펴봅니다.
|
||||
- 빠른 채팅을 사용하여 앱 자체에 관해 알아봅니다.
|
||||
|
||||
## 시나리오
|
||||
|
||||
팀에서 늘어나는 백로그를 처리하기 위해 AI 에이전트를 도입하고 있습니다. Copilot app에서는 이슈 선택, 에이전트 실행, 변경 내용 검토, 끌어오기 요청 병합을 한곳에서 지시할 수 있습니다. 이 레슨에서는 앱을 설치하고 연결한 다음 프로젝트에 관한 대화를 시작하는 방법을 익힙니다.
|
||||
|
||||
> [!NOTE]
|
||||
> 적격 Copilot 플랜인 Copilot Student 또는 유료 플랜(Pro, Pro+, Business, Enterprise)이 필요합니다. Copilot Business 또는 Copilot Enterprise를 사용하는 경우 앱을 사용하려면 관리자가 **Copilot CLI** 정책을 활성화해야 합니다.
|
||||
|
||||
## GitHub Copilot app 설치 및 구성
|
||||
|
||||
GitHub Copilot app을 사용하려면 먼저 앱을 설치해야 합니다. Windows, macOS, Linux용 버전이 제공됩니다. 앱을 설치하고 인증한 다음 Tailspin Toys 리포지토리를 앱에 추가합니다.
|
||||
|
||||
1. 브라우저에서 [GitHub Copilot app 랜딩 페이지][download-app]를 엽니다.
|
||||
2. 플랫폼에 맞는 앱을 다운로드하고 랜딩 페이지의 지침에 따라 설치합니다.
|
||||
3. 설치가 끝나면 앱을 엽니다.
|
||||
4. **Sign in to GitHub**을 선택하고 안내에 따라 인증합니다. GitHub Enterprise Server를 사용하는 경우 **Use GitHub Enterprise**를 선택하고 메시지가 표시되면 서버 주소를 입력합니다.
|
||||
5. 인증한 후 리포지토리를 연결하라는 메시지가 표시되면 방금 만든 `<YOUR_GITHUB_HANDLE>/tailspin-toys`라는 이름의 Tailspin Toys 리포지토리를 선택합니다.
|
||||
6. **Continue**를 선택하여 온보딩을 계속합니다.
|
||||
7. 테마를 선택하라는 메시지가 표시되면 가장 마음에 드는 테마를 선택한 다음 **Finish**를 선택합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> Tailspin Toys 복사본이 목록에 자동으로 나타나지 않으면 앱에서 온보딩을 완료한 후 추가할 수 있습니다. 온보딩이 끝나면 Copilot app에 홈 화면이 표시됩니다. 여기에서 **Choose from GitHub**을 선택하고 리포지토리 이름(\<YOUR_GITHUB_HANDLE\>/tailspin-toys)을 검색한 다음 해당 리포지토리를 선택합니다. 이제 리포지토리가 Copilot app에 추가됩니다.
|
||||
|
||||
## 워크스페이스 살펴보기
|
||||
|
||||
프로젝트를 연결했으므로 잠시 워크스페이스의 구성을 살펴봅니다. 앱의 사이드바는 몇 가지 영역으로 구성됩니다.
|
||||
|
||||
- **Sessions** — 에이전트가 작업하는 곳입니다. 각 세션은 격리된 워크스페이스에서 실행되므로 변경 내용이 충돌하지 않게 여러 세션을 동시에 실행할 수 있습니다. 다음 레슨에서 첫 번째 세션을 시작합니다.
|
||||
- **Quick chats** — 별도의 브랜치나 워크스페이스가 필요하지 않은 질문과 브레인스토밍을 위한 가벼운 대화입니다. 이 레슨의 마지막에서 사용해 봅니다.
|
||||
- **My work** — 앱의 **GitHub 기본 통합**을 통해 이슈와 끌어오기 요청을 표시합니다. 앱을 벗어나지 않고 이슈와 끌어오기 요청을 찾아 필터링하고, CI 상태를 확인하고, 이슈에서 세션을 시작하고, 끌어오기 요청을 검토할 수 있습니다.
|
||||
- **Automations** — 일정에 따라 또는 요청 시 실행되는 저장된 에이전트 작업입니다. 이 실습 과정의 끝부분에서 하나를 만듭니다.
|
||||
|
||||
### 미리 생성된 백로그 찾기
|
||||
|
||||
앱은 GitHub와 기본적으로 통합되므로 리포지토리에서 대기 중인 작업을 앱 안에서 바로 볼 수 있습니다. 템플릿에서 리포지토리를 만들 때 이슈 백로그가 생성되었습니다. 백로그가 있는지 확인합니다.
|
||||
|
||||
1. 사이드바에서 **My work**를 선택합니다.
|
||||
2. 템플릿은 백로그에 여덟 개의 이슈를 생성했습니다. 이 하네스에서는 다음 세 이슈에 집중합니다. 표시되는지 확인합니다.
|
||||
|
||||
- Allow users to filter games by category and publisher
|
||||
- Update our repository coding standards
|
||||
- Implement pagination on the game list page
|
||||
|
||||
3. 이슈를 선택하여 세부 정보를 읽습니다. 각 이슈는 에이전트 세션을 시작하는 지점이기도 합니다. 이 실습 과정의 뒷부분에서 이 이슈를 바탕으로 작업을 시작합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> My work의 항목 목록은 Copilot app에 추가한 리포지토리의 항목만 표시하도록 자동으로 필터링됩니다. 다른 리포지토리의 작업 항목을 보려면 해당 리포지토리를 앱에 추가합니다.
|
||||
|
||||
## 빠른 채팅 사용해 보기
|
||||
|
||||
앱에 익숙해지는 좋은 방법은 앱을 사용하여 *앱 자체*에 관해 알아보는 것입니다. 이때 **빠른 채팅**이 적합합니다. 빠른 채팅에서는 브랜치나 작업 트리를 만들지 않고 질문하거나 브레인스토밍할 수 있으므로, 세션이 필요 없는 일회성 질문에 알맞습니다.
|
||||
|
||||
1. 사이드바에서 **Quick chats** 옆의 **+**를 선택하여 새 채팅을 엽니다.
|
||||
2. 앱의 세션이 어떻게 작동하는지 질문합니다.
|
||||
|
||||
```plaintext
|
||||
How does the GitHub Copilot app use worktrees?
|
||||
```
|
||||
|
||||
3. 대화 보기에서 응답을 읽습니다. 각 세션이 격리된 git 작업 트리에서 실행되므로 변경 내용이 충돌하지 않게 여러 에이전트를 병렬로 실행할 수 있다는 점을 확인할 수 있습니다. 언제든지 대화를 계속하거나 새 채팅을 시작할 수 있습니다.
|
||||
|
||||
## 요약 및 다음 단계
|
||||
|
||||
GitHub Copilot app을 설치하고 프로젝트를 연결하고 워크스페이스를 살펴봤습니다. 다음 방법을 배웠습니다.
|
||||
|
||||
- 앱을 설치하고 GitHub에 로그인합니다.
|
||||
- GitHub 리포지토리에서 프로젝트를 추가합니다.
|
||||
- 워크스페이스를 살펴보고 **My work**에서 미리 생성된 백로그를 찾습니다.
|
||||
- 빠른 채팅을 사용하여 일회성 질문을 합니다.
|
||||
|
||||
다음으로 첫 번째 에이전트 세션을 시작하고 프로젝트를 처음으로 변경하여 게임 카드에 별점을 표시합니다. [레슨 2 - 첫 번째 에이전트 세션 실행][next-lesson]을 계속 진행합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [GitHub Copilot app 정보][about-copilot-app]
|
||||
- [GitHub Copilot app 시작하기][getting-started]
|
||||
- [GitHub Copilot app에서 에이전트 세션 사용][agent-sessions]
|
||||
|
||||
[ex0]: /ko-kr/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[next-lesson]: /ko-kr/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[download-app]: https://gh.io/app
|
||||
+135
@@ -0,0 +1,135 @@
|
||||
---
|
||||
title: "Lesson 2 - 첫 번째 에이전트 세션 실행"
|
||||
description: "GitHub Copilot app에서 첫 번째 에이전트 세션을 시작하고 게임 카드를 조금 변경한 다음 첫 번째 끌어오기 요청으로 병합합니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
이전 레슨에서는 워크스페이스를 살펴보고 빠른 채팅을 사용했습니다. 이제 **에이전트 세션**을 시작하고 프로젝트를 처음으로 변경합니다. 변경 범위는 작게 유지합니다. 게임 데이터에는 이미 별점이 있지만 홈페이지의 게임 카드에는 아직 표시되지 않습니다. 에이전트에게 별점을 표시하도록 요청하고, 변경 내용을 검토하고, 첫 번째 끌어오기 요청으로 병합합니다.
|
||||
|
||||
이 레슨에서는 다음 작업을 수행합니다.
|
||||
|
||||
- 에이전트 세션을 시작하고 세션의 구조를 알아봅니다.
|
||||
- 에이전트에게 프로젝트를 작고 구체적으로 변경하도록 요청합니다.
|
||||
- 워크스페이스의 diff 보기에서 변경 내용을 검토합니다.
|
||||
- 앱을 로컬에서 실행하여 브라우저에서 변경 내용을 확인합니다.
|
||||
- 첫 번째 끌어오기 요청을 열고 병합합니다.
|
||||
|
||||
## 시나리오
|
||||
|
||||
Tailspin Toys의 각 게임에는 별점이 있을 수 있으며, 별점은 이미 게임 세부 정보 페이지에 표시됩니다. 하지만 홈페이지의 게임 카드에는 제목, 카테고리, 퍼블리셔, 설명만 표시됩니다. 첫 세션 연습으로 에이전트에게 각 카드에 기존 별점을 표시하도록 요청합니다. 첫 번째 세션에 적합한 작고 독립적인 변경입니다.
|
||||
|
||||
## 세션 구조
|
||||
|
||||
**세션**은 격리된 자체 워크스페이스에서 실행되는 에이전트와의 대화입니다. 모든 세션에는 **전용 git 작업 트리와 브랜치**가 제공됩니다. 따라서 변경 내용이 충돌하지 않게 한 세션에서는 기능을 추가하고 다른 세션에서는 버그를 수정하는 등 여러 세션을 동시에 실행할 수 있습니다. 세션은 사이드바에서 리포지토리별로 그룹화되며, 원하는 세션을 선택하여 전환할 수 있습니다.
|
||||
|
||||
세션 안에는 에이전트와의 **대화**, 에이전트가 파일을 탐색하고 편집할 때의 **도구 활동**, diff와 함께 표시되는 **변경된 파일** 목록이 있습니다.
|
||||
|
||||
## 세션을 시작하고 변경 요청하기
|
||||
|
||||
새 세션을 시작하여 프로젝트를 탐색하고 기능을 구현합니다. [이전 레슨][prior-lesson]에서 GitHub 리포지토리의 프로젝트를 추가했습니다. 해당 리포지토리에 새 세션을 만들고 변경을 요청합니다.
|
||||
|
||||
1. GitHub Copilot app으로 돌아가거나 앱을 엽니다.
|
||||
2. **Home screen**을 선택합니다.
|
||||
3. 리포지토리로 `tailspin-toys`가 선택되어 있는지 확인합니다.
|
||||
|
||||
|
||||
|
||||
4. 다음 프롬프트를 사용하여 변경을 요청합니다.
|
||||
|
||||
```plaintext
|
||||
On the game cards, show each game's star rating. The Game type already includes a starRating field — it's a number out of 5, or null when a game hasn't been rated yet. Display it on each card in src/components/GameCard.astro, and when starRating is null show "No rating yet" instead. Keep the change small and don't restructure the card layout.
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> 프롬프트에 Copilot이 업데이트할 파일 이름을 포함했습니다. Copilot이 작업에 포함할 파일을 반드시 지정할 필요는 없지만, 방향을 제시하면 Copilot이 코드를 더 빠르게 생성하고 토큰 사용량을 줄이는 데 도움이 됩니다.
|
||||
|
||||
5. <kbd>Enter</kbd>를 선택하여 Copilot에 프롬프트를 보냅니다.
|
||||
|
||||
Copilot app은 먼저 프로젝트의 격리된 복사본인 새 작업 트리를 만들고 작업을 시작합니다. 그런 다음 프로젝트를 탐색하고 새 기능을 추가하기 위해 업데이트해야 할 파일을 찾은 후 필요한 코드를 만듭니다. 이제 Copilot app으로 새 기능을 추가했습니다.
|
||||
|
||||
## diff 검토
|
||||
|
||||
AI가 생성한 모든 변경 내용은 작더라도 병합하기 전에 검토해야 합니다. Copilot app에서 바로 변경 내용을 살펴봅니다.
|
||||
|
||||
1. 앱 오른쪽 위에서 **Toggle review panel**을 선택합니다. Copilot이 적용한 보류 중인 모든 변경 내용을 보여 주는 diff 화면이 열립니다.
|
||||
|
||||
|
||||
|
||||
2. 게임 세부 정보를 표시하는 핵심 파일인 `GameCard.astro`에 코드가 추가된 것을 확인합니다. 다음 코드와 비슷해야 합니다. 별점이 있으면 표시하고 `starRating`이 `null`이면 "No rating yet"으로 대체하는 작은 블록입니다.
|
||||
|
||||
```astro
|
||||
{game.starRating !== null ? (
|
||||
<span class="text-xs font-medium px-2.5 py-0.5 rounded bg-amber-900/60 text-amber-300" data-testid="game-rating">
|
||||
★ {game.starRating} / 5
|
||||
</span>
|
||||
) : (
|
||||
<span class="text-xs font-medium text-slate-500" data-testid="game-rating-empty">
|
||||
No rating yet
|
||||
</span>
|
||||
)}
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> 모든 생성형 AI 도구와 마찬가지로 Copilot은 결정론적이 아니라 확률적으로 작동하므로 정확한 코드는 위 예제와 다를 수 있지만 대체로 비슷해야 합니다.
|
||||
|
||||
## 변경 내용 확인
|
||||
|
||||
코드를 읽고 작동한다고 가정해서는 안 됩니다. 모든 내용을 시각적으로 테스트해야 합니다. 터미널에서 앱을 시작한 다음 모든 기능이 작동하는지 확인합니다. Copilot app에는 터미널이 기본 제공됩니다.
|
||||
|
||||
1. Copilot app 오른쪽의 검토 패널에서 **Terminal**을 선택합니다. **Terminal** 버튼이 없으면 **+**(**Open in panel** 레이블)를 선택한 다음 **Terminal**을 선택합니다.
|
||||
|
||||
|
||||
|
||||
2. 터미널 창에 다음 명령을 입력하여 웹앱의 개발 서버를 시작합니다.
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
3. 서버가 시작되면 브라우저 창을 엽니다. 잠시만 기다리면 됩니다.
|
||||
4. [http://localhost:4321](http://localhost:4321)로 이동합니다.
|
||||
5. 이제 랜딩 페이지의 모든 게임에 별점이 표시되어야 합니다.
|
||||
6. 터미널 창으로 돌아갑니다.
|
||||
7. <kbd>Ctrl</kbd>+<kbd>C</kbd>를 선택하여 개발 서버를 중지합니다.
|
||||
|
||||
## 첫 번째 끌어오기 요청 열기 및 병합
|
||||
|
||||
변경 내용이 올바르게 작동하므로 이제 제공할 차례입니다. 에이전트에게 끌어오기 요청을 열도록 요청한 다음 github.com에서 직접 검토하고 병합합니다. 지금은 이 과정을 수동으로 관리합니다. 이후 레슨에서는 Copilot이 일부 작업을 자동으로 처리하는 방법을 살펴봅니다.
|
||||
|
||||
1. 오른쪽 위에서 **Create PR**을 선택합니다.
|
||||
2. 메시지가 표시되면 **Sign in with your browser**를 선택하고 안내에 따라 인증합니다.
|
||||
3. Copilot이 PR을 만들기 시작합니다.
|
||||
|
||||
PR이 만들어지면 Copilot은 리포지토리에서 실행해야 하는 워크플로를 모니터링합니다. 잠시 후 오른쪽 위의 버튼이 **Ready to merge**로 바뀝니다. 이는 PR을 병합할 준비가 되었다는 표시입니다.
|
||||
|
||||
4. 채팅 바로 위의 **PR** 버블을 선택하여 검토 창에서 PR을 열고 끌어오기 요청을 확인합니다. 필요에 따라 여기에서 PR을 검토할 수 있습니다.
|
||||
5. 준비가 되면 **Ready to merge**를 선택합니다.
|
||||
6. 새 대화 상자에서 **Merge pull request**를 선택하여 끌어오기 요청을 병합합니다.
|
||||
|
||||
이제 웹사이트에 새 기능을 제공했습니다.
|
||||
|
||||
## 요약 및 다음 단계
|
||||
|
||||
첫 번째 에이전트 세션을 시작하고 첫 번째 변경을 제공했습니다. 구체적으로 다음 작업을 수행했습니다.
|
||||
|
||||
- 에이전트 세션을 시작하고 세션의 구조를 알아봤습니다.
|
||||
- 에이전트에게 게임 카드를 작고 구체적으로 변경하도록 지시했습니다.
|
||||
- 워크스페이스의 diff 보기에서 변경 내용을 검토했습니다.
|
||||
- 앱을 로컬에서 실행하여 브라우저에서 별점을 확인했습니다.
|
||||
- 끌어오기 요청을 열고 github.com에서 직접 병합했습니다.
|
||||
|
||||
다음으로 백로그의 이슈 중 하나에서 시작하여 앱으로 리포지토리에 사용자 지정 지침 표준을 추가합니다. [레슨 3 - 사용자 지정 지침으로 Copilot 안내][next-lesson]를 계속 진행합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [GitHub Copilot app에서 에이전트 세션 사용][agent-sessions]
|
||||
- [GitHub Copilot app 정보][about-copilot-app]
|
||||
- [GitHub Copilot app으로 이슈 및 끌어오기 요청 관리][managing-issues-prs]
|
||||
|
||||
[prior-lesson]: /ko-kr/learning-hub/copilot-workshops/app/1-install-copilot-app/#github-copilot-app-설치-및-구성
|
||||
[next-lesson]: /ko-kr/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+165
@@ -0,0 +1,165 @@
|
||||
---
|
||||
title: "Lesson 3 - 사용자 지정 지침으로 Copilot 안내"
|
||||
description: "GitHub Copilot app을 사용하여 백로그의 이슈에서 시작해 리포지토리에 사용자 지정 지침 표준을 추가하고 변경 내용을 끌어오기 요청으로 병합합니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
생성형 AI를 사용할 때는 컨텍스트가 중요합니다. 작업을 특정 방식으로 수행해야 하거나 Copilot이 알아야 할 배경 정보가 있다면 해당 컨텍스트를 제공해야 합니다. 가장 강력한 도구 중 하나는 원하는 코드의 *내용*뿐 아니라 코드의 *구조*도 설명하는 [지침 파일][instruction-files]입니다. 이 레슨에서는 리포지토리에 문서화 표준을 추가합니다. 이후 대부분의 작업과 마찬가지로 백로그의 이슈에서 시작하여 에이전트가 변경하도록 합니다.
|
||||
|
||||
이 레슨에서는 다음 작업을 수행합니다.
|
||||
|
||||
- 리포지토리 지침과 경로 범위 지침 파일이 에이전트에 전달되는 방식을 살펴봅니다.
|
||||
- 백로그의 지침 이슈에서 세션을 시작합니다.
|
||||
- 에이전트에게 `.github/copilot-instructions.md`에 문서화 표준을 추가하도록 요청합니다.
|
||||
- 변경 내용을 검토하고 끌어오기 요청으로 병합합니다.
|
||||
|
||||
## 시나리오
|
||||
|
||||
모범적인 개발 조직인 Tailspin Toys에는 개발 방식에 관한 지침과 요구 사항이 있습니다. 여기에는 다음 항목이 포함됩니다.
|
||||
|
||||
- 코드에 TSDoc doc comments 형식의 문서를 추가해야 합니다.
|
||||
- 형식을 문서화하고 린팅으로 적용해야 합니다.
|
||||
|
||||
지침 파일을 사용하면 Copilot이 이러한 방식에 맞게 작업을 수행하는 데 필요한 정보를 제공할 수 있습니다.
|
||||
|
||||
## 지침 파일
|
||||
|
||||
사용자 지정 지침은 Copilot에 컨텍스트와 기본 설정을 제공하여 코딩 스타일과 요구 사항을 더 잘 이해하게 합니다. 이 기능을 사용하면 Copilot이 더 관련성 높은 제안과 코드 조각을 생성하도록 안내할 수 있습니다. 선호하는 코딩 규칙과 라이브러리는 물론 코드에 포함할 주석 유형까지 지정할 수 있습니다. 리포지토리 전체에 적용되는 지침이나 작업 수준의 컨텍스트를 제공하는 특정 파일 유형용 지침을 만들 수 있습니다.
|
||||
|
||||
지침 파일에는 두 가지 유형이 있습니다.
|
||||
|
||||
- `.github/copilot-instructions.md`는 리포지토리의 **모든** 요청에서 Copilot에 전달되는 단일 지침 파일입니다. 이 파일에는 Copilot에 보내는 대부분의 채팅 또는 CLI 요청과 관련된 프로젝트 수준 정보를 포함해야 합니다. 사용 중인 기술 스택, 구축 중인 항목의 개요, 모범 사례, 기타 전역 지침을 포함할 수 있습니다.
|
||||
- 특정 작업이나 파일 유형에 맞게 `.github/instructions/*.instructions.md` 파일을 만들 수 있습니다. TypeScript 또는 Astro 같은 특정 언어나 UI 구성 요소 또는 새 단위 테스트 집합 만들기와 같은 작업에 관한 지침을 제공할 수 있습니다.
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot은 AGENTS.md, CLAUDE.md, GEMINI.md를 통해 지침을 가져오는 다른 표준도 지원하므로 항상 올바른 컨텍스트를 제공할 수 있습니다.
|
||||
|
||||
### 지침 파일 관리 모범 사례
|
||||
|
||||
지침 파일 만들기를 모두 다루는 것은 이 워크숍의 범위를 벗어납니다. 하지만 샘플 프로젝트의 예제는 대표적인 접근 방식을 보여 줍니다. 개괄적인 지침은 다음과 같습니다.
|
||||
|
||||
- `copilot-instructions.md`의 지침은 구축 중인 항목의 설명, 프로젝트 구조, 전역 코딩 표준 등 프로젝트 수준의 안내에 집중합니다.
|
||||
- `*.instructions.md` 파일을 사용하여 파일 유형(단위 테스트, Astro 구성 요소, 데이터 계층) 또는 특정 작업에 관한 구체적인 지침을 제공합니다.
|
||||
- 자연어를 사용하고 지침을 명확하게 유지합니다. 코드가 따라야 하는 예와 피해야 하는 예를 제공합니다.
|
||||
|
||||
AI를 사용하는 방식이 하나로 정해져 있지 않듯 지침 파일을 만드는 방식도 하나로 정해져 있지 않습니다. 실험을 통해 프로젝트에 가장 적합한 방법을 찾을 수 있습니다.
|
||||
|
||||
> [!TIP]
|
||||
> GitHub Copilot을 사용하는 모든 프로젝트에는 충실한 지침 파일 모음이 있어야 합니다. 이 프로젝트의 파일을 살펴보면 여러 코드 파일 유형을 위한 지침 파일이 있다는 것을 알 수 있습니다.
|
||||
>
|
||||
> 템플릿이나 시작점을 찾고 있습니까? 지침 파일, 사용자 지정 에이전트, 기타 리소스가 가득한 리포지토리인 [awesome-copilot][awesome-copilot]을 살펴봅니다.
|
||||
|
||||
## 프로젝트의 사용자 지정 지침 파일 살펴보기
|
||||
|
||||
이 리포지토리와 함께 제공되는 지침 파일을 읽어 봅니다. 핵심 `copilot-instructions.md` 하나와 여러 작업을 위한 `*.instructions.md` 파일 모음이 있습니다. 편집기 또는 GitHub 웹 UI에서 파일을 엽니다.
|
||||
|
||||
1. 검토 패널이 표시되지 않으면 오른쪽 위의 **Toggle review panel**을 선택하여 엽니다.
|
||||
|
||||
|
||||
|
||||
2. 검토 패널에 새 항목을 추가하려면 **+**를 선택합니다.
|
||||
3. **File**을 선택합니다.
|
||||
4. `copilot-instructions.md`를 검색합니다.
|
||||
5. 파일 목록에서 `copilot-instructions.md`를 선택하여 엽니다.
|
||||
6. 파일을 살펴봅니다. 프로젝트에 관한 간단한 설명과 **Agent notes**, **Code standards**, **Scripts**, **Repository Structure** 같은 섹션을 확인합니다. **Code standards** 아래에서 중첩된 **GitHub Actions Workflows** 지침을 확인합니다. 이 내용은 Copilot과의 모든 상호 작용에 적용됩니다.
|
||||
7. 폴더 탐색기를 열려면 **Show folder view**를 선택합니다.
|
||||
|
||||
|
||||
|
||||
8. `.github/instructions` 폴더로 이동하여 파일을 살펴봅니다. Astro 파일, Drizzle 데이터 계층, 테스트 등에 관한 지침이 있습니다.
|
||||
9. `.github/instructions/unit-tests.instructions.md`를 엽니다. 위쪽의 `applyTo` 필드는 지침이 적용되는 파일을 결정하는 glob을 리포지토리 루트 기준으로 설정합니다. 여기서는 TypeScript 테스트 파일(예: `**/*.test.ts`와 일치하는 파일)이 모두 일치합니다.
|
||||
10. 이 프로젝트의 단위 테스트 작성에 관한 구체적인 지침을 확인합니다.
|
||||
11. 마지막으로 `.github/instructions/drizzle.instructions.md`를 열고 아래쪽으로 스크롤합니다. 다른 지침 파일(예: `unit-tests.instructions.md`)과 프로젝트의 기존 파일로 연결되는 링크를 확인합니다. 이를 통해 큰 지침 집합을 더 작고 재사용 가능한 파일로 나누고 Copilot이 코드를 생성할 때 따를 예제를 지정할 수 있습니다. 이 경로는 리포지토리 루트가 아니라 지침 파일을 기준으로 합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> `copilot-instructions.md`의 **Code formatting requirements** 섹션에는 프로젝트의 코딩 표준이 있지만 아직 코드 내 문서는 요구하지 않습니다. 다음 단계에서 TSDoc doc comments와 파일 주석 헤더에 관한 규칙을 추가합니다.
|
||||
|
||||
## 지침 이슈에서 시작
|
||||
|
||||
이전 레슨에서는 직접 프롬프트로 세션을 시작했습니다. 하지만 대부분의 작업은 이슈에서 시작합니다. 지침 파일 업데이트를 위해 등록된 이슈를 바탕으로 새 세션을 만들고 업데이트를 요청합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> 지침 파일은 Copilot이 생성하는 코드에 큰 영향을 주므로 Copilot을 명확하게 안내하는지 주의 깊게 확인해야 합니다. 이 레슨처럼 Copilot으로 초안을 만든 다음 요구 사항을 충족하는지 직접 검토하는 방법이 좋습니다.
|
||||
|
||||
1. 사이드바에서 **My work**를 선택합니다.
|
||||
2. **Update our repository coding standards** 이슈를 선택하여 엽니다.
|
||||
3. 오른쪽 위의 **New session**을 선택하여 이슈를 바탕으로 새 세션을 시작합니다.
|
||||
|
||||
|
||||
|
||||
4. 다음 프롬프트를 사용하여 이슈에 문서화된 요구 사항에 맞게 지침 파일을 업데이트하도록 Copilot에 요청합니다.
|
||||
|
||||
```plaintext
|
||||
Following this issue, make the updates to the instructions files in this project to meet the requirements documented. Don't create the PR quite yet!
|
||||
```
|
||||
|
||||
Copilot이 업데이트를 적용합니다.
|
||||
|
||||
## 변경 내용 검토
|
||||
|
||||
Copilot이 적용한 업데이트를 읽고, 업데이트된 지침을 바탕으로 앞으로 생성할 코드의 예제도 요청합니다.
|
||||
|
||||
1. 오른쪽 위의 **Changes**를 선택하여 코드 변경 내용을 엽니다.
|
||||
|
||||
|
||||
|
||||
2. 업데이트된 지침 파일을 검토합니다. 코드에 문서와 주석을 추가하는 지침이 있는지 확인합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> AI는 결정론적이 아니라 확률적으로 작동하므로 정확한 텍스트는 달라질 수 있습니다.
|
||||
|
||||
3. 다음 프롬프트를 사용하여 앞으로 생성할 코드의 예제를 만들도록 Copilot에 요청합니다.
|
||||
|
||||
```plaintext
|
||||
Do not make any updates, but show me what the code would look like. Based on the new instructions, if I asked Copilot to create a new library component to return all Publishers what would that code look like?
|
||||
```
|
||||
|
||||
4. Copilot이 제안한 코드를 검토합니다. 업데이트된 지침에서 요구한 대로 TSDoc doc comments와 파일 헤더 주석이 포함되어 있는지 확인합니다.
|
||||
|
||||
이제 프로젝트의 지침 파일을 업데이트하고 그 영향을 확인했습니다.
|
||||
|
||||
## 끌어오기 요청 열기 및 병합
|
||||
|
||||
지침 파일은 리포지토리 자산이므로 팀의 다른 구성원과 공유됩니다. 다른 자산과 마찬가지로 작업 내용이 포함된 PR을 만듭니다.
|
||||
|
||||
1. 오른쪽 위에서 **Create PR**을 선택합니다.
|
||||
2. 메시지가 표시되면 **Sign in with your browser**를 선택하고 안내에 따라 인증합니다.
|
||||
3. Copilot이 PR을 만들기 시작합니다.
|
||||
|
||||
PR이 만들어지면 Copilot은 리포지토리에서 실행해야 하는 워크플로를 모니터링합니다. 잠시 후 오른쪽 위의 버튼이 **Ready to merge**로 바뀝니다. 이는 PR을 병합할 준비가 되었다는 표시입니다.
|
||||
|
||||
4. **Ready to merge**를 선택합니다.
|
||||
5. 새 대화 상자에서 **Merge pull request**를 선택하여 끌어오기 요청을 병합합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> 표준을 기본 브랜치에 병합하면 모든 사용자와 새 세션에서 프로젝트의 일부로 사용됩니다. 다음 레슨에서 최신 기본 브랜치로 필터링 세션을 시작하면 에이전트가 이 표준을 자동으로 따릅니다. 요청하지 않아도 생성된 TypeScript에 TSDoc doc comments가 포함되는 것을 통해 지침이 생성 코드에 미치는 작지만 실제적인 영향을 확인할 수 있습니다.
|
||||
|
||||
## 요약 및 다음 단계
|
||||
|
||||
앱이 지침 파일에서 컨텍스트를 가져오는 방식을 살펴본 다음 세션을 사용하여 리포지토리 전체에 적용되는 표준을 추가하고 병합했습니다. 구체적으로 다음 작업을 수행했습니다.
|
||||
|
||||
- 리포지토리의 `copilot-instructions.md`와 경로 범위 `*.instructions.md` 파일을 살펴봤습니다.
|
||||
- 백로그의 지침 이슈에서 세션을 시작했습니다.
|
||||
- 에이전트에게 `.github/copilot-instructions.md`에 문서화 표준을 추가하도록 요청했습니다.
|
||||
- 변경 내용을 검토하고 끌어오기 요청으로 병합했습니다.
|
||||
|
||||
다음으로 새 세션에서 필터링 기능을 구축하고 방금 병합한 표준이 자동으로 적용되는지 확인합니다. [레슨 4 - Autopilot으로 기능 구축][next-lesson]을 계속 진행합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [GitHub Copilot 사용자 지정을 위한 지침 파일][instruction-files]
|
||||
- [GitHub Copilot app 사용자 지정][customize-app]
|
||||
- [사용자 지정 지침 만들기 모범 사례][instructions-best-practices]
|
||||
- [Awesome Copilot — 지침 파일 및 기타 리소스 모음][awesome-copilot]
|
||||
|
||||
[next-lesson]: /ko-kr/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[instruction-files]: https://docs.github.com/copilot/customizing-copilot/about-customizing-github-copilot-chat-responses
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[awesome-copilot]: https://awesome-copilot.github.com/
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+186
@@ -0,0 +1,186 @@
|
||||
---
|
||||
title: "Lesson 4 - Autopilot으로 기능 구축"
|
||||
description: "GitHub Copilot app의 Plan 및 Autopilot 모드로 정적 클라이언트 쪽 필터링 기능을 구축하고, 문서화 표준이 적용되는지 확인하고, 에이전트 스킬로 검증합니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
지금까지 프로젝트를 작게 몇 차례 업데이트했습니다. 하지만 더 큰 변경에는 더 탄탄한 프로세스가 필요합니다. GitHub Copilot app은 기존 흐름과 함께 작동하도록 구축되어 올바른 항목을 올바른 방식으로 만들 수 있게 합니다. 이 레슨은 일반적인 개발 프로세스를 따르는 세 레슨 중 첫 번째입니다. 이슈를 사용하여 새 기능을 생성하고 에이전트 스킬로 검증 테스트와 린터를 실행합니다.
|
||||
|
||||
이 레슨에서는 다음 작업을 수행합니다.
|
||||
|
||||
- 필터링 이슈에서 새 세션을 시작합니다.
|
||||
- **Plan** 모드로 기능을 계획한 다음 **Autopilot**으로 구축합니다.
|
||||
- 생성된 코드가 이전에 병합한 문서화 표준을 따르는지 확인합니다.
|
||||
- 프로젝트의 `quality-checks` 스킬로 작업을 검증합니다.
|
||||
|
||||
## 시나리오
|
||||
|
||||
홈페이지에는 모든 게임이 표시되지만 방문자는 목록을 좁힐 수 없습니다. 필터링 이슈에서는 **category**와 **publisher**로 게임을 필터링할 수 있게 해 달라고 요청합니다. Copilot을 사용하여 이 기능을 구현합니다.
|
||||
|
||||
## 배경
|
||||
|
||||
AI 코딩 에이전트를 개발 흐름에 도입해도 기본 원칙은 달라지지 않습니다. 오히려 더 중요해집니다. 대부분의 개발자는 다음과 비슷한 흐름을 따릅니다.
|
||||
|
||||
1. 수행할 작업의 세부 정보가 담긴 이슈를 엽니다.
|
||||
2. 구축할 항목을 계획합니다.
|
||||
3. 코드를 구축하고 검토합니다.
|
||||
4. 테스트를 실행하여 코드를 검증합니다.
|
||||
5. 새 기능을 수동으로 검증합니다.
|
||||
6. 끌어오기 요청(PR)을 만듭니다.
|
||||
7. 코드를 검토하고 지속적 통합 프로세스가 성공하면 코드를 병합합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> 정확한 세부 사항은 팀과 조직에 따라 달라지지만 대부분 위 주제의 변형입니다.
|
||||
|
||||
이 표준 접근 방식을 따르면 AI가 생성한 코드가 요구 사항을 충족하고 사람이 작성한 코드와 동일한 검증 과정을 거치게 할 수 있습니다.
|
||||
|
||||
## 세션 모드
|
||||
|
||||
**세션 모드**는 에이전트의 자율성 수준을 제어합니다. 프롬프트 필드 아래의 드롭다운에서 설정하고 언제든지 변경할 수 있습니다.
|
||||
|
||||
- **Interactive**: 사용자와 에이전트가 함께 작업합니다. 에이전트는 변경을 제안하고 진행하기 전에 사용자의 입력을 기다립니다.
|
||||
- **Plan**: 에이전트가 먼저 계획을 만듭니다. 에이전트가 실행하기 전에 계획을 검토하고 승인합니다.
|
||||
- **Autopilot**: 에이전트가 입력을 기다리지 않고 코드 작성, 테스트 실행, 반복 작업을 완전히 자율적으로 수행합니다.
|
||||
|
||||
## 필터링 기능 계획
|
||||
|
||||
잠재적인 문제는 코드를 작성하기 전에 발견하는 것이 가장 좋으며, 사전 계획이 이를 돕습니다. Copilot에 계획을 요청하면 단계와 접근 방식을 문서화합니다. 계획을 검토하고 개선 제안을 한 후 해당 계획을 바탕으로 Copilot이 코드를 생성하게 할 수 있습니다.
|
||||
|
||||
이슈를 열고 새 세션을 시작한 다음 Plan 모드로 전환하여 계획을 만듭니다.
|
||||
|
||||
1. 탐색 탭에서 **My work**를 선택합니다.
|
||||
2. **Allow users to filter games by category and publisher** 이슈를 선택합니다.
|
||||
3. 오른쪽 위의 **New session**을 선택합니다.
|
||||
|
||||
|
||||
|
||||
4. 모드에 **Plan**이 표시될 때까지 <kbd>Shift</kbd>+<kbd>Tab</kbd>을 선택합니다.
|
||||
|
||||
|
||||
|
||||
5. 다음 프롬프트를 보냅니다. 이슈에서 세션을 시작했으므로 필터링 이슈는 이미 세션의 컨텍스트에 있습니다.
|
||||
|
||||
```plaintext
|
||||
Plan the work based on the requirements documented in the issue. Please ask any clarifying questions you might have as you build the plan.
|
||||
```
|
||||
|
||||
6. 에이전트가 계획을 세우면서 후속 질문을 할 수 있습니다. 기능을 구축할 방식에 따라 답변합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot은 확률적으로 작동하므로 정확한 후속 질문은 달라질 수 있으며 질문을 하지 않을 수도 있습니다. 이는 정상입니다.
|
||||
|
||||
7. 완료되면 Copilot이 계획 요약을 제공합니다. 계획을 검토합니다. 쿼리 구축, 필터 컨트롤 추가, 테스트를 제안해야 합니다. 원하는 경우 피드백을 제공하여 구체화할 수 있으며 에이전트는 제안을 새 버전에 반영합니다.
|
||||
|
||||
## Autopilot으로 구축
|
||||
|
||||
계획을 만들었으므로 Copilot이 구현을 구축하게 합니다.
|
||||
|
||||
1. **Plan summary** 대화 상자의 옵션 목록에서 **Approve and implement with autopilot**과 가장 가까운 옵션을 선택합니다.
|
||||
|
||||
Copilot이 구현 작업을 시작합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot이 필요한 코드를 자동으로 만들기 시작하지 않으면 "Go ahead and start building out the plan!" 같은 프롬프트로 요청할 수 있습니다.
|
||||
>
|
||||
> 필요한 업데이트를 만드는 데 몇 분 정도 걸립니다. 에이전트는 파일을 편집하고 만들며, 테스트를 작성하고 실행하고, 반복해서 개선합니다. 지금까지 살펴본 내용을 돌아보거나 잠시 쉬어도 좋습니다.
|
||||
|
||||
## 변경 내용 검토
|
||||
|
||||
AI가 생성한 모든 코드는 병합 전에 검토해야 합니다. 코드를 검토하고 사이트를 실행하여 올바르게 작동하는지 확인합니다.
|
||||
|
||||
1. 오른쪽 위의 **Changes**를 선택하여 코드 변경 내용을 엽니다.
|
||||
|
||||
|
||||
|
||||
2. 변경 내용을 검토합니다. 새 TypeScript, Astro, 테스트 파일이 표시되어야 합니다. 새 도우미 함수에 TSDoc doc comments와 파일 헤더 주석이 있는지 확인합니다. 레슨 3에서 병합한 문서화 표준이 요청 없이 자동으로 적용된 것입니다.
|
||||
3. Copilot app 오른쪽의 검토 패널에서 **Terminal**을 선택합니다. **Terminal** 버튼이 없으면 **+**(**Open in panel** 레이블)를 선택한 다음 **Terminal**을 선택합니다.
|
||||
|
||||
|
||||
|
||||
4. 터미널 창에 다음 명령을 입력하여 웹앱의 개발 서버를 시작합니다.
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
5. 서버가 시작되면 브라우저 창을 엽니다. 잠시만 기다리면 됩니다.
|
||||
6. [http://localhost:4321](http://localhost:4321)로 이동합니다.
|
||||
7. 이제 랜딩 페이지에 필터가 표시되어야 합니다.
|
||||
8. 올바르게 보이지 않는 항목이 있으면 Copilot에 업데이트를 요청할 수 있습니다.
|
||||
9. 만족하면 터미널 창으로 돌아갑니다.
|
||||
10. <kbd>Ctrl</kbd>+<kbd>C</kbd>를 선택하여 개발 서버를 중지합니다.
|
||||
|
||||
## quality-checks 스킬로 작업 검증
|
||||
|
||||
diff를 눈으로 확인하고 끝낼 수도 있지만 팀에는 정해진 품질 기준과 이를 반복해서 확인하는 방법이 있습니다.
|
||||
|
||||
**에이전트 스킬(Agent skills)**은 테스트 실행, 빌드 생성, 끌어오기 요청 만들기처럼 반복 가능한 작업을 수행하는 방법을 Copilot에 안내합니다. 스킬은 에이전트가 필요할 때 불러올 수 있는 지침, 스크립트, 리소스가 담긴 폴더입니다. [Agent Skills는 공개 표준][agent-skills-repo]이며 다양한 에이전트에서 사용되므로 동일한 스킬을 에이전트 모드의 Copilot Chat, Copilot cloud agent, Copilot CLI, GitHub Copilot app에서 사용할 수 있습니다.
|
||||
|
||||
스킬은 프로젝트의 `.github/skills` 폴더 또는 전역 `~/.copilot/skills`에 있습니다. 각 스킬은 YAML frontmatter의 `name`과 `description` 뒤에 Markdown 지침이 이어지는 `SKILL.md` 파일을 포함하는 폴더입니다.
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: quality-checks
|
||||
description: Run the project's test suites and linter to verify code changes are ready to commit, push, or merge.
|
||||
---
|
||||
```
|
||||
|
||||
스킬에는 스크립트, 자산, 참조 자료가 담긴 하위 폴더도 포함할 수 있습니다. 전체 구조는 [에이전트 스킬 사양][agent-skills-spec]에서 확인할 수 있습니다.
|
||||
|
||||
> [!TIP]
|
||||
> 스킬은 동적으로 불러옵니다. 에이전트는 `description` 필드를 바탕으로 적용할 스킬을 결정하므로, 명확하고 시나리오에 맞는 설명이 있어야 스킬을 제대로 사용할 수 있습니다.
|
||||
|
||||
## quality-checks 스킬 살펴보기
|
||||
|
||||
스킬의 작동 방식을 살펴봅니다.
|
||||
|
||||
1. 검토 패널이 표시되지 않으면 오른쪽 위의 **Toggle review panel**을 선택하여 엽니다.
|
||||
|
||||
|
||||
|
||||
2. 검토 패널에 새 항목을 추가하려면 **+**를 선택합니다.
|
||||
3. **File**을 선택합니다.
|
||||
4. `SKILL.md`를 검색합니다.
|
||||
5. 파일 목록에서 `SKILL.md .github/skills/quality-checks`를 선택하여 엽니다.
|
||||
6. `name`과 `description`을 확인합니다. 설명은 커밋, 푸시, 병합 전에 코드 변경을 테스트하거나 린팅하거나 검증할 때 이 스킬을 사용하라고 에이전트에 알려 줍니다.
|
||||
7. 스킬을 읽습니다. 어떤 스크립트가 어떤 도구 모음(단위 테스트, Playwright 엔드투엔드 테스트, ESLint)을 어떤 순서로 실행하는지, 일반적인 실패를 디버그하는 방법은 무엇인지 확인합니다. 따라서 에이전트가 추측하지 않고 팀의 방식대로 검사를 실행합니다.
|
||||
|
||||
## 검사 실행
|
||||
|
||||
동일한 필터링 세션에서 에이전트에게 작업을 검증하도록 요청합니다. 스킬 이름을 설명하지 않아도 에이전트가 요청과 일치시킵니다.
|
||||
|
||||
1. Copilot app으로 돌아갑니다.
|
||||
2. 슬래시 명령 `/quality-checks`를 사용하여 스킬을 직접 호출하고 <kbd>Enter</kbd>를 선택합니다.
|
||||
3. 에이전트는 스킬에 따라 단위 테스트, 린터, 엔드투엔드 테스트를 실행하고 결과를 보고합니다. 실패하는 항목이 있으면 문제를 수정하고 모두 통과할 때까지 검사를 다시 실행하도록 요청합니다.
|
||||
4. **이 세션을 열어 둡니다.** 다음 레슨에서 Playwright MCP 서버를 추가하고 실제 브라우저에서 필터링 기능이 작동하는지 확인합니다.
|
||||
|
||||
## 요약 및 다음 단계
|
||||
|
||||
실제 기능을 처음부터 끝까지 구축하고 팀의 품질 기준에 맞게 검증했습니다. 구체적으로 다음 작업을 수행했습니다.
|
||||
|
||||
- 최신 프로젝트의 필터링 이슈에서 새 세션을 시작했습니다.
|
||||
- Plan 모드로 기능을 계획하고 Autopilot으로 구축했습니다.
|
||||
- 생성된 도우미가 레슨 3에서 병합한 문서화 표준을 따르는지 확인했습니다.
|
||||
- `quality-checks` 스킬로 작업을 검증했습니다.
|
||||
|
||||
다음으로 Playwright MCP 서버를 연결하고 에이전트에게 실제 브라우저에서 필터링 기능을 살펴보도록 요청합니다. [레슨 5 - Playwright MCP 서버로 테스트][next-lesson]를 계속 진행합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [GitHub Copilot app에서 에이전트 세션 사용][agent-sessions]
|
||||
- [Agent Skills 정보][about-agent-skills]
|
||||
- [GitHub Copilot app 사용자 지정][customize-app]
|
||||
- [GitHub Copilot용 클라우드 및 로컬 샌드박스 정보][sandboxes]
|
||||
|
||||
[ex0]: /ko-kr/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex2]: /ko-kr/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /ko-kr/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[next-lesson]: /ko-kr/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-agent-skills]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[agent-skills-repo]: https://github.com/agentskills/agentskills
|
||||
[agent-skills-spec]: https://agentskills.io/specification
|
||||
@@ -0,0 +1,86 @@
|
||||
---
|
||||
title: "Lesson 5 - Playwright MCP 서버로 테스트"
|
||||
description: "GitHub Copilot app에 Playwright MCP 서버를 추가하고 에이전트에게 실제 브라우저에서 필터링 기능을 수동으로 테스트하도록 요청합니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
이전 레슨에서는 프로젝트의 자동화된 테스트 도구 모음으로 필터링 기능을 만들고 검증했습니다. 테스트는 코드 검증을 자동화하지만 에이전트가 동작을 직접 확인하게 하는 것도 강력합니다. 에이전트는 자신이 만드는 실제 UI에서 발견한 문제에 대응할 수 있습니다. MCP가 AI 에이전트에 외부 기능을 제공하는 방식을 살펴보고, Copilot이 구축 중인 사이트와 직접 상호 작용할 수 있도록 Playwright MCP 서버를 추가합니다.
|
||||
|
||||
이 레슨에서는 다음 작업을 수행합니다.
|
||||
|
||||
- Model Context Protocol (MCP)의 개념과 GitHub Copilot app에서 사용하는 방식을 이해합니다.
|
||||
- 앱 설정에서 Playwright MCP 서버를 추가합니다.
|
||||
- 에이전트에게 브라우저를 조작하여 필터링 기능을 살펴보도록 요청합니다.
|
||||
|
||||
## 시나리오
|
||||
|
||||
단위 테스트와 엔드투엔드 테스트도 중요하지만 UI 업데이트를 검증하려면 실제로 UI와 상호 작용해야 합니다. Copilot이 사용자처럼 작업 중인 웹사이트를 사용하도록 하여 변경 작업을 더 자동화하고, 업데이트가 예상대로 작동한다는 확신을 높이려고 합니다.
|
||||
|
||||
## Model Context Protocol (MCP)이란?
|
||||
|
||||
[Model Context Protocol (MCP)][mcp-blog-post]은 AI 에이전트가 외부 도구 및 서비스와 통신하는 방법을 제공합니다. MCP를 사용하면 AI 에이전트가 외부 도구 및 서비스와 실시간으로 통신할 수 있습니다. 따라서 리소스를 사용하여 최신 정보에 접근하고 도구를 사용하여 사용자를 대신해 작업을 수행할 수 있습니다.
|
||||
|
||||
이러한 도구와 리소스에는 AI 에이전트와 외부 도구 및 서비스를 연결하는 MCP 서버를 통해 접근합니다. MCP 서버는 AI 에이전트와 외부 도구(예: 기존 API 또는 NPM 패키지 같은 로컬 도구) 간의 통신을 관리합니다. 각 MCP 서버는 AI 에이전트가 접근할 수 있는 서로 다른 도구 및 리소스 집합을 나타냅니다.
|
||||
|
||||
널리 사용되는 기존 MCP 서버의 예는 다음과 같습니다.
|
||||
|
||||
- [**GitHub MCP Server**](https://github.com/github/github-mcp-server): GitHub 리포지토리 관리를 위한 API 집합에 접근할 수 있게 합니다. AI 에이전트가 새 리포지토리 만들기, 기존 리포지토리 업데이트, 이슈 및 끌어오기 요청 관리 같은 작업을 수행할 수 있습니다.
|
||||
- [**Playwright MCP Server**][playwright-mcp-server]: Playwright를 사용하는 브라우저 자동화 기능을 제공합니다. AI 에이전트가 웹페이지 이동, 양식 작성, 버튼 선택 같은 작업을 수행할 수 있습니다.
|
||||
|
||||
다양한 도구와 리소스에 접근할 수 있는 다른 MCP 서버도 많습니다. GitHub는 MCP 서버를 쉽게 찾고 생태계에 기여할 수 있도록 [MCP registry](https://github.com/mcp)를 호스팅합니다.
|
||||
|
||||
> [!CAUTION]
|
||||
> MCP 서버를 프로젝트의 다른 종속성과 동일하게 취급합니다. MCP 서버를 사용하기 전에 소스 코드를 주의 깊게 검토하고, 게시자를 확인하고, 보안 영향을 고려합니다. 신뢰하는 MCP 서버만 사용하고 중요한 리소스나 작업에 대한 접근 권한을 부여할 때 주의합니다.
|
||||
|
||||
## Playwright MCP 서버 추가
|
||||
|
||||
앱 설정에서 MCP 서버를 추가하고 관리합니다. 앱에는 인기 서버 카탈로그가 포함되어 있으므로 몇 번의 선택만으로 [Playwright MCP 서버][playwright-mcp-server]를 추가할 수 있습니다.
|
||||
|
||||
1. <kbd>Ctrl</kbd>+<kbd>,</kbd>를 선택하여 Copilot app 설정 페이지를 엽니다.
|
||||
2. **MCP servers**를 선택합니다.
|
||||
3. 검색 대화 상자에 `Playwright`를 입력합니다.
|
||||
4. **Popular MCP servers** 목록에서 **Playwright**를 선택합니다.
|
||||
5. **Add server**를 선택하여 사용 가능한 MCP 서버 목록에 추가합니다.
|
||||
6. <kbd>Esc</kbd>를 선택하여 설정 대화 상자를 닫습니다.
|
||||
|
||||
이제 Playwright MCP 서버를 추가했습니다.
|
||||
|
||||
## Copilot에 Playwright로 기능 탐색 요청
|
||||
|
||||
Copilot에 Playwright MCP 서버를 사용하여 기능을 수동으로 테스트하도록 요청합니다.
|
||||
|
||||
1. 다음 프롬프트를 사용하여 새 기능을 검증하도록 Copilot에 요청합니다.
|
||||
|
||||
```plaintext
|
||||
Start the dev server then use the Playwright MCP server to validate the functionality you just added exists. Use the details in the issue to ensure the newly added behavior matches the specs.
|
||||
```
|
||||
|
||||
Copilot은 Playwright MCP 서버를 통해 브라우저를 시작하고 각 단계를 수행한 다음 발견한 내용을 보고합니다. 작업을 수행하기 위해 시스템에서 브라우저가 실제로 열리는 것을 볼 수 있습니다.
|
||||
|
||||
2. 이슈의 승인 조건과 비교하여 요약을 읽습니다. 올바르지 않은 부분이 있으면 후속 질문을 하거나 끌어오기 요청을 열기 전에 코드를 수정하도록 요청합니다.
|
||||
3. 다음 레슨에서 이 세션을 마무리하므로 세션을 열어 둡니다.
|
||||
|
||||
이제 Copilot은 사용자처럼 기능을 살펴보며 브라우저에서도 기능을 검증했습니다.
|
||||
|
||||
## 요약 및 다음 단계
|
||||
|
||||
GitHub Copilot app에서 Playwright MCP 서버를 사용하여 실제 브라우저로 기능을 살펴봤습니다. 요약하면 다음 작업을 수행했습니다.
|
||||
|
||||
- Model Context Protocol (MCP)의 개념과 앱에서 MCP 도구를 제공하는 방식을 배웠습니다.
|
||||
- 앱 설정에서 Playwright MCP 서버를 추가했습니다.
|
||||
- 에이전트에게 브라우저를 조작하여 필터링 기능을 살펴보도록 요청했습니다.
|
||||
|
||||
기능을 구축하고 검증하고 작동하는 모습까지 확인했습니다. 이제 **Agent Merge**를 사용하여 끌어오기 요청을 열고 병합하도록 합니다. [레슨 6 - Agent Merge로 병합][next-lesson]을 계속 진행합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [MCP란 무엇이며 왜 모두가 이야기할까요?][mcp-blog-post]
|
||||
- [Microsoft Playwright MCP Server][playwright-mcp-server]
|
||||
- [GitHub Copilot app에서 MCP 서버 구성][customize-app]
|
||||
|
||||
[next-lesson]: /ko-kr/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[mcp-blog-post]: https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/
|
||||
[playwright-mcp-server]: https://github.com/microsoft/playwright-mcp
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
@@ -0,0 +1,67 @@
|
||||
---
|
||||
title: "Lesson 6 - Agent Merge로 병합"
|
||||
description: "필터링 끌어오기 요청을 열고 My work에서 검토한 다음, Agent Merge가 차단 요소를 수정하고 병합하도록 하여 병합 자동화의 최상위 단계를 경험합니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
필터링 기능을 구축하고 검증하고 브라우저에서 작동하는 모습까지 확인했습니다. 마지막 단계는 병합입니다. 이 실습 과정에서 이미 두 번 병합했으며, 두 번 모두 끌어오기 요청을 열고 github.com에서 직접 병합했습니다. 이번에는 앱 안에서 끌어오기 요청의 전체 수명 주기를 관리하는 **Agent Merge**를 사용하여 앱이 번거로운 작업을 처리하게 합니다.
|
||||
|
||||
이 레슨에서는 다음 작업을 수행합니다.
|
||||
|
||||
- Agent Merge의 개념과 병합 수명 주기를 자동화하는 방식을 알아봅니다.
|
||||
- 필터링 세션에서 Agent Merge를 활성화합니다.
|
||||
- Agent Merge가 끌어오기 요청을 만들고 CI를 실행한 다음 모든 검사가 통과하면 병합하는 과정을 확인합니다.
|
||||
|
||||
## 시나리오
|
||||
|
||||
지난 몇 개 모듈에서 코드 생성부터 Copilot이 UI를 직접 검증하도록 하는 것까지 다양한 자동화 수준을 살펴봤습니다. Tailspin Toys는 개발 속도를 더욱 높이기 위해 검토와 검증을 마친 끌어오기 요청을 자동으로 병합할 방법이 있는지 알아보려고 합니다.
|
||||
|
||||
## Agent Merge 소개
|
||||
|
||||
**Agent Merge**는 Copilot app을 통해 끌어오기 요청을 병합하는 마지막 단계를 자동화합니다. 활성화하면 앱의 세션이 끌어오기 요청을 읽고, 실패한 CI 검사 수정, 검토 의견 대응, 필요할 때 리베이스 수행 등 병합을 차단하는 문제를 해결한 다음 GitHub에서 허용하는 즉시 병합합니다. 백그라운드에서 실행되고 앱을 다시 시작해도 계속 작동하며 끌어오기 요청이 병합되면 자동으로 꺼집니다.
|
||||
|
||||
지금까지는 github.com에서 직접 **Merge pull request**를 선택했습니다. Agent Merge는 해당 책임을 에이전트로 옮기므로, 에이전트가 PR 완료 과정을 관리하는 동안 다음 작업으로 넘어갈 수 있습니다. 작업을 검토하고 승인하는 책임은 여전히 사용자에게 있으며, 에이전트는 기계적인 마무리 작업만 처리합니다.
|
||||
|
||||
## Agent Merge로 PR 관리
|
||||
|
||||
코드를 직접 검토하고 테스트를 실행했으며 Copilot이 UI를 검증하도록 했습니다. 이제 새 코드를 코드베이스에 병합합니다. Agent Merge가 지속적 통합(CI)과 병합 과정을 관리하게 합니다.
|
||||
|
||||
1. 이전 모듈에서 필터링 기능을 추가하며 열어 둔 세션으로 돌아갑니다.
|
||||
2. 오른쪽 위에서 **Create PR** 옆의 드롭다운을 선택합니다.
|
||||
3. **Agent merge**를 선택하여 Agent Merge를 활성화합니다.
|
||||
|
||||
|
||||
|
||||
4. 이제 버튼 텍스트가 **Agent merge**로 바뀝니다.
|
||||
5. **Agent merge** 버튼을 선택하여 Agent Merge 프로세스를 시작합니다.
|
||||
|
||||
Copilot app이 PR을 만들고 관리하는 프로세스를 시작합니다. 먼저 프로젝트를 탐색하여 PR을 만드는 최적의 방법을 결정한 다음 새 PR을 만듭니다.
|
||||
|
||||
잠시 후 Copilot이 다시 작업을 시작하여 PR 조건, 즉 리포지토리의 모든 테스트를 실행하는 CI 프로세스를 확인합니다. 다른 팀 구성원이 남긴 검토, 실행해야 하는 검사(CI 프로세스), PR의 병합 가능 여부를 보고합니다.
|
||||
|
||||
6. **Agent merge** 옆의 드롭다운을 선택한 다음 **Merge pull request**를 선택하여 Agent Merge가 끌어오기 요청을 병합하도록 허용합니다.
|
||||
|
||||
|
||||
|
||||
7. 모든 CI 프로세스가 통과하면, 즉 테스트가 성공하면 Copilot이 끌어오기 요청을 병합합니다.
|
||||
|
||||
## 요약 및 다음 단계
|
||||
|
||||
코드 생성, 코드 테스트와 검증, 끌어오기 요청 프로세스를 포함한 개발 프로세스의 여러 부분을 자동화했습니다. 다음 작업을 수행했습니다.
|
||||
|
||||
- Agent Merge의 개념과 병합 수명 주기를 자동화하는 방식을 배웠습니다.
|
||||
- 필터링 세션에서 Agent Merge를 활성화했습니다.
|
||||
- Agent Merge가 끌어오기 요청을 만들고 CI를 실행한 다음 모든 검사가 통과했을 때 병합하는 과정을 확인했습니다.
|
||||
|
||||
다음으로 에이전트와 함께 작업을 계획하고 시각화하는 더 풍부한 방법인 **캔버스**를 살펴봅니다. [레슨 7 - 캔버스로 계획 수립][next-lesson]을 계속 진행합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [GitHub Copilot app으로 이슈 및 끌어오기 요청 관리][managing-issues-prs]
|
||||
- [GitHub Copilot app 정보][about-copilot-app]
|
||||
|
||||
[next-lesson]: /ko-kr/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,127 @@
|
||||
---
|
||||
title: "Lesson 7 - 캔버스로 계획 수립"
|
||||
description: "GitHub Copilot app에서 공유 에이전트 기반 캔버스를 만들어 에이전트와 함께 작업을 계획하고 추적합니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
지금까지 채팅을 통해 에이전트를 지시했습니다. 하지만 많은 작업은 대화가 아니라 보드, 문서, 검사 목록에서 이루어집니다. **캔버스**는 바로 이러한 작업을 위해 앱 안에서 사용자와 에이전트가 함께 사용하는 화면을 제공합니다. 이 레슨에서는 지금까지 처리한 백로그를 계획하고 추적하는 간단한 캔버스를 만듭니다.
|
||||
|
||||
이 레슨에서는 다음 작업을 수행합니다.
|
||||
|
||||
- 캔버스의 개념과 사용 시점을 이해합니다.
|
||||
- 백로그를 분류하는 공유 Kanban 보드 캔버스를 만듭니다.
|
||||
- 캔버스를 리포지토리에 저장하고 팀에서 사용할 수 있도록 병합합니다.
|
||||
- 새 세션에서 캔버스를 열고 캔버스에서 작업을 시작합니다.
|
||||
|
||||
## 시나리오
|
||||
|
||||
이슈 목록은 아무리 좋은 상황에서도 부담스러울 수 있습니다. Tailspin Toys 개발자는 이슈를 빠르게 분류하고 Copilot app에서 작업을 시작할 수 있는 도구를 찾고 있습니다.
|
||||
|
||||
## 캔버스란?
|
||||
|
||||
[캔버스][canvas-docs]는 계획, 분류 보드, 릴리스 검사 목록, 대시보드, 문서 같은 작업 산출물을 위한 공유 대화형 화면입니다. 채팅은 의도를 설명하고 모호한 부분을 함께 추론하는 데 유용하지만 대부분의 작업은 *화면*에서 이루어집니다. 캔버스를 사용하면 해당 화면에서 에이전트와 직접 협업할 수 있습니다.
|
||||
|
||||
캔버스는 **양방향**입니다. 에이전트가 작업하면서 캔버스를 업데이트할 수 있고 사용자도 동일한 화면을 편집할 수 있습니다. 캔버스를 만들면 에이전트가 프롬프트와 워크플로를 바탕으로 구축하며, 진행하면서 기능을 추가하거나 제거하거나 수정하도록 요청할 수 있습니다. 캔버스를 만들면 앱의 오른쪽 패널에서 열립니다.
|
||||
|
||||
일반적인 예는 다음과 같습니다.
|
||||
|
||||
- 하루를 계획하고 이슈와 끌어오기 요청의 우선순위를 정하는 **Markdown 캔버스**
|
||||
- 사용자와 에이전트가 카드를 추가하고 열 사이에서 작업을 이동하는 **에이전트 Kanban 보드**
|
||||
- 리포지토리의 주요 이슈와 반복되는 주제를 요약하는 **이슈 분류 보드**
|
||||
|
||||
## 캔버스를 사용하는 이유
|
||||
|
||||
작업에 구조화, 반복, 검증이 필요하고 채팅만으로 충분하지 않다면 캔버스를 사용합니다. 캔버스로 다음 작업을 수행할 수 있습니다.
|
||||
|
||||
- 워크플로에 맞는 실제 산출물을 기반으로 에이전트가 작업하게 합니다.
|
||||
- 공유 화면에서 작업을 직접 안내하거나 수정한 다음 에이전트가 변경 내용에서 계속 작업하게 합니다.
|
||||
- 채팅 응답만 보는 대신 산출물의 눈에 보이는 변경으로 진행 상황을 확인합니다.
|
||||
|
||||
## 작업 추적 캔버스 만들기
|
||||
|
||||
별점, 문서화 표준, 필터링 기능을 모두 병합하여 많은 작업을 제공했습니다. 하지만 백로그에는 아직 항목이 남아 있습니다. 작업을 빠르게 분류하는 데 도움이 되는 캔버스를 만듭니다.
|
||||
|
||||
1. GitHub Copilot app으로 돌아가거나 앱을 엽니다.
|
||||
2. **Home screen**을 선택합니다.
|
||||
3. 리포지토리로 `tailspin-toys`가 선택되어 있는지 확인합니다.
|
||||
4. 프롬프트 상자에서 다음 프롬프트를 사용하여 요구 사항을 충족하는 캔버스를 만듭니다.
|
||||
|
||||
```plaintext
|
||||
Create a basic Kanban board canvas that allows me to quickly triage work. Highlight the three issues which are most likely to need attention right now, with the remainder in a second section down below. The top three cards should include a description of the issue's content and a justification of why they're at the top of the list. Each issue should have a button that allows me to add it to the current context for the current session so I can get to work on it straightaway.
|
||||
```
|
||||
|
||||
Copilot이 캔버스를 만들기 시작합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> 이 작업에는 몇 분 정도 걸립니다. 복잡한 작업이므로 첫 번째 버전이 만족스럽지 않을 수 있습니다. 원하는 도구가 완성될 때까지 프롬프트로 계속 개선할 수 있습니다.
|
||||
|
||||
## 캔버스를 저장하고 리포지토리에 병합
|
||||
|
||||
캔버스는 지침 파일 및 스킬과 마찬가지로 리포지토리의 자산이 될 수 있습니다. Copilot에 캔버스를 리포지토리에 추가하고 병합하도록 요청하여 팀 전체에서 사용하게 합니다.
|
||||
|
||||
1. 같은 세션에서 다음 프롬프트를 사용하여 캔버스를 리포지토리에 저장하도록 Copilot에 요청합니다.
|
||||
|
||||
```plaintext
|
||||
Let's save this canvas definition to the repository so I can share it with my development team
|
||||
```
|
||||
|
||||
2. Copilot이 캔버스 파일을 저장하면 오른쪽 위에서 **Create PR** 옆의 드롭다운을 선택합니다.
|
||||
3. **Agent merge**를 선택하여 Agent Merge를 활성화합니다.
|
||||
|
||||
|
||||
|
||||
4. 이제 버튼 텍스트가 **Agent merge**로 바뀝니다.
|
||||
5. **Agent merge** 버튼을 선택하여 Agent Merge 프로세스를 시작합니다.
|
||||
|
||||
Copilot app이 PR을 만들고 관리하는 프로세스를 시작합니다. 먼저 프로젝트를 탐색하여 PR을 만드는 최적의 방법을 결정한 다음 PR을 만듭니다.
|
||||
|
||||
잠시 후 Copilot이 다시 작업을 시작하여 PR 조건, 즉 리포지토리의 모든 테스트를 실행하는 CI 프로세스를 확인합니다. 다른 팀 구성원이 남긴 검토, 실행해야 하는 검사(CI 프로세스), PR의 병합 가능 여부를 보고합니다.
|
||||
|
||||
6. **Agent merge** 옆의 드롭다운을 선택한 다음 **Merge pull request**를 선택하여 Agent Merge가 끌어오기 요청을 병합하도록 허용합니다.
|
||||
|
||||
|
||||
|
||||
7. 모든 CI 프로세스가 통과할 때까지 기다립니다. 모두 통과하면 Copilot이 끌어오기 요청을 자동으로 병합합니다.
|
||||
|
||||
이제 팀을 위한 새 공유 캔버스를 만들었습니다.
|
||||
|
||||
## 캔버스에서 작업
|
||||
|
||||
캔버스를 만들었으므로 새 세션을 시작하고 사용해 봅니다.
|
||||
|
||||
1. Copilot app에서 **tailspin-toys** 옆의 **New session**을 선택하여 새 세션을 시작합니다.
|
||||
2. 다음 프롬프트를 사용하여 분류 캔버스를 열도록 Copilot에 요청합니다.
|
||||
|
||||
```plaintext
|
||||
Open the triage issues canvas
|
||||
```
|
||||
|
||||
3. 이제 새 세션에서 만든 캔버스가 열리는 것을 확인합니다.
|
||||
4. 가장 관심 있는 이슈 중 하나에서 **Add to current context**를 선택합니다.
|
||||
5. Copilot이 이슈 작업을 시작합니다.
|
||||
|
||||
이제 직접 만든 캔버스를 사용하여 개발 프로세스를 간소화했습니다.
|
||||
|
||||
## 요약 및 다음 단계
|
||||
|
||||
사용자와 에이전트가 협업하는 공유 화면을 만들었습니다. 다음 작업을 수행했습니다.
|
||||
|
||||
- 캔버스의 개념과 사용 시점을 배웠습니다.
|
||||
- 에이전트와 공유 Kanban 분류 보드 캔버스를 만들었습니다.
|
||||
- Agent Merge를 사용하여 캔버스를 리포지토리에 저장하고 병합했습니다.
|
||||
- 새 세션에서 캔버스를 열고 캔버스를 사용하여 작업을 시작했습니다.
|
||||
|
||||
백로그를 추적하도록 설정했으므로 지금까지 구축한 항목과 다음 단계를 돌아봅니다. [레슨 8 - 검토 및 다음 단계][next-lesson]를 계속 진행합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [GitHub Copilot app에서 캔버스 확장 사용][canvas-docs]
|
||||
- [Awesome Copilot의 캔버스][awesome-copilot-canvases]
|
||||
- [GitHub Copilot app 정보][about-copilot-app]
|
||||
|
||||
[next-lesson]: /ko-kr/learning-hub/copilot-workshops/app/8-review/
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[awesome-copilot-canvases]: https://awesome-copilot.github.com/extensions/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,83 @@
|
||||
---
|
||||
title: "Lesson 8 - 검토 및 다음 단계"
|
||||
description: "GitHub Copilot app 실습 과정을 되짚어 보고, 반복 작업을 자동화하고, 다음에 살펴볼 내용을 알아봅니다."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
지난 여러 레슨에서 GitHub Copilot app으로 아이디어를 기능으로 만들고 병합하기까지 다음 작업을 수행했습니다.
|
||||
|
||||
- 리포지토리를 연결하고 앱의 워크스페이스와 미리 생성된 백로그를 살펴봤습니다.
|
||||
- 직접 작업과 이슈에서 세션을 시작하고 Plan 및 Autopilot 모드로 에이전트의 작업 방식을 제어했습니다.
|
||||
- 사용자 지정 지침과 재사용 가능한 스킬로 에이전트를 안내했습니다.
|
||||
- Playwright MCP 서버를 사용하여 실제 브라우저에서 작업을 테스트했습니다.
|
||||
- 공유 캔버스에서 에이전트와 협업했습니다.
|
||||
- github.com에서 직접 병합하는 단계부터 **Agent Merge**가 끌어오기 요청을 병합하는 단계까지 병합 자동화 수준을 높여 변경 내용을 제공했습니다.
|
||||
|
||||
이제 반복 작업을 자동화하고 모범 사례를 살펴본 다음 앞으로 진행할 방향을 알아봅니다.
|
||||
|
||||
## 반복 작업 자동화
|
||||
|
||||
앱은 **자동화**를 통해 일정에 따라 또는 요청 시 에이전트를 실행할 수 있습니다. 새 이슈 분류나 최근 활동 요약 같은 일상적인 작업에 유용합니다. 간단하고 비파괴적인 자동화를 하나 만듭니다.
|
||||
|
||||
1. 사이드바에서 **Automations**를 선택한 다음 **New automation**을 선택합니다.
|
||||
2. `Recap my recent work` 같은 이름을 지정합니다.
|
||||
3. 트리거를 선택합니다. **Manual**은 요청 시 실행하고, **On a schedule**은 자동으로 실행하며, **When an issue is created**는 새 이슈에 반응합니다. 이 레슨에서는 **Manual**을 선택합니다.
|
||||
4. 자동화가 내용을 변경할 수 없도록 다음과 같은 읽기 전용 프롬프트를 입력합니다.
|
||||
|
||||
```plaintext
|
||||
Summarize the pull requests merged in this repository over the last week, and list any issues still open in the backlog.
|
||||
```
|
||||
|
||||
5. 프로젝트(Tailspin Toys 리포지토리)를 선택하고 자동화를 만듭니다.
|
||||
6. 요청 시 실행하여 결과를 확인합니다.
|
||||
|
||||
> [!TIP]
|
||||
> 자동화는 로컬 또는 클라우드에서 실행할 수 있습니다. 일정에 따라 사용자 없이 실행하려면 **Run in the cloud**를 활성화하고 자동화에서 사용할 수 있는 **Tools**를 선택합니다. 출력 결과를 신뢰할 수 있을 때까지 예약 자동화의 범위를 제한하고 비파괴적으로 유지합니다.
|
||||
|
||||
## 모범 사례
|
||||
|
||||
AI 도구를 사용할 때는 도구를 둘러싼 인프라가 결과의 품질을 좌우합니다. 이 워크숍에서는 지침 파일, 스킬, 사용자 지정 에이전트를 모두 사용했습니다. 이러한 항목에 투자하고 세션 간에 재사용합니다.
|
||||
|
||||
작업에 맞는 **모드와 모델**을 선택합니다. 구축 전에 접근 방식을 검토하려면 **Plan**을 사용하고, 범위가 명확한 변경에서 계속 참여하려면 **Interactive**를 사용하며, 범위가 명확하고 격리된 작업에만 **Autopilot**을 사용합니다. 일상적인 편집에는 빠른 모델을 선택하고 복잡한 작업에는 추론 능력이 더 높은 모델을 선택합니다.
|
||||
|
||||
컨텍스트는 인프라만큼 중요합니다. 만들려는 *항목*, 그 *이유*, 원하는 *방식*을 명확하게 설명하면 출력이 크게 달라집니다. 빠른 채팅은 아이디어를 전체 세션에 적용하기 전에 범위를 정하기에 적합합니다.
|
||||
|
||||
## 더 살펴볼 내용
|
||||
|
||||
핵심 워크플로를 모두 살펴봤습니다. 다음 기능도 확인해 볼 만합니다.
|
||||
|
||||
- 전체 세션이 필요 없는 빠른 일회성 질문을 위한 **Quick chats**
|
||||
- 구축 전에 문제를 함께 검토하고 유용한 피드백을 받기 위한 **Rubber duck**
|
||||
- 반복 가능한 전문 작업을 위해 역할, 도구, 지침을 패키지하는 [**Custom agents**][custom-agents]
|
||||
- 세션에서 일어난 일을 서술형으로 생성하는 [`/chronicle`][chronicle]
|
||||
- Ollama, Foundry Local, LM Studio를 통한 로컬 모델을 포함하여 자체 공급자의 모델을 사용하는 [Bring your own key (BYOK)][byok]
|
||||
- GitHub에서 호스팅하는 격리된 환경에서 세션을 실행하는 [Cloud sandboxes][sandboxes]
|
||||
- 리포지토리, 세션, 프롬프트에서 바로 앱을 여는 [Deep links][deep-links]
|
||||
|
||||
## 다음 단계
|
||||
|
||||
어떤 도구든 더 능숙하게 사용하려면 계속 사용해야 합니다. 프로덕션 코드, 취미 프로젝트, 오랫동안 생각만 하고 만들지 못했던 작은 앱에 사용해 봅니다. 배운 내용을 팀과 공유하고 팀의 경험에서도 배웁니다. 언제나 그렇듯 문서를 살펴봅니다.
|
||||
|
||||
GitHub Copilot 생태계를 더 살펴보려면 [VS Code 실습 과정](/ko-kr/learning-hub/copilot-workshops/vscode/), [Copilot CLI 실습 과정](/ko-kr/learning-hub/copilot-workshops/cli/), [Cloud agent 실습 과정](/ko-kr/learning-hub/copilot-workshops/cloud/)을 확인합니다.
|
||||
|
||||
## 리소스
|
||||
|
||||
- [GitHub Copilot app 정보][about-copilot-app]
|
||||
- [GitHub Copilot app 시작하기][getting-started]
|
||||
- [GitHub Copilot app 사용자 지정][customize]
|
||||
- [자동화 사용][using-automations]
|
||||
- [캔버스 확장 사용][canvas-docs]
|
||||
- [클라우드 및 로컬 샌드박스 정보][sandboxes]
|
||||
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[customize]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[using-automations]: https://docs.github.com/copilot/how-tos/github-copilot-app/using-automations
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[chronicle]: https://docs.github.com/copilot/how-tos/copilot-cli/use-copilot-cli/chronicle
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[byok]: https://docs.github.com/copilot/how-tos/github-copilot-app/use-byok-models
|
||||
[deep-links]: https://docs.github.com/copilot/how-tos/github-copilot-app/open-with-deep-links
|
||||
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: "GitHub Copilot app"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[**GitHub Copilot app**](https://docs.github.com/copilot/concepts/agents/github-copilot-app)은 Copilot CLI를 기반으로 구축된 데스크톱 애플리케이션으로, 에이전트 기반 개발을 하나의 집중된 워크스페이스에서 수행할 수 있게 해 줍니다. 병렬 에이전트 세션, 전환 가능한 세션 모드, 공유 캔버스, GitHub 이슈 및 끌어오기 요청 기본 관리 기능을 제공합니다. 여기에는 끌어오기 요청의 리베이스, 검토 피드백, CI 수정, 병합 과정을 관리하는 **Agent Merge**도 포함됩니다.
|
||||
|
||||
이 레슨에서는 앱을 설치하고 프로젝트를 설정한 다음, 앱 워크스페이스와 템플릿에서 미리 생성한 백로그를 살펴봅니다. 별점을 추가하는 작은 변경으로 시작한 뒤, 이슈를 바탕으로 사용자 지정 지침 표준을 추가하고, 격리된 에이전트 세션에서 필터링 기능을 구축하고, 재사용 가능한 스킬로 검증합니다. Playwright MCP 서버를 추가하여 실제 브라우저에서 기능을 살펴본 다음, **Agent Merge**가 끌어오기 요청을 병합하는 단계까지 병합 자동화 수준을 높입니다. 마지막으로 공유 캔버스에서 협업하고 반복 작업을 자동화하여 아이디어를 병합된 기능으로 완성하는 전체 과정을 경험합니다.
|
||||
|
||||
## 레슨
|
||||
|
||||
| 레슨 | 주제 | 설명 |
|
||||
|--------|-------|-------------|
|
||||
| [0. 필수 조건][ex0] | 설정 | Node.js를 설치하고 Tailspin Toys 프로젝트의 복사본 만들기 |
|
||||
| [1. Copilot app 설치][ex1] | 설정 | 앱을 설치하고 프로젝트를 연결한 다음 워크스페이스 살펴보기 |
|
||||
| [2. 첫 번째 에이전트 세션 실행][ex2] | 첫 번째 변경 | 세션을 시작하고 작은 변경을 첫 번째 끌어오기 요청으로 제공하기 |
|
||||
| [3. 사용자 지정 지침으로 Copilot 안내][ex3] | 컨텍스트 | 이슈를 바탕으로 문서화 표준을 추가하고 병합하기 |
|
||||
| [4. Autopilot으로 기능 구축][ex4] | 핵심 기능 | Plan과 Autopilot으로 필터링 기능을 구축한 다음 스킬로 검증하기 |
|
||||
| [5. Playwright MCP로 테스트][ex5] | 외부 도구 | Playwright MCP 서버를 추가하고 브라우저에서 기능 살펴보기 |
|
||||
| [6. Agent Merge로 병합][ex6] | 병합 | Agent Merge가 필터링 끌어오기 요청을 수정하고 병합하도록 하기 |
|
||||
| [7. 캔버스로 계획 수립][ex7] | 협업 | 작업을 계획하고 추적하는 공유 캔버스 만들기 |
|
||||
| [8. 검토 및 다음 단계][ex8] | 요약 | 반복 작업을 자동화하고 다음에 살펴볼 내용 알아보기 |
|
||||
|
||||
## 필수 조건
|
||||
|
||||
워크숍에 참여하기 전에 다음 항목을 준비했는지 확인합니다.
|
||||
|
||||
- [ ] 활성 **Copilot Student, Pro, Pro+, Business, or Enterprise** 플랜이 있는 GitHub 계정
|
||||
- [ ] **macOS, Linux, or Windows**를 실행하는 컴퓨터
|
||||
- [ ] 컴퓨터에 [Git 설치][install-git]
|
||||
|
||||
> [!TIP]
|
||||
> 유료 플랜이 없습니까? 인증된 학생은 [GitHub Education][callout-student-plan-education]을 통해 GitHub Copilot을 무료로 사용할 수 있습니다. **Copilot Student** 플랜에는 이 워크숍에서 사용하는 에이전트, MCP, 코드 검토, Copilot CLI 기능이 포함되어 있으므로 모든 실습 과정을 완료할 수 있습니다.
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot app은 codespace가 아니라 사용자의 컴퓨터에서 실행되므로, [레슨 0][ex0]에서는 앱을 설치하기 전에 Node.js를 설치하고 프로젝트 복사본을 만드는 방법을 안내합니다.
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot Business 또는 Copilot Enterprise를 사용하는 경우 앱을 사용하려면 관리자가 **Copilot CLI** 정책을 활성화해야 합니다.
|
||||
|
||||
## 시작하기
|
||||
|
||||
[**레슨 0: 필수 조건부터 시작 →**][ex0]
|
||||
|
||||
[ex0]: /ko-kr/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex1]: /ko-kr/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[ex2]: /ko-kr/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /ko-kr/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[ex4]: /ko-kr/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[ex5]: /ko-kr/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[ex6]: /ko-kr/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[ex7]: /ko-kr/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[ex8]: /ko-kr/learning-hub/copilot-workshops/app/8-review/
|
||||
[install-git]: https://github.com/git-guides/install-git
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
@@ -0,0 +1,41 @@
|
||||
---
|
||||
title: "GitHub Copilot 에이전트 실습"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
최근 GitHub Copilot에 추가된 기능은 소프트웨어 개발 수명 주기(SDLC) 전반에서 개발자에게 강력한 도구를 제공합니다. 여기에는 GitHub의 이슈 및 끌어오기 요청 작업, 외부 서비스와의 상호 작용, 그리고 코드 작성이 포함됩니다. 이 랩에서는 이러한 기능을 살펴보고, 실제 사용 사례와 도구를 최대한 활용하는 방법을 소개합니다.
|
||||
|
||||
> [!CAUTION]
|
||||
> GitHub Copilot은 결정론적이 아니라 확률론적으로 작동하므로 정확한 코드와 변경되는 파일 등이 달라질 수 있습니다. 따라서 랩의 스크린샷 및 코드 조각과 실제 환경에서 약간의 차이가 나타날 수 있습니다. 이는 예상된 결과이며, 이러한 유형의 도구가 작동하는 방식에서 비롯됩니다.
|
||||
>
|
||||
> 무언가 제대로 작동하지 않거나 올바르게 실행되지 않는다면 멘토에게 문의하십시오!
|
||||
|
||||
## 하네스(Harness) 선택
|
||||
|
||||
GitHub Copilot은 어떤 작업 환경에서든 함께할 수 있습니다. 원하는 개발 방식에 맞는 하네스를 선택하고, Tailspin Toys의 공통 백로그를 바탕으로 연습을 진행합니다. 각 하네스는 자체 설정 과정으로 시작하므로 원하는 하네스를 선택해 바로 시작할 수 있습니다.
|
||||
|
||||
### 🖥️ [VS Code](/ko-kr/learning-hub/copilot-workshops/vscode/)
|
||||
|
||||
**Visual Studio Code**와 GitHub Codespaces에서 GitHub Copilot을 사용합니다. 익숙한 편집기를 벗어나지 않고 Copilot Chat 에이전트 모드, MCP 서버, 사용자 지정 에이전트를 활용합니다. AI 지원을 IDE에 직접 통합하고 싶을 때 적합합니다.
|
||||
|
||||
### 💻 [Copilot CLI](/ko-kr/learning-hub/copilot-workshops/cli/)
|
||||
|
||||
**GitHub Copilot CLI**는 터미널에서 실행되는 에이전트형 도우미입니다. 이를 설치하고, MCP 서버를 연결하고, 계획 모드로 코드를 생성하고, 명령줄에서 직접 스킬, 사용자 지정 에이전트, 슬래시 명령을 만듭니다.
|
||||
|
||||
### 🤖 [Copilot 앱](/ko-kr/learning-hub/copilot-workshops/app/)
|
||||
|
||||
**GitHub Copilot 앱**은 Copilot CLI를 기반으로 구축된 데스크톱 애플리케이션입니다. 여러 에이전트 세션을 병렬로 실행하고, 세션 모드를 전환하고, 캔버스에서 협업하고, GitHub 이슈와 끌어오기 요청을 기본 기능으로 관리합니다. 여기에는 끌어오기 요청의 리베이스, 검토 피드백, CI 수정, 병합 과정을 관리하는 **Agent Merge**도 포함됩니다.
|
||||
|
||||
### ☁️ [Copilot 클라우드 에이전트](/ko-kr/learning-hub/copilot-workshops/cloud/)
|
||||
|
||||
**Copilot 클라우드 에이전트**는 백그라운드에서 GitHub 이슈를 처리하는 비동기 동료 프로그래머입니다. 작업을 할당하고, 사용자 지정 에이전트로 작업 방향을 안내하고, 에이전트 대시보드에서 진행 상황을 모니터링하고, 에이전트가 생성한 끌어오기 요청을 검토합니다.
|
||||
|
||||
## 시나리오
|
||||
|
||||
여러분은 개발자 테마의 보드게임 크라우드펀딩을 제공하는 가상 기업 Tailspin Toys에 새로 합류한 개발자입니다. 아주 큰 시장입니다! 팀의 백로그는 이미 GitHub 이슈로 등록되어 있어 바로 작업을 시작할 수 있습니다. 필터링 및 페이지 매김과 같은 기능 작업과 접근성 및 코딩 표준과 같은 품질 개선 작업이 함께 준비되어 있습니다. 사이트와 Copilot의 기능을 모두 살펴보면서 반복적으로 작업을 진행해 과제를 완료합니다.
|
||||
|
||||
## 시작하기
|
||||
|
||||
위에서 하네스를 선택해 시작합니다. 각 하네스는 개발을 시작하는 데 필요한 설정 과정으로 시작합니다.
|
||||
@@ -0,0 +1,85 @@
|
||||
---
|
||||
title: "Lesson 0 - Prerequisites"
|
||||
description: "Set up for the GitHub Copilot app lessons: install Node.js for the Tailspin Toys project and create your own copy of the repository from the template."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
The GitHub Copilot app is a desktop app, serving as your central hub for both Copilot and GitHub. It provides quick access to issues and pull requests, and of course allows you to build using GitHub Copilot. During this workshop you'll be working locally, using both the Tailspin Toys app, built on Astro, and of course the GitHub Copilot app. Before you get started, let's ensure Node.js is installed locally, then install the Copilot app.
|
||||
|
||||
In this lesson, you will:
|
||||
|
||||
- install Node.js so the project's tests can run on your machine.
|
||||
- create your own copy of the Tailspin Toys project from the template.
|
||||
|
||||
## Install Node.js
|
||||
|
||||
Several lessons ask an agent to build features and run the Tailspin Toys test suite locally, which needs **[Node.js][nodejs]** — the only runtime the project requires. Install version **22 or newer**; the current **LTS** release is a safe choice.
|
||||
|
||||
The simplest option on every platform is the official installer:
|
||||
|
||||
1. In your operating system, open a terminal window using Windows Terminal, macOS terminal, or whatever you typically use.
|
||||
2. Run the following command to confirm you have at least Node.js 22 or higher installed:
|
||||
|
||||
```shell
|
||||
node --version
|
||||
```
|
||||
|
||||
3. If you see `v22` or a higher number, you can skip to the next section!
|
||||
|
||||
> [!TIP]
|
||||
> You only need to complete these steps if you don't have Node installed, or you need to update.
|
||||
|
||||
4. Open the [Node.js download page][node-download].
|
||||
5. Download the **LTS** build for your operating system.
|
||||
6. Run the installer and accept the defaults. On Windows, keep the **Add to PATH** option selected.
|
||||
7. Once installed, open a new terminal window.
|
||||
8. Confirm the install in the new terminal window by running the following:
|
||||
|
||||
```bash
|
||||
node --version
|
||||
```
|
||||
|
||||
9. You should see `v22.x.x` or higher.
|
||||
|
||||
> [!TIP]
|
||||
> Prefer containers? If you have **[Docker][docker]**, you can use the repository's [dev container][dev-containers] instead of installing Node.js locally — it bundles Node for you. You don't need both.
|
||||
|
||||
## Set up the lab repository
|
||||
|
||||
You'll work against your own copy of the Tailspin Toys project. Create it now from the [template repository][template-repository]. The new repository contains every file the lab needs, and you'll connect it to the app in the next lesson.
|
||||
|
||||
1. In a new browser window, navigate to the GitHub repository for this lab: `https://github.com/github-samples/tailspin-toys`.
|
||||
2. Create your own copy of the repository by selecting the **Use this template** button on the lab repository page. Then select **Create a new repository**.
|
||||
|
||||
|
||||
|
||||
3. If you are completing the workshop as part of an event being led by GitHub or Microsoft, follow the instructions provided by the mentors. Otherwise, you can create the new repository in an organization where you have access to GitHub Copilot.
|
||||
|
||||
|
||||
|
||||
4. Make a note of the repository path you created (**organization-or-user-name/repository-name**), as you will be referring to this later in the lab.
|
||||
|
||||
> [!NOTE]
|
||||
> When you create your repository from the template, a backlog of GitHub issues is created for you automatically. You'll work from these issues throughout the workshop — there's nothing to file yourself.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You're set up! You installed Node.js so the project can build and test on your machine, and you created your own copy of the Tailspin Toys repository from the template.
|
||||
|
||||
Next, you'll install the GitHub Copilot app, connect the repository you just created, and get oriented in the workspace. Continue to [Lesson 1 - Installing the GitHub Copilot app][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Download Node.js][node-download]
|
||||
- [Creating a repository from a template][template-repository]
|
||||
- [About the GitHub Copilot app][about-copilot-app]
|
||||
|
||||
[next-lesson]: /learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[nodejs]: https://nodejs.org/
|
||||
[node-download]: https://nodejs.org/en/download
|
||||
[docker]: https://www.docker.com/products/docker-desktop/
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,100 @@
|
||||
---
|
||||
title: "Lesson 1 - Installing the GitHub Copilot app"
|
||||
description: "Install the GitHub Copilot app, connect the repository you created from the template, get oriented in the workspace, and try a quick chat."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
The **[GitHub Copilot app][about-copilot-app]** is a desktop application for agent-driven development. It is built on GitHub Copilot CLI and integrates natively with GitHub, so your repositories, branches, and CI pipelines work out of the box. It's designed for workflows where you direct several agents in parallel — each in its own isolated workspace — rather than doing all of the work yourself, and automating repetitive tasks. With Node.js installed and your copy of the project ready, the next step is to install the app and connect that repository.
|
||||
|
||||
In this lesson, you will:
|
||||
|
||||
- install the GitHub Copilot app and sign in.
|
||||
- add your project to the app from its GitHub repository.
|
||||
- get oriented in the workspace, including the backlog the template seeded for you.
|
||||
- try a quick chat to learn about the app itself.
|
||||
|
||||
## Scenario
|
||||
|
||||
Your team is adopting AI agents to work through a growing backlog. The Copilot app gives you one place to direct that work — picking up issues, running agents, reviewing changes, and merging pull requests. This lesson gets you installed, connected, and comfortable starting a conversation about your project.
|
||||
|
||||
> [!NOTE]
|
||||
> An eligible Copilot plan is required — Copilot Student or any paid plan (Pro, Pro+, Business, or Enterprise). If you are on Copilot Business or Copilot Enterprise, your administrator must enable the **Copilot CLI** policy before the app will work.
|
||||
|
||||
## Install and configure the GitHub Copilot app
|
||||
|
||||
To use the GitHub Copilot app the first step, as you might imagine, is to install it. Versions are available for Windows, macOS and Linux. Let's install the app, authenticate, and add our Tailspin Toys repo to the app.
|
||||
|
||||
1. In a browser, open the [landing page for the GitHub Copilot app][download-app].
|
||||
2. Download the app for your platform and install it following the instructions provided on the landing page.
|
||||
3. Open the app once it's installed.
|
||||
4. Select **Sign in to GitHub** and follow the prompts to authenticate. If you use GitHub Enterprise Server, choose **Use GitHub Enterprise** and enter your server address when prompted.
|
||||
5. After authenticating, you'll be asked about connecting your repositories. Select the Tailspin Toys repo you just created, which should be named `<YOUR_GITHUB_HANDLE>/tailspin-toys`.
|
||||
6. Select **Continue** to continue the onboarding.
|
||||
7. When prompted for a theme, select the one which brings you the most joy, then select **Finish**.
|
||||
|
||||
> [!NOTE]
|
||||
> If your copy of Tailspin Toys didn't appear in the list automatically, you can add it after completing the onboarding process in the app. When completed, the Copilot app will bring you to the home screen. From there you can select **Choose from GitHub**, and search for your repo by name (\<YOUR_GITHUB_HANDLE\>/tailspin-toys), then select it. Your repo will now be added to the Copilot app!
|
||||
|
||||
## Get oriented in the workspace
|
||||
|
||||
With your project connected, take a moment to learn your way around. The app organizes everything into a few areas in the sidebar:
|
||||
|
||||
- **Sessions** — where agents do their work. Each session runs in its own isolated workspace, so you can run several at once without their changes colliding. You'll start your first session in the next lesson.
|
||||
- **Quick chats** — lightweight conversations for questions and brainstorming that don't need a branch or workspace of their own. You'll try one at the end of this lesson.
|
||||
- **My work** — your issues and pull requests, surfaced through the app's **native GitHub integration**. From here you can browse and filter issues and pull requests, check CI status, start a session from an issue, and review pull requests — all without leaving the app.
|
||||
- **Automations** — saved agent tasks that run on a schedule or on demand. You'll create one near the end of the harness.
|
||||
|
||||
### Find your seeded backlog
|
||||
|
||||
Because the app integrates with GitHub natively, the work waiting in your repository shows up right inside the app. When you created your repository from the template, a backlog of issues was filed for you — let's confirm it's there.
|
||||
|
||||
1. Select **My work** in the sidebar.
|
||||
2. The template seeded eight issues in your backlog. This harness focuses on the following three — confirm you can see them:
|
||||
|
||||
- Allow users to filter games by category and publisher
|
||||
- Update our repository coding standards
|
||||
- Implement pagination on the game list page
|
||||
|
||||
3. Select an issue to read its details. Each issue is also a launch point for an agent session — you'll start work from these issues later in the harness.
|
||||
|
||||
> [!NOTE]
|
||||
> The list of items in My work is automatically filtered to only display items from the repositories you've added to Copilot app. Want to see work items from other repos? Add them to the app!
|
||||
|
||||
## Try a quick chat
|
||||
|
||||
A great way to get comfortable with the app is to use it to learn about the *app itself* — and a **quick chat** is exactly the right tool for that. Quick chats let you ask a question or brainstorm without creating a branch or worktree, so they're perfect for a fast, throwaway question — no session required.
|
||||
|
||||
1. In the sidebar, select **+** next to **Quick chats** to open a new chat.
|
||||
2. Ask the app how its own sessions work:
|
||||
|
||||
```plaintext
|
||||
How does the GitHub Copilot app use worktrees?
|
||||
```
|
||||
|
||||
3. Read the response in the conversation view. You'll see that each session runs in its own isolated git worktree — the detail that lets you run several agents in parallel without their changes colliding. You can continue the conversation or start a new chat at any time.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
Congratulations! You've installed the GitHub Copilot app, connected your project, and explored your workspace. You learned how to:
|
||||
|
||||
- install the app and sign in to GitHub.
|
||||
- add a project from its GitHub repository.
|
||||
- get oriented in the workspace and find your seeded backlog in **My work**.
|
||||
- use a quick chat to ask a fast, throwaway question.
|
||||
|
||||
Next, you'll start your first agent session and make your first change to the project — showing a star rating on the game cards. Continue to [Lesson 2 - Running your first agent session][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [About the GitHub Copilot app][about-copilot-app]
|
||||
- [Getting started with the GitHub Copilot app][getting-started]
|
||||
- [Working with agent sessions in the GitHub Copilot app][agent-sessions]
|
||||
|
||||
[ex0]: /learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[download-app]: https://gh.io/app
|
||||
@@ -0,0 +1,135 @@
|
||||
---
|
||||
title: "Lesson 2 - Running your first agent session"
|
||||
description: "Start your first agent session in the GitHub Copilot app, make a small change to the game cards, and merge it as your first pull request."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
In the previous lesson you toured the workspace and used a quick chat. Now it's time to start an **agent session** and make your first change to the project. You'll keep it small: the games already have a star rating in their data, but the game cards on the home page don't show it yet. You'll ask the agent to surface it, review the change, and merge it as your first pull request.
|
||||
|
||||
In this lesson, you will:
|
||||
|
||||
- start an agent session and learn how a session is structured.
|
||||
- ask the agent to make a small, focused change to the project.
|
||||
- review the change in the workspace diff view.
|
||||
- run the app locally to confirm the change in the browser.
|
||||
- open and merge your first pull request.
|
||||
|
||||
## Scenario
|
||||
|
||||
Each game in Tailspin Toys can have a star rating, and it already appears on the game details page. The game cards on the home page, though, only show the title, category, publisher, and description. As a warm-up, you'll have the agent display the existing rating on each card — a tiny, self-contained change that's perfect for your first session.
|
||||
|
||||
## Anatomy of a session
|
||||
|
||||
A **session** is a conversation with an agent that runs in its own isolated workspace. Every session gets a **dedicated git worktree and branch**, which is what lets you run several sessions at once — one adding a feature, another fixing a bug — without their changes colliding. Your sessions appear in the sidebar grouped by repository; select any one to switch to it.
|
||||
|
||||
Inside a session you'll see three things: the **conversation** with the agent, the agent's **tool activity** as it explores and edits files, and the list of **changed files** with their diffs.
|
||||
|
||||
## Start a session and request our change
|
||||
|
||||
Let's start a new session to begin exploring the project and implementing our feature. In a [prior lesson][prior-lesson] you added your project from its GitHub repository. We'll create a new session for that repository and request our change.
|
||||
|
||||
1. Return to (or open) the GitHub Copilot app.
|
||||
2. Select the **Home screen**.
|
||||
3. Ensure `tailspin-toys` is selected for the repo.
|
||||
|
||||
|
||||
|
||||
4. Use the following prompt to request the change:
|
||||
|
||||
```plaintext
|
||||
On the game cards, show each game's star rating. The Game type already includes a starRating field — it's a number out of 5, or null when a game hasn't been rated yet. Display it on each card in src/components/GameCard.astro, and when starRating is null show "No rating yet" instead. Keep the change small and don't restructure the card layout.
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> Notice how the prompt contained the name of the file for Copilot to update. While it's not required at all to specify which files Copilot should include in its work, pointing it in the right direction both helps Copilot quickly generate code and reduce token usage.
|
||||
|
||||
5. Select <kbd>Enter</kbd> to send the prompt to Copilot.
|
||||
|
||||
Copilot app begins work by first creating a new worktree, an isolated copy of the project. It then explores the project, locating the necessary files to update to add the new feature. It will then create the necessary code. You've now added a new feature with Copilot app!
|
||||
|
||||
## Review the diff
|
||||
|
||||
All AI-generated changes deserve a review before they're merged, even small ones. Let's explore the changes, right here in Copilot app.
|
||||
|
||||
1. In the upper right-hand corner of the app, select **Toggle review panel**. This will open the diff screen with all the outstanding changes made by Copilot.
|
||||
|
||||
|
||||
|
||||
2. You should notice code added to `GameCard.astro`, the core file used to display game details. It should be similar to the following — a small block that renders the rating when present and falls back to "No rating yet" when `starRating` is `null`:
|
||||
|
||||
```astro
|
||||
{game.starRating !== null ? (
|
||||
<span class="text-xs font-medium px-2.5 py-0.5 rounded bg-amber-900/60 text-amber-300" data-testid="game-rating">
|
||||
★ {game.starRating} / 5
|
||||
</span>
|
||||
) : (
|
||||
<span class="text-xs font-medium text-slate-500" data-testid="game-rating-empty">
|
||||
No rating yet
|
||||
</span>
|
||||
)}
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> Because Copilot, like all generative AI tools, is probabilistic rather than deterministic, the exact code may vary from the above. But it should be relatively similar.
|
||||
|
||||
## Check the changes
|
||||
|
||||
Of course we shouldn't just read the code and assume it works. We should visually test everything as well! To do so we'll need to start the app from the terminal, then confirm everything works. Fortunately there's a terminal built into Copilot app!
|
||||
|
||||
1. In the review panel on the right side of Copilot app, select **Terminal**. If there is no **Terminal** button, select the **+** (labeled as **Open in panel**), then select **Terminal**.
|
||||
|
||||
|
||||
|
||||
2. Enter the following command in the terminal window to start the web app's dev server:
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
3. Once the server starts (this will just take a moment), open a browser window.
|
||||
4. Navigate to http://localhost:4321.
|
||||
5. You should now see star ratings on all the games on the landing page!
|
||||
6. Return to the terminal window.
|
||||
7. Select <kbd>Ctrl</kbd>+<kbd>C</kbd> to stop the dev server.
|
||||
|
||||
## Open and merge your first pull request
|
||||
|
||||
Your change looks good — now it's time to ship it! You'll ask the agent to open a pull request, then review and merge it yourself on github.com. For now we'll manage this manually. In an upcoming lesson we'll explore how Copilot can handle some of the work for you automatically.
|
||||
|
||||
1. In the upper right hand corner, select **Create PR**.
|
||||
2. If prompted, select **Sign in with your browser** and follow the prompts to authenticate.
|
||||
3. Copilot gets to work on creating the PR.
|
||||
|
||||
Once the PR is created, Copilot will monitor any workflows on the repository that need to run. After a few moments, the button in the upper right will change to **Ready to merge**. This will be your indication your PR is ready to merge!
|
||||
|
||||
4. Select the **PR** bubble just above chat to open your PR in the review pane to see your pull request. You can review the PR as needed here.
|
||||
5. Once ready, select **Ready to merge**.
|
||||
6. Select **Merge pull request** on the new dialog window to merge your pull request!
|
||||
|
||||
You've now pushed a new feature to the website!
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You've started your first agent session and shipped your first change! Specifically, you:
|
||||
|
||||
- started an agent session and learned how sessions are structured.
|
||||
- directed the agent to make a small, focused change to the game cards.
|
||||
- reviewed the change in the workspace diff view.
|
||||
- ran the app locally to confirm the star rating in the browser.
|
||||
- opened a pull request and merged it yourself on github.com.
|
||||
|
||||
Next, you'll use the app to add a custom instructions standard to the repository — starting from one of the issues in your backlog. Continue to [Lesson 3 - Guiding Copilot with custom instructions][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Working with agent sessions in the GitHub Copilot app][agent-sessions]
|
||||
- [About the GitHub Copilot app][about-copilot-app]
|
||||
- [Managing issues and pull requests with the GitHub Copilot app][managing-issues-prs]
|
||||
|
||||
[prior-lesson]: /learning-hub/copilot-workshops/app/1-install-copilot-app/#install-and-configure-the-github-copilot-app
|
||||
[next-lesson]: /learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
@@ -0,0 +1,165 @@
|
||||
---
|
||||
title: "Lesson 3 - Guiding Copilot with custom instructions"
|
||||
description: "Use the GitHub Copilot app to add a custom instructions standard to your repository, starting from an issue in your backlog and merging the change as a pull request."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Context is key when working with generative AI. If a task needs to be done a particular way — or there's background information Copilot should know — you want that context available. One of the most powerful tools for this is [instruction files][instruction-files], which describe not just *what* code you want but *how* it should be structured. In this lesson you'll add a documentation standard to your repository, and you'll do it the way you'll do most work from here on: starting from an issue in your backlog and letting the agent make the change.
|
||||
|
||||
In this lesson, you will:
|
||||
|
||||
- explore how repository instructions and path-scoped instruction files reach the agent.
|
||||
- start a session from the instructions issue in your backlog.
|
||||
- ask the agent to add a documentation standard to `.github/copilot-instructions.md`.
|
||||
- review the change and merge it as a pull request.
|
||||
|
||||
## Scenario
|
||||
|
||||
As any good dev shop, Tailspin Toys has a set of guidelines and requirements for development practices. These include:
|
||||
|
||||
- Documentation should be added to code in the form of TSDoc doc comments.
|
||||
- Formatting should be documented and enforced through linting.
|
||||
|
||||
Through the use of instruction files you'll ensure Copilot has the right information to perform the tasks in alignment with the practices highlighted.
|
||||
|
||||
## Instruction files
|
||||
|
||||
Custom instructions allow you to provide context and preferences to Copilot, so that it can better understand your coding style and requirements. This is a powerful feature that can help you steer Copilot to get more relevant suggestions and code snippets. You can specify your preferred coding conventions, libraries, and even the types of comments you like to include in your code. You can create instructions for your entire repository, or for specific types of files for task-level context.
|
||||
|
||||
There are two types of instructions files:
|
||||
|
||||
- `.github/copilot-instructions.md`, a single instruction file sent to Copilot for **every** request for the repository. This file should contain project-level information — context relevant for most chat or CLI requests sent to Copilot. This could include the tech stack being used, an overview of what's being built, best practices, and other global guidance.
|
||||
- `.github/instructions/*.instructions.md` files can be created for specific tasks or file types. You can use them to provide guidelines for particular languages (like TypeScript or Astro), or for tasks like creating a UI component or a new set of unit tests.
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot supports other standards to bring in instructions guidance through AGENTS.md, CLAUDE.md and GEMINI.md, allowing you to ensure Copilot always has the right context.
|
||||
|
||||
### Best practices for managing instructions files
|
||||
|
||||
A full conversation about creating instructions files is beyond the scope of the workshop. However, the examples provided in the sample project show a representative approach. At a high level:
|
||||
|
||||
- Keep instructions in `copilot-instructions.md` focused on project-level guidance, such as a description of what's being built, the structure of the project, and global coding standards.
|
||||
- Use `*.instructions.md` files to provide specific instructions for file types (unit tests, Astro components, the data layer), or for specific tasks.
|
||||
- Use natural language. Keep guidance clear. Provide examples of how code should (and shouldn't) look.
|
||||
|
||||
There isn't one specific way to create instructions files, just as there isn't one specific way to use AI. You will find through experimentation what works best for your project.
|
||||
|
||||
> [!TIP]
|
||||
> Every project using GitHub Copilot should have a robust collection of instruction files. As you explore the ones in this project, you may notice there are instructions files for numerous types of code files.
|
||||
>
|
||||
> Looking for templates or a starting point? Explore [awesome-copilot][awesome-copilot], a repository full of instruction files, custom agents, and other resources.
|
||||
|
||||
## Explore the custom instructions files in this project
|
||||
|
||||
Take a moment to read the instruction files this repository ships with — there's one core `copilot-instructions.md` and a collection of `*.instructions.md` files for various tasks. Open these in your editor or the GitHub web UI.
|
||||
|
||||
1. If the review panel is not already visible, open it by selecting **Toggle review panel** in the upper right.
|
||||
|
||||
|
||||
|
||||
2. Select the **+** to add a new item to the review panel.
|
||||
3. Select **File**.
|
||||
4. Search for `copilot-instructions.md`.
|
||||
5. Select `copilot-instructions.md` from the list of files to open it.
|
||||
6. Explore the file, noting the brief description of the project plus sections such as **Agent notes**, **Code standards**, **Scripts**, and **Repository Structure**. Under **Code standards**, note the nested **GitHub Actions Workflows** guidance. These are applicable to any interactions you'd have with Copilot.
|
||||
7. Select **Show folder view** to open the folder navigator.
|
||||
|
||||
|
||||
|
||||
8. Navigate to the `.github/instructions` folder and explore the files. Note there are instructions for Astro files, the Drizzle data layer, tests, and more.
|
||||
9. Open `.github/instructions/unit-tests.instructions.md`. Note the `applyTo` field at the top — this sets a glob (relative to the repo root) that determines which files the instructions apply to. Here, any TypeScript test file (for example, one matching `**/*.test.ts`) will match.
|
||||
10. Note the instructions specific to creating unit tests for this project.
|
||||
11. Finally, open `.github/instructions/drizzle.instructions.md` and scroll to the bottom. Note the links to other instruction files (like `unit-tests.instructions.md`) and existing files in the project. This lets you break larger instruction sets into smaller, reusable files, and point Copilot at examples to follow when generating code. (Paths there are relative to the instruction file rather than the repo root.)
|
||||
|
||||
> [!NOTE]
|
||||
> The **Code formatting requirements** section in `copilot-instructions.md` documents the project's coding standards, but it doesn't yet require in-code documentation. In the next steps, you'll add rules for TSDoc doc comments and file comment headers.
|
||||
|
||||
## Start from the instructions issue
|
||||
|
||||
In the previous lesson you started a session from a direct prompt. Most work, however, starts with an issue. Let's create a new session based off an issue filed to update the instructions files, then make the request for the update.
|
||||
|
||||
> [!NOTE]
|
||||
> Because instructions files have a large impact on the code generated by Copilot, care should be taken in ensuring they clearly guide Copilot. Having Copilot create a first version, like you'll do in this lesson is a great approach, followed by a review by you to ensure the updates meet your requirements.
|
||||
|
||||
1. Select **My work** in the sidebar
|
||||
2. Select the issue titled **Update our repository coding standards** to open the issue.
|
||||
3. Select **New session** in the upper right to start a new session based on the issue.
|
||||
|
||||
|
||||
|
||||
4. Use the following prompt to request Copilot update the instructions files to meet the requirements documented in the issue:
|
||||
|
||||
```plaintext
|
||||
Following this issue, make the updates to the instructions files in this project to meet the requirements documented. Don't create the PR quite yet!
|
||||
```
|
||||
|
||||
Copilot will make the updates!
|
||||
|
||||
## Review the change
|
||||
|
||||
Let's both read through the updates Copilot made, but also ask it to provide an example of the code it will now generate based on the updated instructions.
|
||||
|
||||
1. Select **Changes** in the upper right to open the code changes.
|
||||
|
||||
|
||||
|
||||
2. Review the updated instructions file. Confirm it has the guidelines about adding documentation and comments to the code.
|
||||
|
||||
> [!NOTE]
|
||||
> Because AI is probabilistic rather than deterministic, the exact text will vary.
|
||||
|
||||
3. Use the following prompt to ask Copilot to create an example of the code it will now generate:
|
||||
|
||||
```plaintext
|
||||
Do not make any updates, but show me what the code would look like. Based on the new instructions, if I asked Copilot to create a new library component to return all Publishers what would that code look like?
|
||||
```
|
||||
|
||||
4. Review the code Copilot proposes. Note the TSDoc doc comments and the file header comment it includes — exactly what the updated instructions ask for.
|
||||
|
||||
You've now updated the instructions files in the project and seen the impact it will have!
|
||||
|
||||
## Open and merge the pull request
|
||||
|
||||
Instructions files become assets in the repository, meaning they're shared with the rest of the team. Let's create a PR with our work, just like we would any other asset!
|
||||
|
||||
1. In the upper right hand corner, select **Create PR**.
|
||||
2. If prompted, select **Sign in with your browser** and follow the prompts to authenticate.
|
||||
3. Copilot gets to work on creating the PR.
|
||||
|
||||
Once the PR is created, Copilot will monitor any workflows on the repository that need to run. After a few moments, the button in the upper right will change to **Ready to merge**. This will be your indication your PR is ready to merge!
|
||||
|
||||
4. Select **Ready to merge**.
|
||||
5. Select **Merge pull request** on the new dialog window to merge your pull request!
|
||||
|
||||
> [!NOTE]
|
||||
> With the standard merged into your default branch, it becomes part of the project for everyone — and for every new session. When you start the filtering session in the next lesson from an up-to-date default branch, the agent will follow this standard automatically. You'll see the TypeScript it generates include TSDoc doc comments without being asked — a small but real demonstration of instructions shaping generated code.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You explored how the app picks up context from instruction files, then used a session to add and merge a repository-wide standard. Specifically, you:
|
||||
|
||||
- explored the repository's `copilot-instructions.md` and path-scoped `*.instructions.md` files.
|
||||
- started a session from the instructions issue in your backlog.
|
||||
- asked the agent to add a documentation standard to `.github/copilot-instructions.md`.
|
||||
- reviewed the change and merged it as a pull request.
|
||||
|
||||
Next, you'll build the filtering feature in a fresh session — and watch it pick up the standard you just merged. Continue to [Lesson 4 - Building a feature with Autopilot][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Instruction files for GitHub Copilot customization][instruction-files]
|
||||
- [Customizing the GitHub Copilot app][customize-app]
|
||||
- [Best practices for creating custom instructions][instructions-best-practices]
|
||||
- [Awesome Copilot — a collection of instruction files and other resources][awesome-copilot]
|
||||
|
||||
[next-lesson]: /learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[instruction-files]: https://docs.github.com/copilot/customizing-copilot/about-customizing-github-copilot-chat-responses
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[awesome-copilot]: https://awesome-copilot.github.com/
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
@@ -0,0 +1,186 @@
|
||||
---
|
||||
title: "Lesson 4 - Building a feature with Autopilot"
|
||||
description: "Use Plan and Autopilot modes in the GitHub Copilot app to build a static, client-side filtering feature, watch it inherit your documentation standard, and verify it with an agent skill."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
We've made a couple of small updates to our project thus far. But more robust changes require a more robust process. Fortunately, the GitHub Copilot app is built to work with our existing flow, ensuring we build the right things the right way. This is the first of three lessons where you will follow a typical development process, starting by using an issue to generate a new feature and an agent skill to run the validation tests and linters.
|
||||
|
||||
In this lesson, you will:
|
||||
|
||||
- start a fresh session from the filtering issue.
|
||||
- use **Plan** mode to plan the feature, then **Autopilot** to build it.
|
||||
- confirm the generated code follows the documentation standard you merged earlier.
|
||||
- verify your work with the project's `quality-checks` skill.
|
||||
|
||||
## Scenario
|
||||
|
||||
The home page lists every game, but visitors can't narrow the list down. The filtering issue asks you to let them filter games by **category** and **publisher**. Let's use Copilot to implement that functionality.
|
||||
|
||||
## Background
|
||||
|
||||
Introducing AI coding agents to your development flow doesn't change the fundamentals. If anything, they become even more important! Most developers follow a flow that resembles:
|
||||
|
||||
1. Open a filed issue with details of what needs to be done.
|
||||
2. Create a plan of what needs to be built.
|
||||
3. Build and review the code.
|
||||
4. Run the tests to validate the code.
|
||||
5. Manually validate the new functionality.
|
||||
6. Create a pull request (PR).
|
||||
7. Once the code has been reviewed and the continuous integration process succeeds, merge the code.
|
||||
|
||||
> [!NOTE]
|
||||
> Depending on your team and organization, the exact specifics will vary. But most will be a variation on the theme listed above.
|
||||
|
||||
By sticking to this standard approach you ensure the code generated by AI meets the requirements set forth, and goes through the same vetting process as code written by hand.
|
||||
|
||||
## Session modes
|
||||
|
||||
The **session mode** controls how much autonomy the agent has. You can set it from the dropdown below the prompt field and change it at any time:
|
||||
|
||||
- **Interactive**: You and the agent work together. The agent suggests changes and waits for your input before proceeding.
|
||||
- **Plan**: The agent creates a plan first. You review and approve the plan before the agent executes it.
|
||||
- **Autopilot**: The agent works fully autonomously—writing code, running tests, and iterating without waiting for input.
|
||||
|
||||
## Plan the filtering feature
|
||||
|
||||
The best time to catch a potential issue is before any code is written, and the best way to do that is a bit of planning in advance. By planning with Copilot you'll ask Copilot to generate a set of steps and document the approach it will take. You can then review the plan, make any suggestions you might have to improve it, before letting Copilot generate the code based on the plan.
|
||||
|
||||
Let's open the issue, start a new session, and create a plan by switching into plan mode and making the request.
|
||||
|
||||
1. Select **My work** from the navigation tab.
|
||||
2. Select the issue titled **Allow users to filter games by category and publisher**.
|
||||
3. Select **New session** in the upper right.
|
||||
|
||||
|
||||
|
||||
4. Select <kbd>Shift</kbd>+<kbd>Tab</kbd> until the mode displays **Plan**.
|
||||
|
||||
|
||||
|
||||
5. Send the following prompt. The filtering issue is already in this session's context because you started from it:
|
||||
|
||||
```plaintext
|
||||
Plan the work based on the requirements documented in the issue. Please ask any clarifying questions you might have as you build the plan.
|
||||
```
|
||||
|
||||
6. The agent may ask follow-up questions as it builds the plan. Answer them based on how you'd build the feature.
|
||||
|
||||
> [!NOTE]
|
||||
> Because Copilot is probabilistic, the exact follow-up questions Copilot asks will vary. In fact, it might not ask any questions! This is perfectly normal.
|
||||
|
||||
7. Once completed, Copilot will offer a plan summary. Review the plan. You should see it propose building queries, adding filter controls, and of course tests. Provide feedback to refine it if you'd like — the agent will incorporate your suggestions into a new version.
|
||||
|
||||
## Build it with Autopilot
|
||||
|
||||
With the plan created, let's let Copilot build the implementation!
|
||||
|
||||
1. In the list of options in the **Plan summary** dialog, select the option closest to **Approve and implement with autopilot**.
|
||||
|
||||
Copilot will begin work on the implementation!
|
||||
|
||||
> [!NOTE]
|
||||
> If Copilot doesn't automatically start creating the necessary code, you can prompt it to do so by using a prompt like "Go ahead and start building out the plan!".
|
||||
>
|
||||
> Creating the necessary updates will take several minutes. The agent edits and creates files, writes and runs tests, and iterates. Now's a good time to reflect on what you've explored so far, or to enjoy a beverage.
|
||||
|
||||
## Review the changes
|
||||
|
||||
All AI-generated code needs review before it's merged. Let's both review the code and run the site to ensure everything looks good.
|
||||
|
||||
1. Select **Changes** in the upper right to open the code changes.
|
||||
|
||||
|
||||
|
||||
2. Review the changes. You should see new TypeScript and Astro files, and test files. Notice the new helper functions include TSDoc doc comments and a file header comment — the documentation standard you merged in Lesson 3, applied automatically without being asked.
|
||||
3. In the review panel on the right side of Copilot app, select **Terminal**. If there is no **Terminal** button, select the **+** (labeled as **Open in panel**), then select **Terminal**.
|
||||
|
||||
|
||||
|
||||
4. Enter the following command in the terminal window to start the web app's dev server:
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
5. Once the server starts (this will just take a moment), open a browser window.
|
||||
6. Navigate to http://localhost:4321.
|
||||
7. You should now see filters available on the landing page!
|
||||
8. If anything doesn't look right, you can ask Copilot to make the updates!
|
||||
9. Once satisfied, return to the terminal window.
|
||||
10. Select <kbd>Ctrl</kbd>+<kbd>C</kbd> to stop the dev server.
|
||||
|
||||
## Verify your work with the quality-checks skill
|
||||
|
||||
You could eyeball the diff and call it done, but the team has a defined quality bar — and a repeatable way to check it.
|
||||
|
||||
**Agent skills** let you give Copilot guidance on how to perform repeatable tasks like running tests, generating builds, or creating pull requests. A skill is a folder of instructions, scripts, and resources that the agent can load on demand. [Agent Skills is an open standard][agent-skills-repo] used by a range of agents, so the same skill works across Copilot Chat in agent mode, Copilot cloud agent, Copilot CLI, and the GitHub Copilot app.
|
||||
|
||||
Skills live in the `.github/skills` folder of a project, or globally in `~/.copilot/skills`. Each skill is a folder containing a `SKILL.md` file with YAML frontmatter (a `name` and a `description`) followed by the markdown instructions:
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: quality-checks
|
||||
description: Run the project's test suites and linter to verify code changes are ready to commit, push, or merge.
|
||||
---
|
||||
```
|
||||
|
||||
Skills can also include subfolders with scripts, assets, and reference material. The full structure is covered in the [agent skills specification][agent-skills-spec].
|
||||
|
||||
> [!TIP]
|
||||
> Skills are loaded dynamically. The agent decides which skill applies based on the `description` field — a clear, scenario-specific description is the difference between a skill that gets used and one that gets ignored.
|
||||
|
||||
## Explore the quality-checks skill
|
||||
|
||||
Let's explore the skill to see what it does.
|
||||
|
||||
1. If the review panel is not already visible, open it by selecting **Toggle review panel** in the upper right.
|
||||
|
||||
|
||||
|
||||
2. Select the **+** to add a new item to the review panel.
|
||||
3. Select **File**.
|
||||
4. Search for `SKILL.md`.
|
||||
5. Select `SKILL.md .github/skills/quality-checks` from the list of files to open it.
|
||||
6. Note the `name` and `description`. The description tells the agent *when* to use it — whenever code changes need to be tested, linted, or verified before a commit, push, or merge.
|
||||
7. Read through the skill. Notice it documents which script runs which suite (unit tests, Playwright end-to-end tests, ESLint), in what order, and how to debug common failures — so the agent runs the checks the team's way instead of guessing.
|
||||
|
||||
## Run the checks
|
||||
|
||||
In the same filtering session, ask the agent to verify the work. You won't name the skill — the agent will match it from your request.
|
||||
|
||||
1. Return to Copilot app.
|
||||
2. Directly call the skill by using the slash command `/quality-checks` and select <kbd>Enter</kbd>.
|
||||
3. Following the skill, the agent runs the unit tests, the linter, and the end-to-end tests, and reports the results. If anything fails, ask it to fix the issue and run the checks again until everything is green.
|
||||
4. **Keep this session open.** In the next lesson you'll add the Playwright MCP server and use it to see the filtering feature working in a real browser.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You built a real feature end to end and verified it against the team's bar! Specifically, you:
|
||||
|
||||
- started a fresh session from the filtering issue on an up-to-date project.
|
||||
- used Plan mode to plan the feature and Autopilot to build it.
|
||||
- confirmed the generated helper followed the documentation standard you merged in Lesson 3.
|
||||
- verified your work with the `quality-checks` skill.
|
||||
|
||||
Next, you'll connect the Playwright MCP server and ask the agent to explore your filtering feature in a real browser. Continue to [Lesson 5 - Testing with the Playwright MCP server][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Working with agent sessions in the GitHub Copilot app][agent-sessions]
|
||||
- [About Agent Skills][about-agent-skills]
|
||||
- [Customizing the GitHub Copilot app][customize-app]
|
||||
- [About cloud and local sandboxes for GitHub Copilot][sandboxes]
|
||||
|
||||
[ex0]: /learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex2]: /learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-agent-skills]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[agent-skills-repo]: https://github.com/agentskills/agentskills
|
||||
[agent-skills-spec]: https://agentskills.io/specification
|
||||
@@ -0,0 +1,86 @@
|
||||
---
|
||||
title: "Lesson 5 - Testing with the Playwright MCP server"
|
||||
description: "Add the Playwright MCP server to the GitHub Copilot app and ask the agent to manually test your filtering feature in a real browser."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
In the previous lesson you created and verified the filtering feature with the project's automated test suite. Tests automate validation of code, but allowing the agent to confirm behavior is powerful. It allows an agent to respond to issues it sees in the actual UI it's creating. Let's explore how MCP allows access to external capabilities to AI agents, and add the Playwright MCP server to allow Copilot to interact with the site you're building directly.
|
||||
|
||||
In this lesson, you will:
|
||||
|
||||
- understand what Model Context Protocol (MCP) is and how the GitHub Copilot app uses it.
|
||||
- add the Playwright MCP server from the app settings.
|
||||
- ask the agent to drive a browser and explore your filtering feature.
|
||||
|
||||
## Scenario
|
||||
|
||||
While unit and end-to-end tests are important, validating updates to the UI requires actually interacting with the UI. You want to allow Copilot to use the website you're working on as a user would to further automate how changes are made, providing more confidence the updates perform as expected.
|
||||
|
||||
## What is Model Context Protocol (MCP)?
|
||||
|
||||
[Model Context Protocol (MCP)][mcp-blog-post] provides AI agents with a way to communicate with external tools and services. By using MCP, AI agents can communicate with external tools and services in real-time. This allows them to access up-to-date information (using resources) and perform actions on your behalf (using tools).
|
||||
|
||||
These tools and resources are accessed through an MCP server, which acts as a bridge between the AI agent and the external tools and services. The MCP server is responsible for managing the communication between the AI agent and the external tools (such as existing APIs or local tools like NPM packages). Each MCP server represents a different set of tools and resources that the AI agent can access.
|
||||
|
||||
A couple of popular existing MCP servers are:
|
||||
|
||||
- **[GitHub MCP Server](https://github.com/github/github-mcp-server)**: This server provides access to a set of APIs for managing your GitHub repositories. It allows the AI agent to perform actions such as creating new repositories, updating existing ones, and managing issues and pull requests.
|
||||
- **[Playwright MCP Server][playwright-mcp-server]**: This server provides browser automation capabilities using Playwright. It allows the AI agent to perform actions such as navigating to web pages, filling out forms, and clicking buttons.
|
||||
|
||||
There are many other MCP servers available that provide access to different tools and resources. GitHub hosts an [MCP registry](https://github.com/mcp) to enhance discoverability and contributions to the ecosystem.
|
||||
|
||||
> [!CAUTION]
|
||||
> Treat MCP servers as you would any other dependency in your project. Before using an MCP server, carefully review its source code, verify the publisher, and consider the security implications. Only use MCP servers that you trust and be cautious about granting access to sensitive resources or operations.
|
||||
|
||||
## Add the Playwright MCP server
|
||||
|
||||
You add and manage MCP servers from the app settings. The app includes a catalog of popular servers, so the [Playwright MCP server][playwright-mcp-server] is just a couple of clicks away.
|
||||
|
||||
1. Select <kbd>Ctrl</kbd>+<kbd>,</kbd> to open the Copilot app settings page.
|
||||
2. Select **MCP servers**.
|
||||
3. In the search dialog, type `Playwright`.
|
||||
4. Select **Playwright** from the list of **Popular MCP servers**.
|
||||
5. Select **Add server** to add it to the list of available MCP servers.
|
||||
6. Select <kbd>Esc</kbd> to close the settings dialog.
|
||||
|
||||
You've now added the Playwright MCP server!
|
||||
|
||||
## Ask Copilot to explore the feature via Playwright
|
||||
|
||||
Let's ask Copilot to test the feature manually by using the Playwright MCP server.
|
||||
|
||||
1. Use the following prompt to ask Copilot to validate the new functionality:
|
||||
|
||||
```plaintext
|
||||
Start the dev server then use the Playwright MCP server to validate the functionality you just added exists. Use the details in the issue to ensure the newly added behavior matches the specs.
|
||||
```
|
||||
|
||||
Copilot will launch a browser through the Playwright MCP server, walk through each step, and report back what it found. You'll actually see it open a browser on your system to perform the tasks!
|
||||
|
||||
2. Read its summary against the acceptance criteria in the issue. If something looks off, ask follow-up questions or send it back to fix the code before you open a pull request.
|
||||
3. Leave this session open as we're going to close it out in the next lesson!
|
||||
|
||||
Copilot has now also validated the functionality in the browser by exploring the feature like a user would.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
Congratulations, you used the Playwright MCP server to explore your feature in a real browser from the GitHub Copilot app! To recap, you:
|
||||
|
||||
- learned what Model Context Protocol (MCP) is and how the app makes MCP tools available.
|
||||
- added the Playwright MCP server from the app settings.
|
||||
- asked the agent to drive a browser and explore your filtering feature.
|
||||
|
||||
Your feature is built, verified, and seen working. Now it's time to ship it — using **Agent Merge** to open and merge the pull request for you. Continue to [Lesson 6 - Merging with Agent Merge][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [What the heck is MCP and why is everyone talking about it?][mcp-blog-post]
|
||||
- [Microsoft Playwright MCP Server][playwright-mcp-server]
|
||||
- [Configuring MCP servers in the GitHub Copilot app][customize-app]
|
||||
|
||||
[next-lesson]: /learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[mcp-blog-post]: https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/
|
||||
[playwright-mcp-server]: https://github.com/microsoft/playwright-mcp
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
@@ -0,0 +1,67 @@
|
||||
---
|
||||
title: "Lesson 6 - Merging with Agent Merge"
|
||||
description: "Open the filtering pull request, review it in My work, and let Agent Merge fix what's blocking it and merge it for you — the top rung of the merge-automation ladder."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Your filtering feature is built, verified, and seen working in a browser. The last step is to merge it. You've merged twice already in this harness — both times you opened the pull request and merged it yourself on github.com. This time you'll let the app do the heavy lifting with **Agent Merge**, which shepherds a pull request through its whole lifecycle from inside the app.
|
||||
|
||||
In this lesson, you will:
|
||||
|
||||
- learn what Agent Merge is and how it automates the merge lifecycle.
|
||||
- enable Agent Merge on your filtering session.
|
||||
- watch it create the pull request, run CI, and merge when everything is green.
|
||||
|
||||
## Scenario
|
||||
|
||||
Over the last few modules you've explored various levels of automation, from creating code to allowing Copilot to validate a UI directly. To further speed development, Tailspin Toys would like to see if there's a way pull requests that have been vetted and validated can automatically be merged.
|
||||
|
||||
## Introducing Agent Merge
|
||||
|
||||
**Agent Merge** allows automation of the last mile of landing a pull request via Copilot app. When you enable it, the app's session reads your pull request, addresses what's blocking it — fixing failing CI checks, responding to review comments, rebasing when needed — and merges it as soon as GitHub allows. It runs in the background, survives app restarts, and turns itself off once your pull request is merged.
|
||||
|
||||
Up to this point you've been the one clicking **Merge pull request** on github.com. Agent Merge shifts that responsibility to the agent so you can move on to the next task while it shepherds the PR through to completion. You still review and approve the work — the agent just handles the mechanical finish line.
|
||||
|
||||
## Use Agent Merge to manage the PR
|
||||
|
||||
You've reviewed the code manually, run tests, and even allowed Copilot to validate the UI. Now it's time to merge the new code into the codebase! Let's allow agent merge to shepherd the PR through continuous integration (CI) and to merge.
|
||||
|
||||
1. Return to the session you had open from the previous module where you were adding filtering functionality.
|
||||
2. In the upper right-hand corner, select the dropdown next to **Create PR**.
|
||||
3. Select **Agent merge** to enable agent merge.
|
||||
|
||||
|
||||
|
||||
4. The button text now changes to **Agent merge**.
|
||||
5. Select the **Agent merge** button to start the agent merge process.
|
||||
|
||||
Copilot app then begins the process of creating and managing the PR! It starts by exploring the project to determine how best to create a PR, followed by creating the new PR.
|
||||
|
||||
After a few moments, you'll notice Copilot starts work again, looking at the PR conditions - the CI process of running all the tests on your repository. It will report back status on any reviews left by other team members, any checks that need to run (the CI process), and if the PR is mergeable.
|
||||
|
||||
6. Allow agent merge to merge the pull request by selecting the dropdown next to **Agent merge** then **Merge pull request**.
|
||||
|
||||
|
||||
|
||||
7. Once all CI processes are green (meaning the tests passed), Copilot will merge the pull request!
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You've automated several parts of the development process, including generating code, testing and validating code, and now the pull request process. You:
|
||||
|
||||
- learned what Agent Merge is and how it automates the merge lifecycle.
|
||||
- enabled Agent Merge on your filtering session.
|
||||
- watched it create the pull request, run CI, and merge when everything was green.
|
||||
|
||||
Next, you'll explore **canvases** — a richer way to plan and visualize work with the agent. Continue to [Lesson 7 - Planning with canvases][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Managing issues and pull requests with the GitHub Copilot app][managing-issues-prs]
|
||||
- [About the GitHub Copilot app][about-copilot-app]
|
||||
|
||||
[next-lesson]: /learning-hub/copilot-workshops/app/7-canvases/
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,127 @@
|
||||
---
|
||||
title: "Lesson 7 - Planning with canvases"
|
||||
description: "Create a shared, agent-driven canvas in the GitHub Copilot app to plan and track your work alongside the agent."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
So far you've directed agents through chat. But a lot of work doesn't live in a conversation — it lives on a board, in a document, or on a checklist. **Canvases** give you and the agent a shared surface for exactly that kind of work, right inside the app. In this lesson you'll create a simple canvas to plan and track the backlog you've been working through.
|
||||
|
||||
In this lesson, you will:
|
||||
|
||||
- understand what a canvas is and when to use one.
|
||||
- create a shared Kanban board canvas to triage your backlog.
|
||||
- save the canvas to your repository and merge it for the team.
|
||||
- open the canvas in a new session and start work from it.
|
||||
|
||||
## Scenario
|
||||
|
||||
Looking at a list of issues can be rather daunting, even in the best of times. Tailspin Toys' developers have been looking for a tool that would allow them to quickly triage issues, and begin work on them in Copilot app.
|
||||
|
||||
## What is a canvas?
|
||||
|
||||
A [canvas][canvas-docs] is a shared, interactive surface for a work artifact — a plan, a triage board, a release checklist, a dashboard, or a document. While chat is great for describing intent and reasoning through ambiguity, most work happens on a *surface*. Canvases let you collaborate with the agent directly on that surface.
|
||||
|
||||
Canvases are **bidirectional**: the agent can update the canvas while it works, and you can edit the same surface yourself. When you create a canvas, the agent builds it based on your prompt and workflow, and you can ask it to add, remove, or revise capabilities as you go. Once created, a canvas opens in the app's right side panel.
|
||||
|
||||
Some common examples include:
|
||||
|
||||
- **Markdown canvases** for planning your day and prioritizing issues and pull requests.
|
||||
- **Agentic kanban boards** where people and agents add cards and move work across columns.
|
||||
- **Issue triage boards** that summarize top issues and recurring themes for a repository.
|
||||
|
||||
## Why use a canvas?
|
||||
|
||||
Reach for a canvas when a task needs structure, iteration, and verification, and a chat alone isn't enough. A canvas lets you:
|
||||
|
||||
- ground the agent's work in an actual artifact that fits your workflow.
|
||||
- steer or correct work directly on the shared surface, then let the agent continue from your changes.
|
||||
- inspect progress as visible changes to an artifact, not just chat responses.
|
||||
|
||||
## Create a canvas to track your work
|
||||
|
||||
You've shipped a lot: the star rating, the documentation standard, and the filtering feature are all merged. But there's still items on the backlog. Let's create the canvas to help quickly triage the work.
|
||||
|
||||
1. Return to (or open) the GitHub Copilot app.
|
||||
2. Select the **Home screen**.
|
||||
3. Ensure `tailspin-toys` is selected for the repo.
|
||||
4. In the prompt box, use the following prompt to create our canvas that meets our needs:
|
||||
|
||||
```plaintext
|
||||
Create a basic Kanban board canvas that allows me to quickly triage work. Highlight the three issues which are most likely to need attention right now, with the remainder in a second section down below. The top three cards should include a description of the issue's content and a justification of why they're at the top of the list. Each issue should have a button that allows me to add it to the current context for the current session so I can get to work on it straightaway.
|
||||
```
|
||||
|
||||
Copilot will get to work on creating the canvas!
|
||||
|
||||
> [!NOTE]
|
||||
> This will take a few minutes for it to do so. Because this is a complicated task, you might not be satisfied with the first version. You can continue to prompt to build the tool of your dreams!
|
||||
|
||||
## Save the canvas and merge it to the repository
|
||||
|
||||
Canvases can become assets in the repository, just like instructions files and skills. Let's ask Copilot to add it to our repository and merge it so the whole team can use it.
|
||||
|
||||
1. In the same session, ask Copilot to save the canvas to the repository by using the following prompt:
|
||||
|
||||
```plaintext
|
||||
Let's save this canvas definition to the repository so I can share it with my development team
|
||||
```
|
||||
|
||||
2. Once Copilot has saved the canvas files, select the dropdown next to **Create PR** in the upper right-hand corner.
|
||||
3. Select **Agent merge** to enable agent merge.
|
||||
|
||||
|
||||
|
||||
4. The button text now changes to **Agent merge**.
|
||||
5. Select the **Agent merge** button to start the agent merge process.
|
||||
|
||||
Copilot app begins the process of creating and managing the PR. It starts by exploring the project to determine how best to create a PR, then creates it.
|
||||
|
||||
After a few moments, you'll notice Copilot starts work again, looking at the PR conditions — the CI process of running all the tests on your repository. It will report back status on any reviews left by other team members, any checks that need to run (the CI process), and if the PR is mergeable.
|
||||
|
||||
6. Allow agent merge to merge the pull request by selecting the dropdown next to **Agent merge** then **Merge pull request**.
|
||||
|
||||
|
||||
|
||||
7. Wait for all CI processes to pass (go green). Once they do, Copilot will merge the pull request automatically!
|
||||
|
||||
You've now created a new shared canvas for your team!
|
||||
|
||||
## Work in the canvas
|
||||
|
||||
With the canvas created, let's start a new session and put it to work!
|
||||
|
||||
1. Inside the Copilot app, start a new session by selecting **New session** next to **tailspin-toys**.
|
||||
2. Ask Copilot to open the triage canvas by using the following prompt:
|
||||
|
||||
```plaintext
|
||||
Open the triage issues canvas
|
||||
```
|
||||
|
||||
3. You should notice the canvas you built is now open in this new session!
|
||||
4. Select **Add to current context** on one of the issues that's of most interest to you.
|
||||
5. Copilot gets to work on the issue!
|
||||
|
||||
You've now used a canvas you created to streamline the development process.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You created a shared surface where you and the agent can collaborate! You:
|
||||
|
||||
- learned what canvases are and when to use them.
|
||||
- created a shared Kanban triage board canvas with the agent.
|
||||
- saved and merged the canvas to your repository with Agent Merge.
|
||||
- opened the canvas in a new session and used it to start work.
|
||||
|
||||
With your backlog tracked, take a step back to review everything you've built and where to go next. Continue to [Lesson 8 - Review and next steps][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Working with canvas extensions in the GitHub Copilot app][canvas-docs]
|
||||
- [Canvases on Awesome Copilot][awesome-copilot-canvases]
|
||||
- [About the GitHub Copilot app][about-copilot-app]
|
||||
|
||||
[next-lesson]: /learning-hub/copilot-workshops/app/8-review/
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[awesome-copilot-canvases]: https://awesome-copilot.github.com/extensions/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,83 @@
|
||||
---
|
||||
title: "Lesson 8 - Review and next steps"
|
||||
description: "Recap the GitHub Copilot app harness, automate recurring work, and explore where to go next."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Over the last several lessons, you took a feature from idea to merge with the GitHub Copilot app, including:
|
||||
|
||||
- connecting a repository and orienting to the app's workspace and your seeded backlog.
|
||||
- starting sessions from a direct task and from issues, and using Plan and Autopilot modes to control how the agent works.
|
||||
- guiding the agent with custom instructions and a reusable skill.
|
||||
- testing your work with the Playwright MCP server in a real browser.
|
||||
- collaborating with the agent on a shared canvas.
|
||||
- shipping changes up a ladder of merge automation — from merging on github.com yourself to letting **Agent Merge** land a pull request.
|
||||
|
||||
Let's automate some recurring work, talk through best practices, and look at where to go next.
|
||||
|
||||
## Automate recurring work
|
||||
|
||||
The app can run agents for you on a schedule or on demand through **automations** — great for routine tasks like triaging new issues or recapping recent activity. Let's create a simple, non-destructive one.
|
||||
|
||||
1. Select **Automations** in the sidebar, then select **New automation**.
|
||||
2. Give it a name, such as `Recap my recent work`.
|
||||
3. Choose a trigger. **Manual** lets you run it on demand; **On a schedule** runs it automatically; **When an issue is created** reacts to new issues. Choose **Manual** for this lesson.
|
||||
4. Enter a read-only prompt so the automation can't change anything, for example:
|
||||
|
||||
```plaintext
|
||||
Summarize the pull requests merged in this repository over the last week, and list any issues still open in the backlog.
|
||||
```
|
||||
|
||||
5. Pick the project (your Tailspin Toys repository) and create the automation.
|
||||
6. Run it on demand to see the result.
|
||||
|
||||
> [!TIP]
|
||||
> Automations can run locally or in the cloud. Enable **Run in the cloud** and pick the **Tools** an automation may use when you want it to run unattended on a schedule. Keep scheduled automations scoped and non-destructive until you trust their output.
|
||||
|
||||
## Best practices
|
||||
|
||||
When using any AI tool, the infrastructure around it drives the quality of what you get out. Instructions files, skills, and custom agents all played a part in this workshop — invest in them and reuse them across sessions.
|
||||
|
||||
Match the **mode and model** to the task. Use **Plan** to think through an approach before building, **Interactive** to stay in the loop on focused changes, and **Autopilot** only for well-scoped, isolated tasks. Choose a faster model for routine edits and a more capable model with higher reasoning effort for complex work.
|
||||
|
||||
Context still matters as much as infrastructure. Clearly describing *what* you want built, *why*, and *how* meaningfully changes the output. Quick chats are a great place to scope an idea before you commit it to a full session.
|
||||
|
||||
## More to explore
|
||||
|
||||
You've covered the core workflow. A few more features worth a look:
|
||||
|
||||
- **Quick chats** for fast, throwaway questions that don't need a full session.
|
||||
- **Rubber duck** to talk through a problem and get high-signal feedback before you build.
|
||||
- [**Custom agents**][custom-agents] to package a role, its tools, and its instructions for repeatable, specialized work.
|
||||
- [`/chronicle`][chronicle] to generate a narrative of what happened in a session.
|
||||
- [Bring your own key (BYOK)][byok] to use models from your own provider, including local models via Ollama, Foundry Local, or LM Studio.
|
||||
- [Cloud sandboxes][sandboxes] to run sessions in a GitHub-hosted isolated environment.
|
||||
- [Deep links][deep-links] to open the app straight into a repository, session, or prompt.
|
||||
|
||||
## Next steps
|
||||
|
||||
The best way to improve with any tool is to keep using it! Use it for production code, for hobby code, for the little app you've had in mind for years but never got around to building. Share your learnings with your team, and learn from theirs. And, as always, explore the documentation.
|
||||
|
||||
If you'd like to explore more of the GitHub Copilot ecosystem, check out the [VS Code harness](/learning-hub/copilot-workshops/vscode/), the [Copilot CLI harness](/learning-hub/copilot-workshops/cli/), or the [Cloud agent harness](/learning-hub/copilot-workshops/cloud/).
|
||||
|
||||
## Resources
|
||||
|
||||
- [About the GitHub Copilot app][about-copilot-app]
|
||||
- [Getting started with the GitHub Copilot app][getting-started]
|
||||
- [Customize the GitHub Copilot app][customize]
|
||||
- [Using automations][using-automations]
|
||||
- [Working with canvas extensions][canvas-docs]
|
||||
- [About cloud and local sandboxes][sandboxes]
|
||||
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[customize]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[using-automations]: https://docs.github.com/copilot/how-tos/github-copilot-app/using-automations
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[chronicle]: https://docs.github.com/copilot/how-tos/copilot-cli/use-copilot-cli/chronicle
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[byok]: https://docs.github.com/copilot/how-tos/github-copilot-app/use-byok-models
|
||||
[deep-links]: https://docs.github.com/copilot/how-tos/github-copilot-app/open-with-deep-links
|
||||
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: "GitHub Copilot app"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
The **[GitHub Copilot app](https://docs.github.com/copilot/concepts/agents/github-copilot-app)** is a desktop application built on Copilot CLI that brings agent-driven development into a single, focused workspace. It adds parallel agent sessions, switchable session modes, shared canvases, and native GitHub issue and pull request management — including **Agent Merge**, which shepherds a pull request through rebases, review feedback, CI fixes, and merge.
|
||||
|
||||
Across these lessons you'll install the app and set up your project, then get oriented in the app's workspace and the backlog the template seeded for you. You'll start with a small change — adding a star rating — then add a custom instructions standard from an issue, build a filtering feature in an isolated agent session, and verify it with a reusable skill. You'll add the Playwright MCP server to explore the feature in a real browser, then climb a ladder of merge automation that ends with **Agent Merge** landing your pull request. Finally you'll collaborate on a shared canvas and automate recurring work — a complete loop from idea to merged feature.
|
||||
|
||||
## Lessons
|
||||
|
||||
| Lesson | Topic | Description |
|
||||
|--------|-------|-------------|
|
||||
| [0. Prerequisites][ex0] | Setup | Install Node.js and create your copy of the Tailspin Toys project |
|
||||
| [1. Install the Copilot app][ex1] | Setup | Install the app, connect your project, and get oriented in the workspace |
|
||||
| [2. Running your first agent session][ex2] | First change | Start a session and ship a small change as your first pull request |
|
||||
| [3. Guiding Copilot with custom instructions][ex3] | Context | Add a documentation standard from an issue and merge it |
|
||||
| [4. Building a feature with Autopilot][ex4] | Core Feature | Use Plan and Autopilot to build filtering, then verify it with a skill |
|
||||
| [5. Testing with Playwright MCP][ex5] | External Tools | Add the Playwright MCP server and explore your feature in a browser |
|
||||
| [6. Merging with Agent Merge][ex6] | Merge | Let Agent Merge fix and land your filtering pull request |
|
||||
| [7. Planning with canvases][ex7] | Collaboration | Create a shared canvas to plan and track your work |
|
||||
| [8. Review and next steps][ex8] | Summary | Automate recurring tasks and explore what's next |
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before attending this workshop, please ensure you have:
|
||||
|
||||
- [ ] A GitHub account with an active **Copilot Student, Pro, Pro+, Business, or Enterprise** plan
|
||||
- [ ] A computer running **macOS, Linux, or Windows**
|
||||
- [ ] [Git installed][install-git] on your computer
|
||||
|
||||
> [!TIP]
|
||||
> No paid plan? Verified students can get GitHub Copilot for free through [GitHub Education][callout-student-plan-education]. The **Copilot Student** plan includes the agent, MCP, code review, and Copilot CLI features this workshop uses — so you can complete every harness with it.
|
||||
|
||||
> [!NOTE]
|
||||
> Because the Copilot app runs on your own machine rather than in a codespace, [Lesson 0][ex0] walks you through installing Node.js and creating your copy of the project before you install the app.
|
||||
|
||||
> [!NOTE]
|
||||
> If you are using Copilot Business or Copilot Enterprise, your administrator must enable the **Copilot CLI** policy before you can use the app.
|
||||
|
||||
## Get Started
|
||||
|
||||
**[Start with Lesson 0: Prerequisites →][ex0]**
|
||||
|
||||
[ex0]: /learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex1]: /learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[ex2]: /learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[ex4]: /learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[ex5]: /learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[ex6]: /learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[ex7]: /learning-hub/copilot-workshops/app/7-canvases/
|
||||
[ex8]: /learning-hub/copilot-workshops/app/8-review/
|
||||
[install-git]: https://github.com/git-guides/install-git
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
@@ -0,0 +1,70 @@
|
||||
---
|
||||
title: "Exercise 0: Prerequisites"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Before you start the Copilot CLI exercises, you need to get everything ready. You'll create your own copy of the Tailspin Toys repository and spin up a [codespace][codespaces], whose integrated terminal you'll use to install and run Copilot CLI in the next exercise.
|
||||
|
||||
## Setting up the lab repository
|
||||
|
||||
To create a copy of the repository for the code you'll create, you'll make an instance from the [template][template-repository]. The new instance will contain all of the necessary files for the lab, and you'll use it as you work through the exercises.
|
||||
|
||||
1. In a new browser window, navigate to the GitHub repository for this lab: `https://github.com/github-samples/tailspin-toys`.
|
||||
2. Create your own copy of the repository by selecting the **Use this template** button on the lab repository page. Then select **Create a new repository**.
|
||||
|
||||
|
||||
|
||||
3. If you are completing the workshop as part of an event being led by GitHub or Microsoft, follow the instructions provided by the mentors. Otherwise, you can create the new repository in an organization where you have access to GitHub Copilot.
|
||||
|
||||
|
||||
|
||||
4. Make a note of the repository path you created (**organization-or-user-name/repository-name**), as you will be referring to this later in the lab.
|
||||
|
||||
> [!NOTE]
|
||||
> **Your backlog is ready**
|
||||
>
|
||||
> When you create your repository from the template, a backlog of GitHub issues is created for you automatically. You'll work from these issues throughout the workshop — there's nothing to file yourself.
|
||||
## Creating a codespace
|
||||
|
||||
Next up, you'll use a codespace to complete the lab exercises.
|
||||
|
||||
[GitHub Codespaces][codespaces] are a cloud-based development environment that allows you to write, run, and debug code directly in your browser. It provides a fully-featured IDE with support for multiple programming languages, extensions, and tools.
|
||||
|
||||
1. Navigate to your newly created repository.
|
||||
2. Select the green **Code** button.
|
||||
|
||||
|
||||
|
||||
3. Select the **Codespaces** tab and select the **+** button to create a new Codespace.
|
||||
|
||||
|
||||
|
||||
The creation of the codespace will take several minutes, although it's still far quicker than having to manually install all the services! That said, you can use this time to explore other features of GitHub Copilot, which we'll turn your attention to next.
|
||||
|
||||
> [!CAUTION]
|
||||
> You'll return to the codespace in a future exercise. For the time being, leave it open in a tab in your browser.
|
||||
|
||||
> [!NOTE]
|
||||
> This workshop is built to run inside a codespace or local [dev container][dev-containers]. Both ensure the environment has all the necessary prerequisites installed for a smooth experience. If you'd prefer to run it locally, open the cloned repository in VS Code and select **Reopen in Container** when prompted — VS Code will build the same dev container the codespace uses.
|
||||
|
||||
## Summary
|
||||
|
||||
Congratulations, you have created a copy of the lab repository! You also began the creation process of your codespace, which you'll use when you begin working with Copilot CLI.
|
||||
|
||||
## Next step
|
||||
|
||||
Let's install Copilot CLI and authenticate it with your GitHub account. Continue to [Exercise 1 - Installing GitHub Copilot CLI][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [GitHub Codespaces overview][codespaces]
|
||||
- [Creating a repository from a template][template-repository]
|
||||
- [Getting started with Codespaces][codespaces-quickstart]
|
||||
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[codespaces-quickstart]: https://docs.github.com/codespaces/getting-started/quickstart
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cli/1-install-copilot-cli/
|
||||
[codespaces]: https://github.com/features/codespaces
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
@@ -0,0 +1,129 @@
|
||||
---
|
||||
title: "Exercise 1 - Installing GitHub Copilot CLI"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[GitHub Copilot CLI][about-copilot-cli] is a powerful agentic coding assistant that runs in your terminal, enabling you to explore codebases, generate code, run commands, and interact with external tools - all from the command line. It allows you to offload tasks, request changes, and stay in the zone. The first step, as you might imagine, is to install the tool! Fortunately this can be done using tools you're already familiar with.
|
||||
|
||||
In this exercise, you will learn how to:
|
||||
|
||||
- install GitHub Copilot CLI using npm.
|
||||
- authenticate with your GitHub account.
|
||||
- verify the installation.
|
||||
|
||||
## Scenario
|
||||
|
||||
Your team is starting to use AI agents to work through a growing backlog. Copilot CLI brings that capability into the terminal, where many developers already live. This exercise gets you installed, authenticated, and ready to use it for the rest of the workshop.
|
||||
|
||||
## Open a terminal in your codespace
|
||||
|
||||
Before installing Copilot CLI, you need to open a terminal window in your codespace.
|
||||
|
||||
1. Return to your codespace if you're not already there.
|
||||
2. Open a terminal window by pressing <kbd>Ctrl</kbd>+<kbd>\`</kbd>.
|
||||
3. You should see a terminal panel appear at the bottom of your VS Code window.
|
||||
|
||||
## Install Copilot CLI
|
||||
|
||||
You can install Copilot CLI through [npm][install-npm], [WinGet][install-winget], and [Homebrew][install-homebrew]. Since GitHub Codespaces come with Node.js pre-installed you'll use npm to install Copilot CLI.
|
||||
|
||||
1. In the terminal, verify Node.js is installed and meets the version requirement:
|
||||
|
||||
```bash
|
||||
node --version
|
||||
```
|
||||
|
||||
You should see version 22 or higher (e.g., `v22.x.x`).
|
||||
|
||||
2. Install Copilot CLI globally in the codespace using npm:
|
||||
|
||||
```bash
|
||||
npm install -g @github/copilot
|
||||
```
|
||||
|
||||
3. Verify the installation by checking the version:
|
||||
|
||||
```bash
|
||||
copilot --version
|
||||
```
|
||||
|
||||
You should see the version number displayed (e.g., `v1.0.XX`).
|
||||
|
||||
> [!TIP]
|
||||
> If you encounter permission errors, you may need to use `sudo npm install -g @github/copilot` on some systems. However, this shouldn't be necessary in GitHub Codespaces.
|
||||
|
||||
## Authenticate with GitHub
|
||||
|
||||
On first launch, Copilot CLI will prompt you to authenticate with your GitHub account.
|
||||
|
||||
1. Start Copilot CLI:
|
||||
|
||||
```bash
|
||||
copilot
|
||||
```
|
||||
|
||||
2. If you're not currently logged in, you'll see a prompt to authenticate. Copilot CLI will display a device code and ask you to visit a URL.
|
||||
3. Follow the on-screen instructions:
|
||||
- Open the provided URL in your browser
|
||||
- Enter the device code when prompted
|
||||
- Authorize Copilot CLI to access your GitHub account
|
||||
4. Once authenticated, you'll see the Copilot CLI prompt, ready to accept your questions and commands.
|
||||
|
||||
> [!NOTE]
|
||||
> In a codespace, you may already be authenticated through your GitHub session. If Copilot CLI starts without prompting for authentication, you're good to go!
|
||||
|
||||
## Trust the directory and verify everything is working
|
||||
|
||||
Now that you're at the Copilot CLI prompt for the first time, let's trust this workshop repository and make sure Copilot CLI is properly installed and connected.
|
||||
|
||||
1. When Copilot CLI asks you to confirm that you trust the files in this folder, you'll see three options:
|
||||
- **Yes, proceed**: Trust for this session only
|
||||
- **Yes, and remember this folder for future sessions**: Trust permanently
|
||||
- **No, exit (Esc)**: Don't allow file access
|
||||
2. For this workshop, select **Yes, and remember this folder for future sessions** since you'll be working in this repository throughout.
|
||||
3. Ask Copilot a simple question to verify it's working:
|
||||
|
||||
```
|
||||
What files are in this project?
|
||||
```
|
||||
|
||||
4. Copilot should explore the repository and provide a summary of the project structure.
|
||||
5. Try the `/help` command to see available slash commands:
|
||||
|
||||
```
|
||||
/help
|
||||
```
|
||||
|
||||
6. Exit Copilot CLI by entering the following command in the terminal. We will return back to Copilot CLI in a future exercise!
|
||||
|
||||
```
|
||||
exit
|
||||
```
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
Congratulations! You've successfully installed and authenticated GitHub Copilot CLI. You learned how to:
|
||||
|
||||
- install Copilot CLI using npm.
|
||||
- authenticate with your GitHub account.
|
||||
- trust a directory for Copilot CLI to work with.
|
||||
- verify the installation is working correctly.
|
||||
|
||||
Now that Copilot CLI is installed, let's give Copilot some project context. Continue to [Exercise 2 - Custom instructions with CLI][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Installing GitHub Copilot CLI][install-copilot-cli]
|
||||
- [About Copilot CLI][about-copilot-cli]
|
||||
- [Using Copilot CLI][using-copilot-cli]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cli/0-prerequisites/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cli/2-custom-instructions/
|
||||
[install-copilot-cli]: https://docs.github.com/copilot/how-tos/set-up/install-copilot-cli
|
||||
[install-npm]: https://docs.github.com/copilot/how-tos/copilot-cli/set-up-copilot-cli/install-copilot-cli#installing-with-npm-all-platforms
|
||||
[install-winget]: https://docs.github.com/copilot/how-tos/copilot-cli/set-up-copilot-cli/install-copilot-cli#installing-with-winget-windows
|
||||
[install-homebrew]: https://docs.github.com/copilot/how-tos/copilot-cli/set-up-copilot-cli/install-copilot-cli#installing-with-homebrew-macos-and-linux
|
||||
[about-copilot-cli]: https://docs.github.com/copilot/concepts/agents/about-copilot-cli
|
||||
[using-copilot-cli]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli
|
||||
@@ -0,0 +1,229 @@
|
||||
---
|
||||
title: "Exercise 2 - Custom instructions (Copilot CLI)"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[← Previous lesson: Installing Copilot CLI][previous-lesson] · [Next lesson: Generating code with CLI →][next-lesson]
|
||||
|
||||
Context is key when working with generative AI. If a task needs to be done a particular way — or there's background information Copilot should know — you want to make sure that context is available. There are several tools available to you to help Copilot, which we'll explore throughout this workshop. We're going to start with [instruction files][instruction-files], which are typically focused on how the code itself should be structured. This helps Copilot understand not just *what* code you want but *how* it should be structured.
|
||||
|
||||
In this exercise, you will:
|
||||
|
||||
- explore how project-specific context, coding guidelines, and documentation standards reach Copilot through repository custom instructions and path-scoped instruction files,
|
||||
- generate the first data slice for filtering (a publishers helper) with the *current* instructions in place,
|
||||
- add a new repository-wide standard to `.github/copilot-instructions.md`,
|
||||
- run a follow-up prompt and watch the regenerated code adopt the new standard,
|
||||
- commit the instruction updates and helper so the next exercise can build on them.
|
||||
|
||||
> [!CAUTION]
|
||||
> Generated code may diverge from some of the standards you set. Copilot is non-deterministic. The goal is to see the *trend* in behavior change after updating the instructions, not to match output character-for-character.
|
||||
|
||||
## Instruction files
|
||||
|
||||
### Scenario
|
||||
|
||||
As any good dev shop, Tailspin Toys has a set of guidelines and requirements for development practices. These include:
|
||||
|
||||
- The data layer always needs unit tests.
|
||||
- UI should be in dark mode and have a modern feel.
|
||||
- Documentation should be added to code in the form of TSDoc doc comments.
|
||||
- A block of comments should be added to the head of each file describing what the file does.
|
||||
|
||||
Through the use of instruction files you'll ensure Copilot has the right information to perform the tasks in alignment with the practices highlighted.
|
||||
|
||||
### Custom instructions
|
||||
|
||||
Custom instructions allow you to provide context and preferences to Copilot, so that it can better understand your coding style and requirements. This is a powerful feature that can help you steer Copilot to get more relevant suggestions and code snippets. You can specify your preferred coding conventions, libraries, and even the types of comments you like to include in your code. You can create instructions for your entire repository, or for specific types of files for task-level context.
|
||||
|
||||
There are two types of instructions files:
|
||||
|
||||
- `.github/copilot-instructions.md`, a single instruction file sent to Copilot for **every** request for the repository. This file should contain project-level information — context relevant for most chat or CLI requests sent to Copilot. This could include the tech stack being used, an overview of what's being built, best practices, and other global guidance.
|
||||
- `.github/instructions/*.instructions.md` files can be created for specific tasks or file types. You can use them to provide guidelines for particular languages (like TypeScript or Astro), or for tasks like creating a UI component or a new set of unit tests.
|
||||
|
||||
> [!NOTE]
|
||||
> When working in your IDE, instructions files are only used for code generation in Copilot Chat — not for code completions or next-edit suggestions.
|
||||
>
|
||||
> Copilot Chat, Copilot CLI and Copilot cloud agent use both repository-level and `*.instructions.md` files (with `applyTo` front matter) when generating code.
|
||||
>
|
||||
> Finally, Copilot [supports instructions files using other standards][custom-instructions-support], including AGENTS.md and CLAUDE.md files.
|
||||
|
||||
### Best practices for managing instructions files
|
||||
|
||||
A full conversation about creating instructions files is beyond the scope of the workshop. However, the examples provided in the sample project show a representative approach. At a high level:
|
||||
|
||||
- Keep instructions in `copilot-instructions.md` focused on project-level guidance, such as a description of what's being built, the structure of the project, and global coding standards.
|
||||
- Use `*.instructions.md` files to provide specific instructions for file types (unit tests, Astro components, the data layer), or for specific tasks.
|
||||
- Use natural language. Keep guidance clear. Provide examples of how code should (and shouldn't) look.
|
||||
|
||||
There isn't one specific way to create instructions files, just as there isn't one specific way to use AI. You will find through experimentation what works best for your project.
|
||||
|
||||
> [!TIP]
|
||||
> Every project using GitHub Copilot should have a robust collection of instruction files. As you explore the ones in this project, you may notice there are files for numerous types of tasks, including [UI updates][ui-instructions] and [Astro][astro-instructions].
|
||||
>
|
||||
> Copilot can also help generate instruction files for you. Each surface exposes this differently (for example, **Configure Chat → Generate Agent Instructions** in VS Code, or `/init` in Copilot CLI) — the lesson for the surface you're on will call it out where it's relevant.
|
||||
>
|
||||
> Looking for templates or a starting point? Explore [awesome-copilot][awesome-copilot], a repository full of instruction files, custom agents, and other resources.
|
||||
|
||||
## Explore the custom instructions files in this project
|
||||
|
||||
Take a moment to read the instruction files this repository ships with — there's one core `copilot-instructions.md` and a collection of `*.instructions.md` files for various tasks. Open these in your editor or the GitHub web UI.
|
||||
|
||||
1. Open `.github/copilot-instructions.md`.
|
||||
2. Explore the file, noting the brief description of the project plus sections such as **Agent notes**, **Code standards**, **Scripts**, and **Repository Structure**. Under **Code standards**, note the nested **GitHub Actions Workflows** guidance. These are applicable to any interactions you'd have with Copilot.
|
||||
3. Open the `.github/instructions` folder and look around. Note there are instructions for Astro files, the Drizzle data layer, tests, and more.
|
||||
4. Open `.github/instructions/unit-tests.instructions.md`. Note the `applyTo` field at the top — this sets a glob (relative to the repo root) that determines which files the instructions apply to. Here, any TypeScript test file (for example, one matching `**/*.test.ts`) will match.
|
||||
5. Note the instructions specific to creating unit tests for this project.
|
||||
6. Finally, open `.github/instructions/drizzle.instructions.md` and scroll to the bottom. Note the links to other instruction files (like `unit-tests.instructions.md`) and existing files in the project. This lets you break larger instruction sets into smaller, reusable files, and point Copilot at examples to follow when generating code. (Paths there are relative to the instruction file rather than the repo root.)
|
||||
|
||||
> [!NOTE]
|
||||
> The **Code formatting requirements** section in `copilot-instructions.md` documents the project's coding standards, but it doesn't yet require in-code documentation. In the next steps, you'll add rules for TSDoc doc comments and file comment headers.
|
||||
## Create a branch
|
||||
|
||||
You'll be making code changes, so create a branch to work in.
|
||||
|
||||
1. From your codespace terminal, create and switch to a new branch:
|
||||
|
||||
```bash
|
||||
git checkout -b update-custom-instructions
|
||||
```
|
||||
|
||||
2. Confirm Copilot CLI is installed and authenticated:
|
||||
|
||||
```bash
|
||||
copilot --version
|
||||
```
|
||||
|
||||
If the command isn't found or you haven't logged in, return to [Exercise 1 - Installing GitHub Copilot CLI](/learning-hub/copilot-workshops/cli/1-install-copilot-cli/).
|
||||
|
||||
## Use Copilot CLI *before* updating the instructions
|
||||
|
||||
To see the impact of custom instructions, start by generating code with the current instructions in place. Later, you'll update the file and run a follow-up prompt.
|
||||
|
||||
> [!CAUTION]
|
||||
> `--yolo` enables full automatic permissions (`--allow-all-tools`, `--allow-all-paths`, and `--allow-all-urls`). Use it only in an isolated environment like a Codespace or VM, and never alias it as your default for day-to-day development. See [Allowing and denying tool use][allow-all-warning] for details.
|
||||
|
||||
Running Copilot CLI from the **repository root** ensures it picks up `.github/copilot-instructions.md` automatically. `--enable-all-github-mcp-tools` turns on the read/write GitHub MCP tools so Copilot can read your backlog and open pull requests later in the workshop.
|
||||
|
||||
1. Return to your codespace. If you closed it, navigate to your repository on GitHub.com, select **Code** > **Codespaces**, then reopen your existing codespace.
|
||||
2. Return to your open Copilot CLI session. If the terminal is closed or you exited Copilot CLI, open a terminal by selecting <kbd>Ctrl</kbd>+<kbd>\`</kbd>, then start it from the repository root by running `copilot --yolo --enable-all-github-mcp-tools`. Trust the project folder if prompted, then run `/models` and select **Auto**.
|
||||
3. At the Copilot CLI prompt, ask it to generate the publishers helper that the filtering UI will use:
|
||||
|
||||
```plaintext
|
||||
Create a new data-access helper at src/lib/publishers.ts to return a list of all publishers. It should return the name and id for all publishers. Do not run the tests yet.
|
||||
```
|
||||
|
||||
4. Copilot CLI will explore the project, propose a plan, and write the file in this `--yolo` session. Monitor the changes in your terminal output, then review in your editor.
|
||||
5. Open the generated `src/lib/publishers.ts` in your editor.
|
||||
6. Notice the helper is a typed function that takes a `db` client as its first argument and returns a typed array of publishers — that's coming from the data-layer conventions in `.github/instructions/drizzle.instructions.md` (which applies to `src/lib/*.ts`).
|
||||
7. Notice the generated code **is missing** TSDoc doc comments and a file-level comment header.
|
||||
|
||||
> [!CAUTION]
|
||||
> Copilot is probabilistic — there's a chance it'll add doc comments even without being told. If that happens, that's fine; the *consistency* improvement after the instruction update is still the takeaway.
|
||||
|
||||
## Add a new repository standard
|
||||
|
||||
As highlighted previously, `.github/copilot-instructions.md` is designed to provide project-level information to Copilot. Let's ensure repository coding standards are documented to improve code suggestions.
|
||||
|
||||
1. Re-open `.github/copilot-instructions.md`.
|
||||
2. Locate the **Code formatting requirements** section, which should be near line 27. Note how it documents the project's coding standards — but it has no rule yet for in-code documentation, which is why the generated helper had no doc comments.
|
||||
3. Add the following lines of markdown right below the existing standards to instruct Copilot to add file comment headers and TSDoc doc comments:
|
||||
|
||||
```markdown
|
||||
- Every exported function should have a TSDoc comment describing its purpose, parameters, and return value.
|
||||
- Before imports or any code, add a comment block to the file that explains its purpose.
|
||||
```
|
||||
|
||||
4. Save `copilot-instructions.md`.
|
||||
|
||||
> [!TIP]
|
||||
> As you saw in the previous lesson, instruction files can be created at the repository level (`.github/copilot-instructions.md`) for global guidance, or as `*.instructions.md` files for specific languages, file types, or tasks. The repository-level file is the right home for project-wide standards like the doc comment rule you just added.
|
||||
## Re-run the prompt and observe the change
|
||||
|
||||
Now that the instructions have a doc comment rule, ask Copilot CLI to update the publishers file you just generated. The same standards directive will steer the rewrite.
|
||||
|
||||
1. Send `/clear` in your Copilot CLI session to start with a clean conversation.
|
||||
2. Send the following prompt:
|
||||
|
||||
```plaintext
|
||||
Update src/lib/publishers.ts to follow the latest documentation conventions in .github/copilot-instructions.md.
|
||||
```
|
||||
|
||||
3. Let the edit complete, then reopen `src/lib/publishers.ts`.
|
||||
4. Notice that the file now opens with a comment block similar to:
|
||||
|
||||
```typescript
|
||||
/**
|
||||
* Publisher data-access helpers for the Tailspin Toys Crowd Funding platform.
|
||||
* Provides functions to retrieve publisher information from the database.
|
||||
*/
|
||||
```
|
||||
|
||||
5. Notice that the generated function now includes a TSDoc comment similar to:
|
||||
|
||||
```typescript
|
||||
/**
|
||||
* Returns a list of all publishers with their id and name.
|
||||
*
|
||||
* @param db - The Drizzle database client.
|
||||
* @returns A promise that resolves to an array of publisher objects.
|
||||
*/
|
||||
```
|
||||
|
||||
6. Keep this updated file in place. It's the first data slice you'll build on in the next exercise.
|
||||
|
||||
## Commit and push this first filtering slice
|
||||
|
||||
1. In your terminal, verify the changed files:
|
||||
|
||||
```bash
|
||||
git status
|
||||
```
|
||||
|
||||
2. Stage the instruction update and the helper:
|
||||
|
||||
```bash
|
||||
git add .github/copilot-instructions.md src/lib/publishers.ts
|
||||
```
|
||||
|
||||
3. Commit the changes:
|
||||
|
||||
```bash
|
||||
git commit -m "Add doc comment standards and publishers helper foundation"
|
||||
```
|
||||
|
||||
4. Push the branch:
|
||||
|
||||
```bash
|
||||
git push -u origin update-custom-instructions
|
||||
```
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You explored how Copilot picks up context from instruction files in this project, then used Copilot CLI to:
|
||||
|
||||
- generate a publishers data-access helper foundation for filtering with the *existing* instructions,
|
||||
- add a new repository-wide standard to `.github/copilot-instructions.md`,
|
||||
- run a follow-up prompt and watch the regenerated code adopt the new standard,
|
||||
- commit and push both the instructions update and the helper foundation.
|
||||
|
||||
Next, you'll apply these instructions while implementing backlog work in [the generating-code exercise][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Instruction files for GitHub Copilot customization][instruction-files]
|
||||
- [Best practices for creating custom instructions][instructions-best-practices]
|
||||
- [5 tips for writing better custom instructions for Copilot][copilot-instructions-five-tips]
|
||||
- [Awesome Copilot — a collection of instruction files and other resources][awesome-copilot]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cli/1-install-copilot-cli/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cli/3-generating-code/
|
||||
[instruction-files]: https://docs.github.com/copilot/customizing-copilot/about-customizing-github-copilot-chat-responses
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[copilot-instructions-five-tips]: https://github.blog/ai-and-ml/github-copilot/5-tips-for-writing-better-custom-instructions-for-copilot/
|
||||
[allow-all-warning]: https://docs.github.com/copilot/how-tos/copilot-cli/use-copilot-cli/allowing-tools
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[awesome-copilot]: https://github.com/github/awesome-copilot
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
@@ -0,0 +1,83 @@
|
||||
---
|
||||
title: "Exercise 3 - Adding project features with GitHub Copilot CLI"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
As you might expect, the core tasks you'll perform with GitHub Copilot CLI is to add features, functionality, and code to a project. Let's take one of the issues from your backlog and ask Copilot to help us implement it.
|
||||
|
||||
## Scenario
|
||||
|
||||
The time has come to complete filtering in the project. You already have the filtering issue in your backlog and a foundation helper from the previous exercise. Let's have Copilot retrieve the issue details, account for existing work, and build the remaining functionality.
|
||||
|
||||
In this exercise, you will:
|
||||
|
||||
- utilize plan mode to generate a plan for implementing the filtering functionality.
|
||||
- generate the code necessary to add filtering to the website with Copilot.
|
||||
|
||||
By the end of this exercise, you will have added new functionality to the project.
|
||||
|
||||
## Utilize plan mode
|
||||
|
||||
One of the best uses of AI is planning. Oftentimes you'll have a good concept of what you want to build, but just need to bounce some ideas off of something. AI tools can help you crystalize your thoughts by asking you follow up questions and working through different pitfalls or missing components. To support this process, Copilot CLI offers a plan mode. Additionally, that time you spend planning will help Copilot generate code that best matches the requirements set forth.
|
||||
|
||||
You'll start the process of creating the new functionality by utilizing plan mode in Copilot CLI.
|
||||
|
||||
1. Return to your codespace. If you closed it, navigate to your repository on GitHub.com, select **Code** > **Codespaces**, then reopen your existing codespace.
|
||||
2. Return to your open Copilot CLI session. If the terminal is closed or you exited Copilot CLI, open a terminal by selecting <kbd>Ctrl</kbd>+<kbd>\`</kbd>, then start it from the repository root by running `copilot --yolo --enable-all-github-mcp-tools`. Trust the project folder if prompted, then run `/models` and select **Auto**.
|
||||
3. Enter the following prompt into Copilot CLI to create a plan based on the filtering issue:
|
||||
|
||||
```
|
||||
/plan Retrieve the issue on the repository related to adding filtering. We already added a publishers helper in src/lib/publishers.ts, so treat that as existing work and plan the remaining updates (games filtering logic, UI, and tests).
|
||||
```
|
||||
|
||||
4. Copilot may ask follow-up questions as it builds out its plan. As those arise, answer them based on how you'd build out the functionality.
|
||||
5. Once the plan is generated, review the blueprint. You should notice it recommends remaining changes across the data layer and UI, as well as generating tests.
|
||||
6. Copilot CLI will offer you the ability to provide additional feedback to the plan. You can cursor down to the indicated section, then type your suggestions. Copilot will incorporate your suggestions into a new version of the plan.
|
||||
7. Once you're satisfied, select the option provided by Copilot to begin work building the new feature!
|
||||
|
||||
> [!NOTE]
|
||||
> Because Copilot is probabilistic, the exact text and options provided will vary. But you will notice an option to begin building that will read something similar to:
|
||||
>
|
||||
> `Yes, and switch to autopilot mode`.
|
||||
>
|
||||
> Copilot may offer you the option to enable [autopilot mode](https://docs.github.com/copilot/concepts/agents/copilot-cli/autopilot), as shown in the example above. Autopilot mode allows Copilot CLI to work through a task without waiting for your input after each step. Once you give the initial instruction, Copilot CLI works through each step autonomously until it determines the task is complete. As we are running in a contained environment, we're OK running autopilot and allowing all tools.
|
||||
|
||||
8. Copilot will get to work generating the files!
|
||||
|
||||
> [!NOTE]
|
||||
> This operation will likely take several minutes. You will see Copilot edit and create files, update and generate tests, and run all of the tests to ensure everything succeeds. Now's a good time to reflect on what you've explored thus far, or to enjoy a beverage.
|
||||
|
||||
## Review the code
|
||||
|
||||
All AI code needs to be reviewed before being merged into production. Let's take the time now to explore the files Copilot created and modified in implementing the new feature.
|
||||
|
||||
1. Use Copilot CLI to display the "diff" or code changes by using the following command in Copilot CLI:
|
||||
|
||||
```
|
||||
/diff
|
||||
```
|
||||
|
||||
2. Note the files changed. Use your arrow keys to switch left and right to view the different files. You should see updates to files such as the games listing page (where the new filter controls and client-side filtering live) and `src/lib/games.ts`, plus tests like `games.test.ts`. You may also see updates to `publishers.ts` if Copilot refines your existing helper to align with the full implementation.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You've now added filtering functionality to the website with the help of Copilot CLI! Specifically, you:
|
||||
|
||||
- utilized plan mode to generate a plan for implementing the filtering functionality.
|
||||
- generated the code necessary to add filtering to the website with Copilot.
|
||||
|
||||
Of course, the next step from here is to make sure it works. Let's [test your feature with the Playwright MCP server][next-lesson] before we open a pull request.
|
||||
|
||||
## Resources
|
||||
|
||||
- [Using Copilot CLI][using-copilot-cli]
|
||||
- [About Copilot CLI][about-copilot-cli]
|
||||
- [Context management in Copilot CLI][context-management]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cli/2-custom-instructions/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cli/4-mcp/
|
||||
[using-copilot-cli]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli
|
||||
[about-copilot-cli]: https://docs.github.com/copilot/concepts/agents/about-copilot-cli
|
||||
[context-management]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli#context-management
|
||||
@@ -0,0 +1,143 @@
|
||||
---
|
||||
title: "Exercise 4 - Testing your feature with the Playwright MCP server"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
You just generated the filtering feature with Copilot CLI. Before you open a pull request, you should confirm it works in the browser. Rather than click through the app yourself, you'll connect the **Playwright MCP server** and let Copilot drive a real browser to test the feature for you.
|
||||
|
||||
In this exercise, you will:
|
||||
|
||||
- understand what Model Context Protocol (MCP) is and how MCP servers extend Copilot CLI.
|
||||
- add the Playwright MCP server to Copilot CLI.
|
||||
- ask Copilot to use it to manually test your filtering feature in a browser.
|
||||
|
||||
## What is Model Context Protocol (MCP)?
|
||||
|
||||
[Model Context Protocol (MCP)](https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/) provides AI agents with a way to communicate with external tools and services. By using MCP, AI agents can communicate with external tools and services in real-time. This allows them to access up-to-date information (using resources) and perform actions on your behalf (using tools).
|
||||
|
||||
These tools and resources are accessed through an MCP server, which acts as a bridge between the AI agent and the external tools and services. The MCP server is responsible for managing the communication between the AI agent and the external tools (such as existing APIs or local tools like NPM packages). Each MCP server represents a different set of tools and resources that the AI agent can access.
|
||||
|
||||
A couple of popular existing MCP servers are:
|
||||
|
||||
- **[GitHub MCP Server](https://github.com/github/github-mcp-server)**: This server provides access to a set of APIs for managing your GitHub repositories. It allows the AI agent to perform actions such as creating new repositories, updating existing ones, and managing issues and pull requests.
|
||||
- **[Playwright MCP Server](https://github.com/microsoft/playwright-mcp)**: This server provides browser automation capabilities using Playwright. It allows the AI agent to perform actions such as navigating to web pages, filling out forms, and clicking buttons.
|
||||
|
||||
There are many other MCP servers available that provide access to different tools and resources. GitHub hosts an [MCP registry](https://github.com/mcp) to enhance discoverability and contributions to the ecosystem.
|
||||
|
||||
> [!CAUTION]
|
||||
> With regard to security, treat MCP servers as you would any other dependency in your project. Before using an MCP server, carefully review its source code, verify the publisher, and consider the security implications. Only use MCP servers that you trust and be cautious about granting access to sensitive resources or operations.
|
||||
|
||||
> [!NOTE]
|
||||
> The [GitHub MCP server][github-mcp-server] is **built in** to Copilot CLI — it's already available without any setup, which is how Copilot has been reading and writing to your repository throughout the workshop. In this exercise you'll add a *second* server, Playwright, to give Copilot a browser.
|
||||
|
||||
## Add the Playwright MCP server
|
||||
|
||||
The quickest way to add a server is the interactive `/mcp add` command. You'll register the [Playwright MCP server][playwright-mcp-server], which gives Copilot a browser it can control.
|
||||
|
||||
1. Return to your codespace. If you closed it, navigate to your repository on GitHub.com, select **Code** > **Codespaces**, then reopen your existing codespace.
|
||||
2. Return to your open Copilot CLI session. If the terminal is closed or you exited Copilot CLI, open a terminal by selecting <kbd>Ctrl</kbd>+<kbd>\`</kbd>, then start it from the repository root by running `copilot --yolo --enable-all-github-mcp-tools`. Trust the project folder if prompted, then run `/models` and select **Auto**.
|
||||
3. In your Copilot CLI session, enter:
|
||||
|
||||
```text
|
||||
/mcp add
|
||||
```
|
||||
|
||||
4. A configuration form appears. Use <kbd>Tab</kbd> to move between fields and fill it in as follows:
|
||||
|
||||
- **Server Name**: `playwright`
|
||||
- **Server Type**: select **Local** (also labelled **STDIO**)
|
||||
- **Command**: `npx @playwright/mcp@latest --headless`
|
||||
- **Tools**: leave as `*` to allow all of the server's tools
|
||||
|
||||
5. Press <kbd>Ctrl</kbd>+<kbd>S</kbd> to save. The server is added and available immediately — no restart required.
|
||||
|
||||
The `--headless` flag tells Playwright to run the browser without a visible window, which is required inside a codespace where there's no desktop to display it. Behind the scenes, this writes the server to your `~/.copilot/mcp-config.json` file:
|
||||
|
||||
```json
|
||||
{
|
||||
"mcpServers": {
|
||||
"playwright": {
|
||||
"type": "local",
|
||||
"command": "npx",
|
||||
"args": ["@playwright/mcp@latest", "--headless"],
|
||||
"tools": ["*"]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
6. Confirm the server is registered and active by listing your MCP servers:
|
||||
|
||||
```text
|
||||
/mcp show
|
||||
```
|
||||
|
||||
7. You should see `playwright` listed alongside the built-in `github` server.
|
||||
|
||||
> [!NOTE]
|
||||
> The Tailspin Toys project already uses Playwright for its end-to-end tests, so the browser Playwright needs is typically already installed. If Copilot later reports that a browser is missing, have it run `npx playwright install chromium` and try again.
|
||||
|
||||
## Start the website
|
||||
|
||||
The Playwright MCP server needs a running app to test against. Start the Astro dev server in a **separate** terminal so it keeps running while you work in Copilot CLI.
|
||||
|
||||
1. Open a new terminal in your codespace by selecting <kbd>Ctrl</kbd>+<kbd>\`</kbd>.
|
||||
2. Start the website:
|
||||
|
||||
```bash
|
||||
npm run dev
|
||||
```
|
||||
|
||||
3. Leave this terminal running. Once you see the `Astro server: http://localhost:4321` banner, the app is ready.
|
||||
|
||||
## Test the filtering feature
|
||||
|
||||
Return to your Copilot CLI session and ask Copilot to test the feature.
|
||||
|
||||
The [Playwright MCP server][playwright-mcp-server] gives Copilot a real browser to drive. Instead of you clicking through the app to check your work, the agent can open a page, navigate, apply filters, and read the result back to you — then summarize what it saw. It's the fastest way to confirm a feature behaves the way you expect without leaving the conversation.
|
||||
|
||||
Under the hood, the Playwright MCP server works from the page's [accessibility tree][playwright-mcp-server] rather than screenshots. That means the agent reasons over structured, labelled elements (buttons, links, list items) the same way assistive technology does — so a quick functional check doubles as a light accessibility sanity check.
|
||||
|
||||
With the server connected and the app running, ask Copilot to exercise the filtering feature you just built:
|
||||
|
||||
```text
|
||||
Using the Playwright MCP server, open a browser to the running app at http://localhost:4321 and verify the new game filtering feature:
|
||||
|
||||
1. Go to the games page and note how many games are listed.
|
||||
2. Apply a category filter and confirm the list updates to only show games in that category.
|
||||
3. Clear it, then apply a publisher filter and confirm the list updates to that publisher.
|
||||
4. Combine a category and a publisher filter and confirm the results respect both.
|
||||
|
||||
Report what you observe at each step, and call out anything that does not behave as expected.
|
||||
```
|
||||
|
||||
Copilot will launch a browser through the Playwright MCP server, walk through each step, and report back what it found. Read its summary against the acceptance criteria in the issue — if something looks off, ask follow-up questions or send it back to fix the code before you open a pull request.
|
||||
|
||||
> [!NOTE]
|
||||
> The app needs to be running at `http://localhost:4321` for this test. If you stopped the dev server, start it again before sending the prompt. The first time Copilot uses the Playwright MCP server it may need to download a browser — if it reports a missing browser, have it run `npx playwright install chromium` and try again.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
Congratulations, you used the Playwright MCP server to manually test your feature with Copilot CLI! To recap, you:
|
||||
|
||||
- learned what Model Context Protocol (MCP) is and how MCP servers extend Copilot CLI.
|
||||
- added the Playwright MCP server with `/mcp add`.
|
||||
- asked Copilot to drive a browser and verify your filtering feature before shipping it.
|
||||
|
||||
Now that you've confirmed the feature works, you can continue to the next exercise, where you'll [open a pull request with the help of an agent skill][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [What the heck is MCP and why is everyone talking about it?][mcp-blog-post]
|
||||
- [Microsoft Playwright MCP Server][playwright-mcp-server]
|
||||
- [Adding MCP servers for Copilot CLI][cli-add-mcp]
|
||||
- [GitHub MCP Server][github-mcp-server]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cli/3-generating-code/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cli/5-agent-skills/
|
||||
[mcp-blog-post]: https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/
|
||||
[github-mcp-server]: https://github.com/github/github-mcp-server
|
||||
[cli-add-mcp]: https://docs.github.com/copilot/how-tos/copilot-cli/customize-copilot/add-mcp-servers
|
||||
[playwright-mcp-server]: https://github.com/microsoft/playwright-mcp
|
||||
@@ -0,0 +1,105 @@
|
||||
---
|
||||
title: "Exercise 5 - Using agent skills"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Doing app development often involves repeatable tasks like generating builds, running tests, or creating pull requests. **Agent skills** let you give Copilot — and other AI agents — guidance on how to perform those tasks. A skill is a folder of instructions, scripts, and resources that the agent can load on demand. [Agent Skills is an open standard][agent-skills-repo] used by a range of agents, so the same skill can work across Copilot Chat in agent mode, Copilot cloud agent, Copilot CLI, and the GitHub Copilot app.
|
||||
|
||||
Let's explore how a skill can ensure pull requests follow the specifications set forth by our team.
|
||||
|
||||
## Scenario
|
||||
|
||||
The team has a set of requirements for pull requests (PR):
|
||||
|
||||
- clear commit messages, with files grouped logically.
|
||||
- all tests must pass before a PR is created.
|
||||
- each PR must contain the following sections:
|
||||
- a description of why the changes were made.
|
||||
- an overview of the files changed.
|
||||
- snippets of important code blocks.
|
||||
- details of the changes made grouped together.
|
||||
|
||||
As the team is using Copilot to generate code and PRs, it wants to ensure the AI tools follow these requirements.
|
||||
|
||||
In this exercise you will:
|
||||
|
||||
- explore an existing skill for creating pull requests.
|
||||
- learn how skills are utilized by the AI agent.
|
||||
- create a PR which matches the guidelines with the help of the skill.
|
||||
|
||||
## Creating agent skills
|
||||
|
||||
Skills live in the `.github/skills` folder of a project, or globally in `~/.copilot/skills`. Each skill is a folder containing a `SKILL.md` file with YAML frontmatter (a `name` and a `description`) followed by the markdown instructions:
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: make-contribution
|
||||
description: All changes to code must follow the guidance documented in the repository. Before any issue is filed, branch is made, commits generated, or pull request (or PR) created, a search must be done to ensure the right steps are followed. Whenever asked to create an issue, commit messages, to push code, or create a PR, use this skill so everything is done correctly.
|
||||
---
|
||||
```
|
||||
|
||||
Skills can also include subfolders with scripts, assets, and reference material. The full structure is covered in the [agent skills specification][agent-skills-spec].
|
||||
|
||||
> [!TIP]
|
||||
> Skills are loaded dynamically. The agent decides which skill applies based on the `description` field — a clear, scenario-specific description is the difference between a skill that gets used and one that gets ignored.
|
||||
|
||||
## Executing skills
|
||||
|
||||
Skills are loaded dynamically when the agent determines they're necessary. The decision of what skills to use is driven by the description in the `SKILL.md` file. As such, it's important to have clear descriptions which define the use case for the skill.
|
||||
|
||||
## Exploring the PR skill
|
||||
|
||||
Because Tailspin Toys has a set of requirements for creating PRs, they created a skill to help AI tools be able to generate PRs which follow these guidelines. Let's explore the skill to understand what it'll do.
|
||||
|
||||
1. Open `.github/skills/make-contribution/SKILL.md`.
|
||||
2. Note the name and description. Notice how the description highlights the scenario in which it should be used, which is whenever a request is made to create a pull request or committing code.
|
||||
3. Read through the skill. Notice the rules are defined about how branches should be created, commits generated, and the contents of the pull request.
|
||||
|
||||
## Using the skill
|
||||
|
||||
As highlighted previously, skills are automatically invoked by Copilot CLI. As a result, all we need to do is ask Copilot to create a PR!
|
||||
|
||||
1. Return to your codespace. If you closed it, navigate to your repository on GitHub.com, select **Code** > **Codespaces**, then reopen your existing codespace.
|
||||
2. Return to your open Copilot CLI session. If the terminal is closed or you exited Copilot CLI, open a terminal by selecting <kbd>Ctrl</kbd>+<kbd>\`</kbd>, then start it from the repository root by running `copilot --yolo --enable-all-github-mcp-tools`. Trust the project folder if prompted, then run `/models` and select **Auto**.
|
||||
3. Ask Copilot to create a PR by using the following prompt:
|
||||
|
||||
```
|
||||
Can you please create a pull request for me!
|
||||
```
|
||||
|
||||
4. Copilot will acknowledge the request. After a few moments, you'll notice Copilot will indicate it's utilizing the **make-contribution** skill.
|
||||
5. Copilot will then follow the instructions in the skill. It will start by running the tests, then create a branch, commits, and eventually the PR.
|
||||
6. Once the PR is created, return to your repository and open the PR. Note the sections follow the guidelines set forth in the skill, matching the requirements the team put forth.
|
||||
7. Before moving to the next exercise, reset your local workspace to a fresh branch from `main` so your accessibility work stays separate from this filtering PR:
|
||||
|
||||
```bash
|
||||
git checkout main
|
||||
git pull
|
||||
git checkout -b accessibility-cli
|
||||
```
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
With the help of an agent skill, you created a new PR which matches documented requirements! You:
|
||||
|
||||
- explored an existing skill for creating pull requests.
|
||||
- learned how skills are utilized by the AI agent.
|
||||
- created a PR which matches the guidelines with the help of the skill.
|
||||
|
||||
Skills are perfect for tasks, but for more robust operations we want to take advantage of [custom agents][next-lesson], which we'll explore next!
|
||||
|
||||
## Resources
|
||||
|
||||
- [About Agent Skills][about-agent-skills]
|
||||
- [Agent Skills Specification][agent-skills-spec]
|
||||
- [Agent Skills Repository][agent-skills-repo]
|
||||
- [Agent Skills on awesome-copilot][awesome-copilot-skills]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cli/4-mcp/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cli/6-custom-agents/
|
||||
[about-agent-skills]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[awesome-copilot-skills]: https://github.com/github/awesome-copilot/tree/main/skills
|
||||
[agent-skills-repo]: https://github.com/agentskills/agentskills
|
||||
[agent-skills-spec]: https://agentskills.io/specification
|
||||
@@ -0,0 +1,97 @@
|
||||
---
|
||||
title: "Exercise 6 - Custom agents with GitHub Copilot CLI"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
## What are custom agents?
|
||||
|
||||
[Custom agents][custom-agents-concept] in GitHub Copilot allow you to create specialized AI assistants tailored to specific tasks or domains within your development workflow. By defining agents through markdown files in the `.github/agents` folder of your repository, you can provide Copilot with focused instructions, best practices, coding patterns, and domain-specific knowledge that guide it to perform particular types of work more effectively. Teams can codify their expertise into reusable agents — an accessibility agent that enforces [WCAG][wcag] compliance, a security agent that follows secure coding practices, or a testing agent that maintains consistent test patterns.
|
||||
|
||||
Custom agents are defined by markdown files in the `.github/agents` folder of your project, or globally in `~/.copilot/agents`. Each file has YAML frontmatter with at least a `name` and `description`, followed by a markdown prompt that defines the agent's behavior, expertise, and instructions.
|
||||
|
||||
### Custom agents compared with agent skills
|
||||
|
||||
There's some logical overlap between custom agents and [agent skills][agent-skills-concept]. Both are primarily defined with markdown files and tell an AI how to perform operations. The cleanest way to separate them: a **custom agent** is the worker, and **skills** are tools.
|
||||
|
||||
Custom agents have their own context window and are built to orchestrate skills (and even other agents) as part of doing their work. In this lab, the accessibility custom agent reviews and updates the site against accessibility guidelines; as part of that work it could call skills such as a pull-request workflow skill or one that runs and manages tests.
|
||||
|
||||
> [!NOTE]
|
||||
> There's no single "right" way to author a custom agent. As with anything in AI, test and iterate to find what works for your environments and scenarios.
|
||||
|
||||
## Scenario
|
||||
|
||||
Many web applications fall short of being accessible to all users, and the website you're working in is no exception. You'll use a custom agent to identify and resolve accessibility shortcomings.
|
||||
|
||||
Tailspin Toys is committed to ensuring their crowdfunding platform is accessible to all users, regardless of their visual abilities or preferences. Recent user feedback has highlighted that some users find the current dark theme difficult to read due to insufficient contrast between text and background colors. To address this accessibility concern, the design team has requested the implementation of a high-contrast mode that users can toggle on and off.
|
||||
|
||||
Because accessibility is critical, you want to ensure this is implemented as quickly as possible. You're going to utilize a custom agent to generate the functionality.
|
||||
In this exercise, you will:
|
||||
|
||||
- explore custom agents.
|
||||
- enable a custom agent and assign it a task using Copilot CLI.
|
||||
|
||||
## Reviewing the accessibility custom agent
|
||||
|
||||
A custom agent has already been created for you for accessibility. Let's review the contents to understand how it will guide Copilot.
|
||||
|
||||
1. Open `.github/agents/accessibility.md`.
|
||||
2. Note the YAML frontmatter with the `name` and `description` fields.
|
||||
|
||||
> [!CAUTION]
|
||||
> The frontmatter with `name` and `description` is required for custom agents.
|
||||
|
||||
3. From there, scan and review the next sections which highlight:
|
||||
- Core responsibilities when generating code for an accessible website.
|
||||
- Best practices for accessibility.
|
||||
- Code examples for HTML, CSS, and JavaScript.
|
||||
- A list of common pitfalls and mistakes.
|
||||
## Using a custom agent in Copilot CLI
|
||||
|
||||
You can start a custom agent in Copilot CLI by using the `/agent` command. Let's perform an accessibility pass on our website.
|
||||
|
||||
1. Return to your codespace. If you closed it, navigate to your repository on GitHub.com, select **Code** > **Codespaces**, then reopen your existing codespace.
|
||||
2. Return to your open Copilot CLI session. If the terminal is closed or you exited Copilot CLI, open a terminal by selecting <kbd>Ctrl</kbd>+<kbd>\`</kbd>, then start it from the repository root by running `copilot --yolo --enable-all-github-mcp-tools`. Trust the project folder if prompted, then run `/models` and select **Auto**.
|
||||
3. Bring up the list of agents by typing `/agent` in the prompt window in Copilot CLI and selecting <kbd>Enter</kbd>.
|
||||
4. Select the **Accessibility agent** from the list of available agents.
|
||||
5. Use the following prompt to ask the accessibility agent to perform a review and generate fixes for the accessibility backlog item:
|
||||
|
||||
```
|
||||
Perform an accessibility review of the site. Pull the related issue down from the repository for details. Implement a high-contrast mode toggle that persists the user's preference across page reloads. Ensure there are e2e tests for any updates made to the project. Then create a PR with the updates.
|
||||
```
|
||||
|
||||
6. Copilot gets to work on the task! It will start by retrieving the issue, then performing the review, generating updates, and finally creating the PR. You should also notice when it creates the PR it utilizes the skill focused on PRs for the project.
|
||||
|
||||
> [!NOTE]
|
||||
> This process will likely take a few minutes. It's a good time to reflect on everything you've learned, enjoy a beverage, or sneak ahead to the next module which talks about some additional commands available to you in Copilot CLI.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
This lesson explored [custom agents][custom-agents] in GitHub Copilot, specialized AI assistants tailored to specific tasks and domains. With custom agents you can codify your team's expertise and standards into reusable agents that guide Copilot to perform particular types of work more effectively.
|
||||
|
||||
You explored these concepts:
|
||||
|
||||
- how custom agents are defined.
|
||||
- using a custom agent in Copilot CLI.
|
||||
|
||||
Next up, let's explore [some slash commands][next-lesson] to learn some additional tricks with Copilot CLI.
|
||||
|
||||
## Resources
|
||||
|
||||
- [Custom agents][custom-agents]
|
||||
- [Creating custom agents for a repository][creating-custom-agents]
|
||||
- [Custom agents on awesome-copilot][awesome-copilot-agents]
|
||||
- [Preparing to use custom agents in your organization][org-custom-agents]
|
||||
- [Preparing to use custom agents in your enterprise][enterprise-custom-agents]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cli/5-agent-skills/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cli/7-slash-commands/
|
||||
[custom-agents]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli#use-custom-agents
|
||||
[creating-custom-agents]: https://docs.github.com/copilot/how-tos/use-copilot-agents/cloud-agent/create-custom-agents
|
||||
[awesome-copilot-agents]: https://github.com/github/awesome-copilot/tree/main/agents
|
||||
[org-custom-agents]: https://docs.github.com/copilot/how-tos/administer-copilot/manage-for-organization/prepare-for-custom-agents
|
||||
[enterprise-custom-agents]: https://docs.github.com/copilot/how-tos/administer-copilot/manage-for-enterprise/manage-agents/prepare-for-custom-agents
|
||||
[custom-agents-concept]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[agent-skills-concept]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[wcag]: https://www.w3.org/WAI/standards-guidelines/wcag/
|
||||
@@ -0,0 +1,161 @@
|
||||
---
|
||||
title: "Exercise 7 - Slash commands in GitHub Copilot CLI"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Like any good CLI tool, GitHub Copilot CLI includes many slash commands to interact with it. These commands expose advanced functionality, "behind-the-scenes" information, or additional configuration options. You've already explored a couple with `/clear` to clear context and `/mcp` to inspect MCP servers. Let's explore a couple of other powerful ones, including `/context`, `/model`, `/share`, and `/delegate`.
|
||||
|
||||
## Scenario
|
||||
|
||||
You've wrapped the core CLI flows. Now let's look at a few additional capabilities — sharing sessions, switching models, and delegating tasks to [Copilot cloud agent][about-cloud-agent].
|
||||
|
||||
In this exercise you will use:
|
||||
|
||||
- `/share` to create a GitHub gist to share your session with the team.
|
||||
- `/context` to see the context Copilot CLI is currently using.
|
||||
- `/model` to explore the list of available models and select a new one if you so desire.
|
||||
- `/delegate` to optionally hand off a task to cloud agent. This requires cloud agent, available on Copilot Student, Pro, Pro+, Business, or Enterprise — every plan except Copilot Free.
|
||||
|
||||
## Sharing a session
|
||||
|
||||
Using any tool, including an AI tool, is a skill. Working together as a team, sharing learnings with each other, is the best way to help improve everyone's experience and generate higher quality code. To support this, Copilot CLI provides a `/share` command. The `/share` command can generate a markdown file or GitHub gist with the details of the session, including the prompts used and logic Copilot followed.
|
||||
|
||||
Let's create a GitHub gist we could share with our team.
|
||||
|
||||
1. Return to your codespace. If you closed it, navigate to your repository on GitHub.com, select **Code** > **Codespaces**, then reopen your existing codespace.
|
||||
2. Return to your open Copilot CLI session. If the terminal is closed or you exited Copilot CLI, open a terminal by selecting <kbd>Ctrl</kbd>+<kbd>\`</kbd>, then start it from the repository root by running `copilot --yolo --enable-all-github-mcp-tools`. Trust the project folder if prompted, then run `/model` and select **Auto**.
|
||||
3. In the prompt window for Copilot CLI, send the following command:
|
||||
|
||||
```
|
||||
/share gist
|
||||
```
|
||||
|
||||
4. In just a couple of moments, Copilot will create a gist and display the link.
|
||||
5. Copy the link text.
|
||||
6. In a new browser tab, paste the link to explore the gist. Note how the gist highlights the prompts sent, skills and agents used, Copilot's thought process, and even the code and results from locally run commands.
|
||||
|
||||
The gists and markdown files generated by `/share` can be used for documentation purposes of how code was generated, or to share with your team about how certain actions were performed that generated the desired results from Copilot.
|
||||
|
||||
## Exploring Copilot CLI's context
|
||||
|
||||
When working on larger or more complex tasks you may bump into the maximum context window for the model. The exact size of the window will vary based on the model being used and the version of Copilot CLI. When the context window is maxed out, Copilot CLI will automatically compact it, summarizing information and removing anything it deems isn't relevant to the current task. You can both see the current state of the context and manually compact the context by using slash commands. Let's explore the context window.
|
||||
|
||||
1. In the prompt window for Copilot CLI, send the following command:
|
||||
|
||||
```
|
||||
/context
|
||||
```
|
||||
|
||||
2. In just a couple of moments, Copilot CLI will generate a visual representation of its current context:
|
||||
|
||||
|
||||
|
||||
3. Note the model displayed (which may be different than the one in the image), and the current percentage of tokens used. The rest of the information highlights:
|
||||
|
||||
| Title | Description |
|
||||
| ------------ | ------------------------------------------------------ |
|
||||
| System/Tools | Instructions files, file contents and tool definitions |
|
||||
| Messages | Conversation history between you and Copilot |
|
||||
| Buffer | Reserved space by Copilot CLI for generating responses |
|
||||
| Free space | Remaining free space |
|
||||
|
||||
4. Compact the conversation history by sending the following slash command to Copilot CLI:
|
||||
|
||||
```
|
||||
/compact
|
||||
```
|
||||
|
||||
5. Once completed, send the following command to display the current context stats again:
|
||||
|
||||
```
|
||||
/context
|
||||
```
|
||||
|
||||
6. Note the change in context. There might not be a drastic change as the context window is likely relatively small at the moment.
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot CLI will automatically compact when it becomes full. As it approaches 100% capacity it will display the percentage just above the prompt window. Normally it will compact asynchronously, allowing you to continue interacting with Copilot while it does its work. It may however block a running operation for several seconds while performing its work.
|
||||
|
||||
### Best practices with context
|
||||
|
||||
In most sessions with Copilot context will be managed efficiently by Copilot itself without any specific guidance. However, there may be instances when you decide to manually instruct Copilot to either clear or compact its history:
|
||||
|
||||
- If you are changing to a different part of the application, or to an unrelated task, you can use `/clear` to start new to avoid confusing Copilot with older, unrelated context.
|
||||
- If you are approaching the maximum context window, you can manually `/compact` your context to control when it happens.
|
||||
|
||||
> [!CAUTION]
|
||||
> Again, the majority of the time, Copilot will manage its context without direct interaction from you. If you notice Copilot is a bit confused by older information, or are about to switch to an unrelated task, then you might consider using the manual commands.
|
||||
|
||||
## Choosing your model
|
||||
|
||||
Different models have different strengths, and different developers have different preferences. Copilot CLI allows you to list and select the model you wish to use!
|
||||
|
||||
1. Display the list of models by sending the following slash command to Copilot CLI:
|
||||
|
||||
```
|
||||
/model
|
||||
```
|
||||
|
||||
2. Note the list of models. Each model will have both its name and cost-per-request modifier listed next to it.
|
||||
3. If you wish, select a new model! Or select <kbd>Esc</kbd> to exit the model list.
|
||||
|
||||
> [!CAUTION]
|
||||
> Model selection persists in Copilot CLI.
|
||||
|
||||
## Delegating to cloud agent (optional)
|
||||
|
||||
There are times when you want to keep working in your terminal but hand off a longer-running task to Copilot cloud agent. The `/delegate` command sends the current Copilot CLI session to GitHub.com, where cloud agent picks it up, works asynchronously, and opens a pull request when done.
|
||||
|
||||
> [!NOTE]
|
||||
> `/delegate` requires cloud agent, available on Copilot Student, Pro, Pro+, Business, or Enterprise — every plan except Copilot Free. If you don't have access, read through this section and skip the hands-on steps.
|
||||
|
||||
1. Clear the current session first so accumulated workshop context isn't delegated:
|
||||
|
||||
```
|
||||
/clear
|
||||
```
|
||||
|
||||
2. Send a small, well-scoped prompt. For example, you could delegate the stretch-goal pagination from your backlog:
|
||||
|
||||
```
|
||||
Implement pagination on the game list page so it shows a fixed number of games per page with Previous and Next controls, and add tests.
|
||||
```
|
||||
|
||||
3. Send the following slash command to hand the session to cloud agent, and confirm the prompt you want to delegate:
|
||||
|
||||
```
|
||||
/delegate
|
||||
```
|
||||
|
||||
4. Open [Copilot agents](https://github.com/copilot/agents) in a browser to monitor progress.
|
||||
5. You don't need to wait for the pull request to complete in this harness; you can return to it later. If you want to dig deeper into managing asynchronous agent work, continue with the [Cloud agent harness](/learning-hub/copilot-workshops/cloud/).
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
Using slash commands in Copilot CLI allows you to configure it, share sessions, and get internal information about how Copilot's working. In this lesson you used or explored:
|
||||
|
||||
- `/share` to create a GitHub gist to share your session with the team.
|
||||
- `/context` to see the context Copilot CLI is currently using.
|
||||
- `/model` to explore the list of available models and select a new one if you so desire.
|
||||
- Learned about `/delegate` as an optional bridge to cloud agent.
|
||||
|
||||
There are of course more slash commands available, and more to explore with Copilot CLI! Let's close out our journey by [reviewing what we've learned][next-lesson] and some next steps to continue learning.
|
||||
|
||||
## Resources
|
||||
|
||||
- [Using Copilot CLI][using-copilot-cli]
|
||||
- [About Copilot CLI][about-copilot-cli]
|
||||
- [Context Management in Copilot CLI][context-management]
|
||||
- [Share Sessions with Copilot CLI][share-sessions]
|
||||
- [Selecting Models in Copilot CLI][selecting-models]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cli/6-custom-agents/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cli/8-review/
|
||||
[using-copilot-cli]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli
|
||||
[about-copilot-cli]: https://docs.github.com/copilot/concepts/agents/about-copilot-cli
|
||||
[about-cloud-agent]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-cloud-agent
|
||||
[context-management]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli#context-management
|
||||
[share-sessions]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli#share-sessions
|
||||
[selecting-models]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli#select-an-llm
|
||||
@@ -0,0 +1,70 @@
|
||||
---
|
||||
title: "Exercise 8 - Review and Next Steps"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Over the last several exercises, you explored some of the most common use cases for GitHub Copilot CLI, including:
|
||||
|
||||
- interacting with GitHub and other MCP servers.
|
||||
- using instructions files to guide code generation.
|
||||
- implementing skills to add tools to the Copilot CLI toolbox.
|
||||
- calling custom agents for advanced and more complex tasks.
|
||||
- using slash commands to manage your session, and optionally bridging back to cloud agent via `/delegate`.
|
||||
|
||||
Let's talk about some slash commands, best practices, and next steps.
|
||||
|
||||
## Slash commands
|
||||
|
||||
Copilot CLI has a series of slash commands available to interact with it, including ones which allow you to configure it or see what's going on behind the scenes. You've already used `/clear` to start a new chat which clears the current context, and `/mcp` to inspect and manage MCP servers. Some additional ones you might find helpful are:
|
||||
|
||||
| Command | Description |
|
||||
| ------------------ | ------------------------------------------------------------- |
|
||||
| `/add-dir` | Add a directory to the trusted list for Copilot |
|
||||
| `/clear`, `/new` | Clear the conversation history and start fresh |
|
||||
| `/compact` | Summarize conversation history to reduce context window usage |
|
||||
| `/context` | Show context window token usage and visualization |
|
||||
| `/diff` | Review the changes made in the current directory |
|
||||
| `/model` | Select AI model to use (Claude Sonnet, GPT-5, etc.) |
|
||||
| `/plan <prompt>` | Create an implementation plan before coding |
|
||||
| `/review <prompt>` | Run code review agent to analyze changes |
|
||||
| `/delegate` | Delegate task to Copilot cloud agent for async processing |
|
||||
| `/session` | Show session info and workspace summary |
|
||||
| `/share` | Share session to markdown file or GitHub gist |
|
||||
| `/skills` | Manage skills for enhanced capabilities |
|
||||
| `/usage` | Display session usage metrics and statistics |
|
||||
|
||||
> [!TIP]
|
||||
> Use `/help` to see the full list of available commands and keyboard shortcuts.
|
||||
|
||||
## Best practices
|
||||
|
||||
When using any AI tool, the underlying infrastructure drives the quality of what you get out. Robust instructions files, custom agents, and agent skills all play a part — you explored each of them in this workshop. [awesome-copilot][awesome-copilot] is a good source of templates, and Copilot itself can scaffold these for you as a starting point.
|
||||
|
||||
Context still matters as much as infrastructure. Clearly describing *what* you want built, *why*, and *how* meaningfully changes the output. If a piece of information would help Copilot, pass it along.
|
||||
|
||||
## Next steps
|
||||
|
||||
The best way to improve your skills with any tool is to keep using the tool! Use it for production code, for hobby code, for the little app you've had in your mind for years but never got around to building. Share your learnings with your team, and learn from your team. And, as always, explore the documentation.
|
||||
|
||||
If you'd like to explore more of the GitHub Copilot ecosystem, check out the [VS Code harness](/learning-hub/copilot-workshops/vscode/) or the [Cloud agent harness](/learning-hub/copilot-workshops/cloud/).
|
||||
|
||||
## Resources
|
||||
|
||||
- [About Copilot CLI][about-copilot-cli]
|
||||
- [Using Copilot CLI][using-copilot-cli]
|
||||
- [Awesome Copilot Repository][awesome-copilot]
|
||||
- [Custom Instructions Guide][repo-instructions]
|
||||
- [Agent Skills Documentation][agent-skills]
|
||||
- [Custom Agents Documentation][custom-agents]
|
||||
- [MCP Specification][mcp-spec]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cli/7-slash-commands/
|
||||
[about-copilot-cli]: https://docs.github.com/copilot/concepts/agents/about-copilot-cli
|
||||
[using-copilot-cli]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli
|
||||
[awesome-copilot]: https://github.com/github/awesome-copilot
|
||||
[repo-instructions]: https://docs.github.com/copilot/how-tos/configure-custom-instructions/add-repository-instructions
|
||||
[agent-skills]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[custom-agents]: https://docs.github.com/copilot/how-tos/use-copilot-agents/use-copilot-cli#use-custom-agents
|
||||
[mcp-spec]: https://modelcontextprotocol.io/
|
||||
@@ -0,0 +1,53 @@
|
||||
---
|
||||
title: "GitHub Copilot CLI"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
**[GitHub Copilot CLI](https://docs.github.com/copilot/concepts/agents/about-copilot-cli)** puts GitHub Copilot in your terminal as an agentic coding assistant. It explores codebases, generates code, runs commands, and connects to external tools — all from the command line, so you can stay in the flow without switching to a graphical editor.
|
||||
|
||||
Across these exercises you'll install and authenticate Copilot CLI, then give it project context with custom instructions before using plan mode to generate a feature deliberately. You'll connect the Playwright MCP server to test that feature in a real browser, then extend Copilot with reusable agent skills and custom agents. Finally, you'll explore slash commands for managing context, models, and sharing, and wrap up with a review of what you've built.
|
||||
|
||||
## Exercises
|
||||
|
||||
| Exercise | Topic | Description |
|
||||
|----------|-------|-------------|
|
||||
| [0. Prerequisites][ex0] | Setup | Create your repository and codespace |
|
||||
| [1. Installing Copilot CLI][ex1] | Installation | Install and authenticate Copilot CLI |
|
||||
| [2. Custom instructions][ex2] | Context | Add an instruction and see how Copilot CLI follows it |
|
||||
| [3. Generating Code][ex3] | Code Generation | Use plan mode and generate features |
|
||||
| [4. Testing with Playwright MCP][ex4] | External Tools | Add the Playwright MCP server and test your feature in a browser |
|
||||
| [5. Agent Skills][ex5] | Skills | Enhance Copilot with specialized skills |
|
||||
| [6. Custom Agents][ex6] | Agents | Review and use custom agents |
|
||||
| [7. Slash Commands][ex7] | CLI Features | Explore context, models, sharing, and optional delegation to cloud agent |
|
||||
| [8. Review][ex8] | Summary | Review key concepts and next steps |
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before attending this workshop, please ensure you have:
|
||||
|
||||
- [ ] A GitHub account with an active **Copilot Student, Pro, Pro+, Business, or Enterprise** plan
|
||||
- [ ] Basic familiarity with terminal/command line operations
|
||||
- [ ] Git installed and configured
|
||||
|
||||
> [!TIP]
|
||||
> No paid plan? Verified students can get GitHub Copilot for free through [GitHub Education][callout-student-plan-education]. The **Copilot Student** plan includes the agent, MCP, code review, and Copilot CLI features this workshop uses — so you can complete every harness with it.
|
||||
|
||||
> [!NOTE]
|
||||
> If you are using Copilot Business or Copilot Enterprise, ensure your admin has enabled Copilot CLI for use.
|
||||
|
||||
## Get Started
|
||||
|
||||
**[Start with Exercise 0: Prerequisites →][ex0]**
|
||||
|
||||
[ex0]: /learning-hub/copilot-workshops/cli/0-prerequisites/
|
||||
[ex1]: /learning-hub/copilot-workshops/cli/1-install-copilot-cli/
|
||||
[ex2]: /learning-hub/copilot-workshops/cli/2-custom-instructions/
|
||||
[ex3]: /learning-hub/copilot-workshops/cli/3-generating-code/
|
||||
[ex4]: /learning-hub/copilot-workshops/cli/4-mcp/
|
||||
[ex5]: /learning-hub/copilot-workshops/cli/5-agent-skills/
|
||||
[ex6]: /learning-hub/copilot-workshops/cli/6-custom-agents/
|
||||
[ex7]: /learning-hub/copilot-workshops/cli/7-slash-commands/
|
||||
[ex8]: /learning-hub/copilot-workshops/cli/8-review/
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
@@ -0,0 +1,65 @@
|
||||
---
|
||||
title: "Exercise 0: Prerequisites"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Before you start the Copilot cloud agent exercises, you need to get everything ready. You'll create your own copy of the Tailspin Toys repository and spin up a [codespace][codespaces] you can use to edit instruction files and review the work the cloud agent produces.
|
||||
|
||||
## Setting up the lab repository
|
||||
|
||||
To create a copy of the repository for the code you'll create, you'll make an instance from the [template][template-repository]. The new instance will contain all of the necessary files for the lab, and you'll use it as you work through the exercises.
|
||||
|
||||
1. In a new browser window, navigate to the GitHub repository for this lab: `https://github.com/github-samples/tailspin-toys`.
|
||||
2. Create your own copy of the repository by selecting the **Use this template** button on the lab repository page. Then select **Create a new repository**.
|
||||
|
||||
|
||||
|
||||
3. If you are completing the workshop as part of an event being led by GitHub or Microsoft, follow the instructions provided by the mentors. Otherwise, you can create the new repository in an organization where you have access to GitHub Copilot.
|
||||
|
||||
|
||||
|
||||
4. Make a note of the repository path you created (**organization-or-user-name/repository-name**), as you will be referring to this later in the lab.
|
||||
## Creating a codespace
|
||||
|
||||
Next up, you'll use a codespace to complete the lab exercises.
|
||||
|
||||
[GitHub Codespaces][codespaces] are a cloud-based development environment that allows you to write, run, and debug code directly in your browser. It provides a fully-featured IDE with support for multiple programming languages, extensions, and tools.
|
||||
|
||||
1. Navigate to your newly created repository.
|
||||
2. Select the green **Code** button.
|
||||
|
||||
|
||||
|
||||
3. Select the **Codespaces** tab and select the **+** button to create a new Codespace.
|
||||
|
||||
|
||||
|
||||
The creation of the codespace will take several minutes, although it's still far quicker than having to manually install all the services! That said, you can use this time to explore other features of GitHub Copilot, which we'll turn your attention to next.
|
||||
|
||||
> [!CAUTION]
|
||||
> You'll return to the codespace in a future exercise. For the time being, leave it open in a tab in your browser.
|
||||
|
||||
> [!NOTE]
|
||||
> This workshop is built to run inside a codespace or local [dev container][dev-containers]. Both ensure the environment has all the necessary prerequisites installed for a smooth experience. If you'd prefer to run it locally, open the cloned repository in VS Code and select **Reopen in Container** when prompted — VS Code will build the same dev container the codespace uses.
|
||||
|
||||
[codespaces]: https://github.com/features/codespaces
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
## Summary
|
||||
|
||||
Congratulations, you have created a copy of the lab repository! You also began the creation process of your codespace, which you'll use as you work alongside the Copilot cloud agent.
|
||||
|
||||
## Next step
|
||||
|
||||
Let's add custom instructions the cloud agent will follow. Continue to [Exercise 1 - Custom instructions][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [GitHub Codespaces overview][codespaces]
|
||||
- [Creating a repository from a template][template-repository]
|
||||
- [Getting started with Codespaces][codespaces-quickstart]
|
||||
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[codespaces-quickstart]: https://docs.github.com/codespaces/getting-started/quickstart
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cloud/1-custom-instructions/
|
||||
+149
@@ -0,0 +1,149 @@
|
||||
---
|
||||
title: "Exercise 1 - Custom instructions (Cloud agent)"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[← Previous lesson: Prerequisites][previous-lesson] · [Next lesson: Copilot cloud agent →][next-lesson]
|
||||
|
||||
Context is key when working with generative AI. If a task needs to be done a particular way — or there's background information Copilot should know — you want to make sure that context is reachable. [Instruction files][instruction-files] are how you provide that guidance, so Copilot understands not just *what* you want it to do but *how* you want it done.
|
||||
|
||||
In this exercise, you will:
|
||||
|
||||
- explore how project-specific context, coding guidelines, and documentation standards reach Copilot through repository custom instructions and path-scoped instruction files,
|
||||
- add a new repository-wide standard to `.github/copilot-instructions.md`.
|
||||
|
||||
> [!NOTE]
|
||||
> Unlike the VS Code and CLI harnesses, you won't run a *before/after* prompt here — Copilot cloud agent works asynchronously on GitHub issues, so the impact is harder to demonstrate side-by-side in real time. You'll see your instruction file's influence later in this harness when you review the pull requests cloud agent produces.
|
||||
|
||||
## Instruction files
|
||||
|
||||
### Scenario
|
||||
|
||||
As any good dev shop, Tailspin Toys has a set of guidelines and requirements for development practices. These include:
|
||||
|
||||
- The data layer always needs unit tests.
|
||||
- UI should be in dark mode and have a modern feel.
|
||||
- Documentation should be added to code in the form of TSDoc doc comments.
|
||||
- A block of comments should be added to the head of each file describing what the file does.
|
||||
|
||||
Through the use of instruction files you'll ensure Copilot has the right information to perform the tasks in alignment with the practices highlighted.
|
||||
|
||||
### Custom instructions
|
||||
|
||||
Custom instructions allow you to provide context and preferences to Copilot, so that it can better understand your coding style and requirements. This is a powerful feature that can help you steer Copilot to get more relevant suggestions and code snippets. You can specify your preferred coding conventions, libraries, and even the types of comments you like to include in your code. You can create instructions for your entire repository, or for specific types of files for task-level context.
|
||||
|
||||
There are two types of instructions files:
|
||||
|
||||
- `.github/copilot-instructions.md`, a single instruction file sent to Copilot for **every** request for the repository. This file should contain project-level information — context relevant for most chat or CLI requests sent to Copilot. This could include the tech stack being used, an overview of what's being built, best practices, and other global guidance.
|
||||
- `.github/instructions/*.instructions.md` files can be created for specific tasks or file types. You can use them to provide guidelines for particular languages (like TypeScript or Astro), or for tasks like creating a UI component or a new set of unit tests.
|
||||
|
||||
> [!NOTE]
|
||||
> When working in your IDE, instructions files are only used for code generation in Copilot Chat — not for code completions or next-edit suggestions.
|
||||
>
|
||||
> Copilot Chat, Copilot CLI and Copilot cloud agent use both repository-level and `*.instructions.md` files (with `applyTo` front matter) when generating code.
|
||||
>
|
||||
> Finally, Copilot [supports instructions files using other standards][custom-instructions-support], including AGENTS.md and CLAUDE.md files.
|
||||
|
||||
### Best practices for managing instructions files
|
||||
|
||||
A full conversation about creating instructions files is beyond the scope of the workshop. However, the examples provided in the sample project show a representative approach. At a high level:
|
||||
|
||||
- Keep instructions in `copilot-instructions.md` focused on project-level guidance, such as a description of what's being built, the structure of the project, and global coding standards.
|
||||
- Use `*.instructions.md` files to provide specific instructions for file types (unit tests, Astro components, the data layer), or for specific tasks.
|
||||
- Use natural language. Keep guidance clear. Provide examples of how code should (and shouldn't) look.
|
||||
|
||||
There isn't one specific way to create instructions files, just as there isn't one specific way to use AI. You will find through experimentation what works best for your project.
|
||||
|
||||
> [!TIP]
|
||||
> Every project using GitHub Copilot should have a robust collection of instruction files. As you explore the ones in this project, you may notice there are files for numerous types of tasks, including [UI updates][ui-instructions] and [Astro][astro-instructions].
|
||||
>
|
||||
> Copilot can also help generate instruction files for you. Each surface exposes this differently (for example, **Configure Chat → Generate Agent Instructions** in VS Code, or `/init` in Copilot CLI) — the lesson for the surface you're on will call it out where it's relevant.
|
||||
>
|
||||
> Looking for templates or a starting point? Explore [awesome-copilot][awesome-copilot], a repository full of instruction files, custom agents, and other resources.
|
||||
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[awesome-copilot]: https://github.com/github/awesome-copilot
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
## Explore the custom instructions files in this project
|
||||
|
||||
Take a moment to read the instruction files this repository ships with — there's one core `copilot-instructions.md` and a collection of `*.instructions.md` files for various tasks. Open these in your editor or the GitHub web UI.
|
||||
|
||||
1. Open `.github/copilot-instructions.md`.
|
||||
2. Explore the file, noting the brief description of the project plus sections such as **Agent notes**, **Code standards**, **Scripts**, and **Repository Structure**. Under **Code standards**, note the nested **GitHub Actions Workflows** guidance. These are applicable to any interactions you'd have with Copilot.
|
||||
3. Open the `.github/instructions` folder and look around. Note there are instructions for Astro files, the Drizzle data layer, tests, and more.
|
||||
4. Open `.github/instructions/unit-tests.instructions.md`. Note the `applyTo` field at the top — this sets a glob (relative to the repo root) that determines which files the instructions apply to. Here, any TypeScript test file (for example, one matching `**/*.test.ts`) will match.
|
||||
5. Note the instructions specific to creating unit tests for this project.
|
||||
6. Finally, open `.github/instructions/drizzle.instructions.md` and scroll to the bottom. Note the links to other instruction files (like `unit-tests.instructions.md`) and existing files in the project. This lets you break larger instruction sets into smaller, reusable files, and point Copilot at examples to follow when generating code. (Paths there are relative to the instruction file rather than the repo root.)
|
||||
|
||||
> [!NOTE]
|
||||
> The **Code formatting requirements** section in `copilot-instructions.md` documents the project's coding standards, but it doesn't yet require in-code documentation. In the next steps, you'll add rules for TSDoc doc comments and file comment headers.
|
||||
## Add a new repository standard
|
||||
|
||||
The next step is the one bit of editing you'll do here: add a project-wide rule that documentation should live in code as TSDoc doc comments and a file-level comment header. Cloud agent will pick this up when it works on issues you assign to it later in this harness.
|
||||
|
||||
Before you edit, set up a branch to work on (cloud agent will read your instructions from whatever branch the issue targets, but you'll commit your edits cleanly anyway):
|
||||
|
||||
1. From your codespace terminal, create and switch to a new branch:
|
||||
|
||||
```bash
|
||||
git checkout -b custom-instructions-cloud
|
||||
```
|
||||
|
||||
As highlighted previously, `.github/copilot-instructions.md` is designed to provide project-level information to Copilot. Let's ensure repository coding standards are documented to improve code suggestions.
|
||||
|
||||
1. Re-open `.github/copilot-instructions.md`.
|
||||
2. Locate the **Code formatting requirements** section, which should be near line 27. Note how it documents the project's coding standards — but it has no rule yet for in-code documentation, which is why the generated helper had no doc comments.
|
||||
3. Add the following lines of markdown right below the existing standards to instruct Copilot to add file comment headers and TSDoc doc comments:
|
||||
|
||||
```markdown
|
||||
- Every exported function should have a TSDoc comment describing its purpose, parameters, and return value.
|
||||
- Before imports or any code, add a comment block to the file that explains its purpose.
|
||||
```
|
||||
|
||||
4. Save `copilot-instructions.md`.
|
||||
|
||||
> [!TIP]
|
||||
> As you saw in the previous lesson, instruction files can be created at the repository level (`.github/copilot-instructions.md`) for global guidance, or as `*.instructions.md` files for specific languages, file types, or tasks. The repository-level file is the right home for project-wide standards like the doc comment rule you just added.
|
||||
## Commit, push, and merge your instruction update
|
||||
|
||||
Cloud agent reads instruction files from the branch the issue targets. When you assign an issue to Copilot in the next exercise, Copilot will branch from `main` — so your instruction changes must land on `main` for cloud agent to pick them up.
|
||||
|
||||
1. Stage and commit:
|
||||
|
||||
```bash
|
||||
git add .github/copilot-instructions.md
|
||||
git commit -m "Add doc comment and file-header standards to copilot instructions"
|
||||
```
|
||||
|
||||
2. Push the branch:
|
||||
|
||||
```bash
|
||||
git push -u origin custom-instructions-cloud
|
||||
```
|
||||
|
||||
3. Open a pull request from `custom-instructions-cloud` into `main` on github.com and merge it. Cloud agent will then read these instructions when it works on issues assigned in the next exercise.
|
||||
|
||||
> [!TIP]
|
||||
> If you'd rather work on `main` directly for this workshop, you can skip the branch and commit straight to `main`. The branch step is here so the workshop mirrors the way you'd handle this on a real project.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You explored how Copilot picks up context from instruction files in this project and added a new repository-wide standard to `.github/copilot-instructions.md`. You'll see that standard exercised in the pull requests cloud agent generates over the rest of this harness.
|
||||
|
||||
Next, you'll [assign your first issue to Copilot cloud agent][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Instruction files for GitHub Copilot customization][instruction-files]
|
||||
- [Best practices for creating custom instructions][instructions-best-practices]
|
||||
- [5 tips for writing better custom instructions for Copilot][copilot-instructions-five-tips]
|
||||
- [Awesome Copilot — a collection of instruction files and other resources][awesome-copilot]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cloud/0-prerequisites/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cloud/2-cloud-agent/
|
||||
[instruction-files]: https://docs.github.com/copilot/customizing-copilot/about-customizing-github-copilot-chat-responses
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[copilot-instructions-five-tips]: https://github.blog/ai-and-ml/github-copilot/5-tips-for-writing-better-custom-instructions-for-copilot/
|
||||
@@ -0,0 +1,202 @@
|
||||
---
|
||||
title: "Exercise 2 - GitHub Copilot cloud agent"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
| [← Previous lesson: Custom instructions][previous-lesson] |
|
||||
|:--|
|
||||
|
||||
There are likely very few, if any, organizations who don't struggle with tech debt. This could be unresolved security issues, legacy code requiring updates, or feature requests which have languished on the backlog because there just wasn't the time to implement them. GitHub Copilot's cloud agent is built to perform tasks such as updating code and adding functionality, all in an autonomous fashion. Once the agent completes its work, it generates a draft PR ready for a human developer to review. This allows offloading of tedious tasks and an acceleration of the development process, and frees developers to focus on larger picture items.
|
||||
|
||||
You'll explore the following with Copilot cloud agent:
|
||||
|
||||
- customizing the environment for generating code.
|
||||
- ensuring operations are performed securely.
|
||||
- the importance of clearly scoped issues.
|
||||
- assigning issues to Copilot.
|
||||
|
||||
## Scenarios
|
||||
|
||||
Tailspin Toys has some tech debt they'd like to address. The contractors initially hired to create the first version of the site left the documentation in an unideal state - and by that you'll notice it's completely lacking. As a first step, they'd like to see TSDoc doc comments added to all exported functions in the application.
|
||||
|
||||
Additionally, the design team is ready to improve game discovery. They'd like each game's details page to show related games — other titles in the same category — so people can keep browsing. They don't need a polished implementation yet; they just want something they can use for acceptance testing of the UX. This is currently a blocker, but there are other issues which are of higher priority at the moment.
|
||||
|
||||
These are both examples of tasks which can quickly find themselves deprioritized, and are great to assign to Copilot cloud agent. Copilot cloud agent can then work on them asynchronously, allowing the developer to focus on other tasks, then return to review Copilot's work and ensure everything is as expected.
|
||||
## Introducing GitHub Copilot cloud agent
|
||||
|
||||
[GitHub Copilot cloud agent](https://docs.github.com/copilot/concepts/agents/cloud-agent/about-cloud-agent#overview-of-copilot-cloud-agent-formerly-copilot-coding-agent) can perform tasks in the background, much in the same way a human developer would. And, just like with working with a human developer, this can be done in multiple ways, including [assigning a GitHub issue to Copilot](https://docs.github.com/copilot/how-tos/use-copilot-agents/cloud-agent/start-copilot-sessions). Once assigned, Copilot will create a draft pull request to track its progress, setup an environment, and begin working on the task. You can dig into Copilot's session while it's still in flight or after its completed. Once its ready for you to review the proposed solution, it'll tag you in the pull request!
|
||||
## The importance of well-scoped instructions
|
||||
|
||||
There's no magic in GitHub Copilot — you don't get to skip the thinking. Even seemingly straightforward operations carry complexity once you peel back the layers, so [be mindful about how you scope tasks for Copilot cloud agent][cloud-agent-best-practices]. Treat it like an AI pair programmer: work in stages, learn, experiment, and adapt as you go. The fundamentals of software development don't change with the addition of generative AI.
|
||||
|
||||
## Custom instructions in this repository
|
||||
|
||||
Earlier exercises introduced custom instructions and how they guide Copilot. If you've already worked through a custom-instructions hands-on you've seen `.github/copilot-instructions.md` in action; if not, this is a good moment to take a quick look. Before assigning work to Copilot cloud agent, take a read-only look at the instruction files already included in this repository so you can spot their effect later.
|
||||
|
||||
Open the following files in the GitHub web UI for your repository, or in a codespace if you already have one running:
|
||||
|
||||
- `.github/copilot-instructions.md` - Review the **Code standards** section, especially the expectations for TypeScript conventions and TSDoc doc comments.
|
||||
- `.github/instructions/unit-tests.instructions.md` - Notice the `applyTo` frontmatter, which scopes these instructions to `**/*.test.ts` files.
|
||||
|
||||
When you assign the `Code lacks documentation` issue to cloud agent in the next section, watch the resulting pull request for TSDoc doc comments, TypeScript conventions, and comment headers - these come from these instruction files. We'll call this out again when reviewing PRs in a later exercise.
|
||||
|
||||
## Setting up the dev environment for the Copilot cloud agent
|
||||
|
||||
Creating code, regardless of who's involved, typically requires a specific environment and some setup scripts to be run to ensure everything is in a good state. This holds true when assigning tasks to Copilot, which is performing tasks in a similar fashion to a SWE.
|
||||
|
||||
Cloud agent uses [GitHub Actions][github-actions] for its environment when doing its work. You can customize this environment by creating a [special setup workflow][setup-workflow], configured in the `.github/workflows/copilot-setup-steps.yml` file, to run before it gets to work. This enables it to have access to the required development tools and dependencies. This has been pre-configured ahead of the lab to help the lab flow and allow this learning opportunity. It makes sure that Copilot has access to Node.js, project dependencies, browser binaries for end-to-end tests, and the migrated and seeded SQLite database for the single Astro app:
|
||||
|
||||
```yaml
|
||||
name: "Copilot Setup Steps"
|
||||
|
||||
# Allows you to test the setup steps from your repository's "Actions" tab
|
||||
on: workflow_dispatch
|
||||
|
||||
env:
|
||||
ASTRO_TELEMETRY_DISABLED: "1"
|
||||
|
||||
jobs:
|
||||
copilot-setup-steps:
|
||||
runs-on: ubuntu-latest
|
||||
# Set the permissions to the lowest permissions possible needed for *your steps*. Copilot will be given its own token for its operations.
|
||||
permissions:
|
||||
# If you want to clone the repository as part of your setup steps, for example to install dependencies, you'll need the `contents: read` permission. If you don't clone the repository in your setup steps, Copilot will do this for you automatically after the steps complete.
|
||||
contents: read
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v5
|
||||
|
||||
# Frontend / app setup - Node.js (the whole app is now Astro + Drizzle/libSQL)
|
||||
- name: Set up Node.js
|
||||
uses: actions/setup-node@v6
|
||||
with:
|
||||
node-version: "lts/*"
|
||||
cache: "npm"
|
||||
cache-dependency-path: "./package-lock.json"
|
||||
|
||||
- name: Install JavaScript dependencies
|
||||
run: npm ci
|
||||
|
||||
- name: Install Playwright browsers
|
||||
run: npx playwright install --with-deps chromium
|
||||
|
||||
# Migrate + seed the local SQLite database so builds and tests have data.
|
||||
- name: Set up the database
|
||||
run: npm run db:setup
|
||||
```
|
||||
|
||||
It looks like any other GitHub workflow file, but it has a few key points:
|
||||
|
||||
- It contains a single job called `copilot-setup-steps`. This job is executed in GitHub Actions before Copilot starts working on the pull request.
|
||||
- Notice the `workflow_dispatch` trigger, which allows you to run the workflow manually from the **Actions** tab of your repository. This is useful for testing that the workflow runs successfully instead of waiting for Copilot to run it.
|
||||
|
||||
## Adding documentation
|
||||
|
||||
While everyone understands the importance of documentation, most projects have either outdated information or lack it altogether. This is the type of tech debt which often goes unaddressed, slowing productivity and making it more difficult to maintain the codebase or bring new developers into the team. Fortunately, Copilot shines at creating documentation, and this is a perfect issue to assign to Copilot cloud agent. It'll work in the background to generate the necessary documentation. In a future exercise you'll return to review its work.
|
||||
|
||||
1. Navigate to your repository on github.com in a new browser tab.
|
||||
2. Select the **Issues** tab.
|
||||
3. Select **New issue** to open the new issue dialog.
|
||||
4. Select **Blank issue** to create the new issue.
|
||||
5. Set the **Title** to `Code lacks documentation`.
|
||||
6. Set the **Description** to:
|
||||
|
||||
```plaintext
|
||||
Our organization has a requirement that functions and methods include TSDoc doc comments where helpful. Unfortunately, recent updates haven't followed this standard. We need to update the existing code to ensure doc comments are included where they clarify behavior.
|
||||
```
|
||||
|
||||
7. Select **Create** to create the issue.
|
||||
8. On the right side, select **Assign to Copilot** to open the assignment dialog.
|
||||
|
||||
|
||||
|
||||
9. Select **Assign**.
|
||||
|
||||
|
||||
|
||||
10. Select the **Pull Requests** tab.
|
||||
11. Open the newly generated pull request (PR), which will be titled something similar to `[WIP]: Code lacks documentation`. If a new PR doesn't appear on the list, wait for a moment or two and refresh the browser window.
|
||||
12. After a few minutes, you should see that Copilot has created a todo list.
|
||||
|
||||
> [!NOTE]
|
||||
> It may take several minutes for the todo list from Copilot to appear in the PR. Copilot is creating its environment (running the workflow highlighted previously), analyzing the project, and determining the best approach to tackling the problem.
|
||||
|
||||
13. Review the list and the tasks it's going to complete.
|
||||
14. Scroll down the pull request timeline, and you should see an update that Copilot has started working on the issue.
|
||||
15. Select the **View session** button.
|
||||
|
||||
|
||||
|
||||
> [!CAUTION]
|
||||
> You may need to refresh the window to see the updated indicator.
|
||||
|
||||
16. Notice that you can scroll through the live session, and how Copilot is solving the problem. That includes exploring the code and understanding the state, how Copilot pauses to think and decide on the appropriate plan and also creating code.
|
||||
|
||||
This will likely take several minutes. One of the primary goals of Copilot cloud agent is to allow it to perform tasks asynchronously, freeing us to focus on other tasks. We're going to take advantage of that very feature by both assigning another task to Copilot cloud agent, then turning our attention to writing some code to add features to our application.
|
||||
|
||||
## Add a related games section to the game details page
|
||||
|
||||
As has been highlighted, one of the great advantages of GitHub Copilot cloud agent is the ability to divide work, where you can focus on one set of tasks while it focuses on another. While adding a related games section for the design team might not necessarily take a long time, it's still time which could be used for other tasks. Let's assign it to Copilot cloud agent!
|
||||
|
||||
1. Return to your repository on github.com.
|
||||
2. Select the **Issues** tab.
|
||||
3. Select **New issue** to open the new issue dialog.
|
||||
4. Select **Blank issue** to use the blank template.
|
||||
5. Set the **Title** to: `Show related games on the game details page`
|
||||
6. Set the **Description** to:
|
||||
|
||||
```markdown
|
||||
We want to help people discover more games by showing related games on each game's details page. The design team wants to explore the UX and do some acceptance testing. Our requirements are:
|
||||
|
||||
- Add a data-access helper in `src/lib/` that returns other games in the same category as a given game, excluding that game
|
||||
- Show a "Related games" section on the game details page that uses the helper
|
||||
- Handle the case where a game has no related games
|
||||
- There should be unit tests created for the new helper
|
||||
- Before creating the PR, ensure all tests pass
|
||||
```
|
||||
|
||||
7. Select **Create** to create the issue.
|
||||
8. On the right side, select **Assign to Copilot** to open the assignment dialog.
|
||||
|
||||
|
||||
|
||||
9. Select **Assign**.
|
||||
|
||||
Shortly after, you should see a set of 👀 on the first comment in the issue, indicating Copilot is on the job!
|
||||
|
||||
|
||||
|
||||
Copilot is now diligently working on your second request! Copilot cloud agent works in a similar fashion to a SWE, so you don't need to actively monitor it, but instead review once it's completed. Let's turn your attention to creating and using custom agents.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
This lesson explored [GitHub Copilot cloud agent][copilot-agents]. With cloud agent you can assign issues to Copilot to perform asynchronously. You can use Copilot to address tech debt, create new features, or aid in migrating code from one framework to another.
|
||||
|
||||
You explored these concepts:
|
||||
|
||||
- customizing the environment for generating code.
|
||||
- ensuring operations are performed securely.
|
||||
- the importance of clearly scoped issues.
|
||||
- assigning issues to Copilot.
|
||||
|
||||
With cloud agent working diligently in the background, we can now turn our attention to creating and using custom agents. [Copilot cloud agent can also use MCP servers][cloud-agent-mcp], and has custom instructions available to it, which we explored in earlier modules.
|
||||
|
||||
## Resources
|
||||
|
||||
- [About Copilot cloud agent][copilot-agents]
|
||||
- [Assigning GitHub issues to Copilot][assign-issue]
|
||||
- [Copilot cloud agent setup workflow best practices][cloud-agent-best-practices]
|
||||
|
||||
| [Next lesson: Custom agents →][next-lesson] |
|
||||
|--:|
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cloud/1-custom-instructions/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cloud/3-custom-agents/
|
||||
[cloud-agent-mcp]: https://docs.github.com/copilot/how-tos/copilot-on-github/customize-copilot/customize-cloud-agent/extend-cloud-agent-with-mcp
|
||||
[assign-issue]: https://docs.github.com/copilot/how-tos/use-copilot-agents/cloud-agent/start-copilot-sessions
|
||||
[setup-workflow]: https://docs.github.com/copilot/how-tos/copilot-on-github/customize-copilot/customize-cloud-agent/customize-the-agent-environment
|
||||
[copilot-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-cloud-agent
|
||||
[cloud-agent-best-practices]: https://docs.github.com/copilot/how-tos/copilot-on-github/customize-copilot/customize-cloud-agent/customize-the-agent-environment
|
||||
[github-actions]: https://docs.github.com/actions
|
||||
@@ -0,0 +1,103 @@
|
||||
---
|
||||
title: "Exercise 3 - Custom agents"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
## What are custom agents?
|
||||
|
||||
[Custom agents][custom-agents-concept] in GitHub Copilot allow you to create specialized AI assistants tailored to specific tasks or domains within your development workflow. By defining agents through markdown files in the `.github/agents` folder of your repository, you can provide Copilot with focused instructions, best practices, coding patterns, and domain-specific knowledge that guide it to perform particular types of work more effectively. Teams can codify their expertise into reusable agents — an accessibility agent that enforces [WCAG][wcag] compliance, a security agent that follows secure coding practices, or a testing agent that maintains consistent test patterns.
|
||||
|
||||
Custom agents are defined by markdown files in the `.github/agents` folder of your project, or globally in `~/.copilot/agents`. Each file has YAML frontmatter with at least a `name` and `description`, followed by a markdown prompt that defines the agent's behavior, expertise, and instructions.
|
||||
|
||||
### Custom agents compared with agent skills
|
||||
|
||||
There's some logical overlap between custom agents and [agent skills][agent-skills-concept]. Both are primarily defined with markdown files and tell an AI how to perform operations. The cleanest way to separate them: a **custom agent** is the worker, and **skills** are tools.
|
||||
|
||||
Custom agents have their own context window and are built to orchestrate skills (and even other agents) as part of doing their work. In this lab, the accessibility custom agent reviews and updates the site against accessibility guidelines; as part of that work it could call skills such as a pull-request workflow skill or one that runs and manages tests.
|
||||
|
||||
> [!NOTE]
|
||||
> There's no single "right" way to author a custom agent. As with anything in AI, test and iterate to find what works for your environments and scenarios.
|
||||
|
||||
[custom-agents-concept]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[agent-skills-concept]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[wcag]: https://www.w3.org/WAI/standards-guidelines/wcag/
|
||||
You'll explore the following with custom agents:
|
||||
|
||||
- how custom agents are defined.
|
||||
- assigning a task to a custom agent.
|
||||
|
||||
## Scenario
|
||||
|
||||
Tailspin Toys is committed to ensuring their crowdfunding platform is accessible to all users, regardless of their visual abilities or preferences. Recent user feedback has highlighted that some users find the current dark theme difficult to read due to insufficient contrast between text and background colors. To address this accessibility concern, the design team has requested the implementation of a high-contrast mode that users can toggle on and off.
|
||||
|
||||
Because accessibility is critical, you want to ensure this is implemented as quickly as possible. You're going to utilize a custom agent to generate the functionality.
|
||||
## Reviewing the accessibility custom agent
|
||||
|
||||
A custom agent has already been created for you for accessibility. Let's review the contents to understand how it will guide Copilot.
|
||||
|
||||
Return to your codespace, then review the accessibility custom agent file:
|
||||
|
||||
1. Open `.github/agents/accessibility.md`.
|
||||
2. Note the YAML frontmatter with the `name` and `description` fields.
|
||||
|
||||
> [!CAUTION]
|
||||
> The frontmatter with `name` and `description` is required for custom agents.
|
||||
|
||||
3. From there, scan and review the next sections which highlight:
|
||||
- Core responsibilities when generating code for an accessible website.
|
||||
- Best practices for accessibility.
|
||||
- Code examples for HTML, CSS, and JavaScript.
|
||||
- A list of common pitfalls and mistakes.
|
||||
## Create and assign an issue
|
||||
|
||||
Mission control is the central location for working with all agents for your environment. You can assign tasks to Copilot cloud agent, monitor tasks, and even redirect and provide additional guidance. Let's start by assigning a task to create the high contrast mode to Copilot.
|
||||
|
||||
1. Navigate to your repository.
|
||||
2. Select the issues tab.
|
||||
3. Select **New issue** to open the new issue dialog.
|
||||
4. Select **Blank issue** to create the new issue.
|
||||
5. Set the **Title** to `Add high contrast mode to website`.
|
||||
6. Set the **Description** to:
|
||||
|
||||
```plaintext
|
||||
We need a high contrast mode for the site. There should be a toggle for high contrast which the user can set. It should store the setting in local storage on the browser.
|
||||
```
|
||||
|
||||
7. Select **Create** to create the issue.
|
||||
8. On the right side, select **Assign to Copilot** to open the assignment dialog.
|
||||
9. Select **Accessibility agent** from the list of custom agents.
|
||||
|
||||
|
||||
|
||||
10. Select **Assign**.
|
||||
11. Copilot gets to work on the task in the background!
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
This lesson explored [custom agents][custom-agents] in GitHub Copilot, specialized AI assistants tailored to specific tasks and domains. With custom agents you can codify your team's expertise and standards into reusable agents that guide Copilot to perform particular types of work more effectively.
|
||||
|
||||
You explored these concepts:
|
||||
|
||||
- how custom agents are defined.
|
||||
- assigning a task to a custom agent.
|
||||
|
||||
With Copilot working on implementing the high contrast mode, we can now turn our attention to [monitoring and steering the agent session][next-lesson] from mission control.
|
||||
|
||||
## Resources
|
||||
|
||||
- [About custom agents][custom-agents]
|
||||
- [Preparing to use custom agents in your organization][org-custom-agents]
|
||||
- [Preparing to use custom agents in your enterprise][enterprise-custom-agents]
|
||||
|
||||
---
|
||||
|
||||
| [← Previous lesson: GitHub Copilot cloud agent][previous-lesson] | [Next lesson: Monitoring and managing agents →][next-lesson] |
|
||||
|:--|--:|
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cloud/2-cloud-agent/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cloud/4-managing-agents/
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[org-custom-agents]: https://docs.github.com/copilot/how-tos/administer-copilot/manage-for-organization/prepare-for-custom-agents
|
||||
[enterprise-custom-agents]: https://docs.github.com/copilot/how-tos/administer-copilot/manage-for-enterprise/manage-agents/prepare-for-custom-agents
|
||||
@@ -0,0 +1,91 @@
|
||||
---
|
||||
title: "Exercise 4 - Monitoring and managing agents"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
In the last couple of exercises you asked Copilot cloud agent to take on three separate tasks focused on improving the user experience and adding functionality. While cloud agent is built to operate asynchronously and autonomously, the ability to monitor these tasks is still important.
|
||||
|
||||
There are numerous tools available to you to manage tasks assigned to cloud agent, including [the agents page][agents-page] on GitHub.com. From this mission control you can see all agent tasks with open pull requests (PRs). You can explore the operations performed, and even steer an in-progress session to help guide it.
|
||||
|
||||
In this lesson you will:
|
||||
|
||||
- explore the agents page to monitor cloud agent tasks.
|
||||
- steer an in-flight session to request additional functionality.
|
||||
|
||||
## Scenario
|
||||
|
||||
After assigning the agent to create a high-contrast mode, the team realized it would be a good time to add a light mode as well. Since work was already being done to update the style of the site and add toggle functionality, it seemed logical to include this functionality. You want to steer the agent's work to ensure it adds a light mode as well as high contrast.
|
||||
|
||||
## Review Copilot cloud agent tasks
|
||||
|
||||
Let's see the current status of all tasks assigned to Copilot cloud agent.
|
||||
|
||||
1. Navigate to the agents page at [https://github.com/copilot/agents](https://github.com/copilot/agents).
|
||||
2. Note the list of tasks, both on the main pane and on the left pane. You should see the list of the tasks you've assigned to Copilot, including:
|
||||
- Updating documentation for your codebase.
|
||||
- Generating APIs for modifying games.
|
||||
- Adding a high contrast mode for the website.
|
||||
3. Select one of the running tasks. Review the tasks which have been performed by Copilot. These can include:
|
||||
- Checking out the code from the repository.
|
||||
- Creating the environment for Copilot to work.
|
||||
- Setting up MCP servers.
|
||||
- Performing various steps to complete the assigned task.
|
||||
|
||||
> [!NOTE]
|
||||
> The exact steps listed will vary depending on the state of Copilot's work and the approach it took.
|
||||
|
||||
4. Also note the pull request (PR) pane which appears on the right side. This allows you to see the PR and files changed for additional monitoring.
|
||||
|
||||
## Steering cloud agent
|
||||
|
||||
Now that you've seen the tasks which are active, let's request Copilot include the light mode toggle while it works on the high-contrast mode.
|
||||
|
||||
1. Select the session which refers to adding a high contrast mode. The exact title will vary depending on the name Copilot uses and the current state of work.
|
||||
|
||||
|
||||
|
||||
2. Watch the session for a few minutes, until it indicates it's completed the setup and begun its work. You'll know this has happened when you start seeing messages similar to the ones below.
|
||||
3. In the **Steer active session while Copilot is working** dialog, add the following prompt:
|
||||
|
||||
```
|
||||
While we are working on a high contrast mode, let's also add a light mode. There should be a switch for this mode as well where users can select their desired display mode.
|
||||
```
|
||||
|
||||
|
||||
|
||||
4. Press <kbd>Enter</kbd> to send the prompt.
|
||||
5. Notice how Copilot acknowledges the prompt and includes it in its flow.
|
||||
|
||||
## Let Copilot do its work
|
||||
|
||||
Just like before, Copilot will get to work on the updated task! It will incorporate the new request into its flow after it completes the particular step it's working on when you sent the message.
|
||||
|
||||
As before, this will take several minutes, so it's a good time to pause and reflect on everything you've learned and explored thus far.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
This lesson explored the Copilot agents page, your central hub for monitoring and guiding GitHub Copilot cloud agent tasks. With this mission control you can track all active and completed tasks, review the work being performed, and even redirect in-flight tasks to adjust scope or provide additional guidance.
|
||||
|
||||
You explored these concepts:
|
||||
|
||||
- explored mission control and the agents page to monitor cloud agent tasks.
|
||||
- redirected an in-flight session to request additional functionality.
|
||||
|
||||
With Copilot completing its work on the accessibility features, we can now turn our attention to [iterating on the pull requests Copilot created][next-lesson].
|
||||
|
||||
## Resources
|
||||
|
||||
- [Copilot agents page][agents-page]
|
||||
- [About custom agents][custom-agents]
|
||||
|
||||
---
|
||||
|
||||
| [← Previous lesson: Custom agents][previous-lesson] | [Next lesson: Iterating on Copilot's work →][next-lesson] |
|
||||
|:--|--:|
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cloud/3-custom-agents/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/cloud/5-iterating/
|
||||
[agents-page]: https://github.blog/changelog/2025-07-03-agents-page-for-copilot-coding-agent-in-public-preview
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
@@ -0,0 +1,187 @@
|
||||
---
|
||||
title: "Exercise 5: Iterating on GitHub Copilot's work"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
| [← Previous lesson: Managing agents][previous-lesson] |
|
||||
|:--|
|
||||
|
||||
## Reviewing the work
|
||||
|
||||
Throughout this lab you've worked with GitHub Copilot on several tasks focused on improving the user experience and adding functionality. You asked Copilot to add documentation to your code, build a related games feature for the design team to iterate on, and implement accessibility features including high-contrast and light mode toggles. Let's explore the code changes and, if necessary, provide feedback to Copilot to improve its work.
|
||||
|
||||
### Scenario
|
||||
|
||||
As has been highlighted numerous times, the fundamentals of software design and DevOps do not change with the addition of generative AI. We always want to review the code generated, and work through our normal DevOps process. With that in mind, let's review the suggestions from GitHub Copilot for creating the documentation, the related games feature, and accessibility features before we turn on review for the rest of our team.
|
||||
## Security and GitHub Copilot cloud agent
|
||||
|
||||
Because Copilot cloud agent performs its tasks asynchronously and without supervision, certain security constraints have been put in place to ensure everything remains safe. These include:
|
||||
|
||||
- Copilot only has read access to your repository and write access **only** to the branch it will use for its code.
|
||||
- Cloud agent runs inside of GitHub Actions, where it will create a separate, ephemeral environment in which to work.
|
||||
- Any GitHub Actions workflows require approval from a human before they can be run.
|
||||
- [Access to external resources is limited by default](https://docs.github.com/copilot/how-tos/copilot-on-github/customize-copilot/customize-cloud-agent/customize-the-agent-firewall), including MCP servers.
|
||||
## Reviewing the generated documentation
|
||||
|
||||
Let's start by exploring the first pull request (PR) generated by GitHub Copilot cloud agent - adding documentation to your code. You'll perform this task by utilizing the standard PR interface in GitHub.com.
|
||||
|
||||
> [!NOTE]
|
||||
> When you explore the PR you may notice a warning about GitHub Copilot being blocked by a firewall. This **is expected**, as Copilot has limited access to external resources by default, including calls to external MCP servers. If you wish, you can [customize or disable the firewall for Copilot cloud agent][agent-firewall].
|
||||
|
||||
1. Return to your repository on github.com.
|
||||
2. Select **Pull Requests** to open the list of pull requests.
|
||||
3. Open the pull request titled something similar to **Add missing documentation** or something more robust.
|
||||
|
||||
> [!NOTE]
|
||||
> If Copilot is still working on the task, the pull request will contain the **[WIP]** flag. If so, wait for Copilot to complete the work. This may take a few minutes, so feel free to take a break, or reflect on everything you've learned so far.
|
||||
|
||||
4. Once the pull request is ready, select the **Files changed** tab and review the changes.
|
||||
|
||||
|
||||
|
||||
5. Explore the newly updated code, which includes the newly created TSDoc doc comments and other documentation. The exact changes will vary.
|
||||
|
||||
As you scan the changes, look for TSDoc doc comments, TypeScript conventions, and comment headers. These come from the custom instruction files you reviewed at the start of Exercise 2.
|
||||
|
||||
6. Once you've reviewed the updates and everything looks good, navigate back to the **Conversation** tab and scroll down.
|
||||
7. You should see an indicator that some workflows are waiting for approval.
|
||||
8. If workflows are waiting for approval, select **Approve and run workflows**.
|
||||
|
||||
|
||||
9. You should see the workflows get queued in the checks section of the pull request. All being well, you should see that the project checks pass for the single Astro app. This may take a few minutes to complete.
|
||||
|
||||
## Requesting changes from GitHub Copilot
|
||||
|
||||
Working with Copilot on a pull request is not just a one-way street. You can also tag Copilot in comments - like you would other members of your team - in the pull request, or inline comments of the code. Copilot will see these comments, and trigger another session to address them. Due to the non-deterministic results, we can't give prescriptive text of what to ask for. Some ideas of what to ask Copilot to update include:
|
||||
|
||||
- Add comment headers to the top of each code file with a brief description of what they do.
|
||||
- Add TSDoc doc comments to TypeScript and Astro files.
|
||||
- Create a README with a description of the Astro app structure.
|
||||
|
||||
1. Add a comment requesting a change to the generated documentation, tagging **@copilot** like you would any user. Use one of the ideas above, or another suggestion for Copilot around documentation you'd like to see in the codebase.
|
||||
2. Select **View Session** to watch Copilot perform its work. Notice how Copilot starts a new session to make the updates.
|
||||
3. You can select **Back to pull request** to return to the pull request.
|
||||
|
||||
|
||||
|
||||
4. Once Copilot has completed the changes, you should see a new commit in the pull request.
|
||||
5. Select the **Files changed** tab to review the changes.
|
||||
|
||||
Feel free to continue iterating until you are happy. Once happy, you can convert the PR to ready from a draft, and merge it into the main branch.
|
||||
|
||||
|
||||
|
||||
## Review the related games feature
|
||||
|
||||
Let's return to the PR Copilot generated for resolving our issue about showing related games on the game details page.
|
||||
|
||||
1. Return to your repository in GitHub.com.
|
||||
2. Select the **Pull Requests** tab.
|
||||
3. Select the PR which has a title similar to **Show related games on the game details page** or something more robust.
|
||||
4. Select the **Files changed** tab to review the code it generated.
|
||||
5. Once you've reviewed the updates and everything looks good, navigate back to the **Conversation** tab and scroll down.
|
||||
6. You should see an indicator that some workflows are waiting for approval.
|
||||
7. If workflows are waiting for approval, select **Approve and run workflows**.
|
||||
|
||||
|
||||
8. You should see the workflows get queued in the checks section of the pull request. All being well, you should see that the project checks pass for the single Astro app. This may take a few minutes to complete.
|
||||
9. **Optional:** You could even switch to this branch in your Codespace to perform a manual test of the related games feature. Navigate to your Codespace, open the terminal, and run the following commands (replace `<branch-name>` with the name of the branch Copilot created, e.g. **copilot/fix-8**.):
|
||||
|
||||
```bash
|
||||
git fetch origin
|
||||
git checkout <branch-name>
|
||||
```
|
||||
|
||||
Copilot has built the related games feature! Just as before, you can work iteratively with Copilot cloud agent to request updates. For example, you might want to request Copilot tweak how many related games are shown, or ensuring comment headers and TSDoc doc comments are added (remember - this was assigned **before** you made the updates to your custom instructions!) Just like before, you can make these requests by adding a new comment on the **Conversation** tab, which Copilot will see and kickoff a new session.
|
||||
|
||||
## Review the accessibility features
|
||||
|
||||
Finally, let's review the accessibility features that were implemented using the custom accessibility agent. This PR should include both the high-contrast mode you assigned in Exercise 3, and the light mode that was requested in mission control in Exercise 4.
|
||||
|
||||
1. Return to your repository in GitHub.com.
|
||||
2. Select the **Pull Requests** tab.
|
||||
3. Select the PR which has a title similar to **Add high contrast mode to website** or something more robust.
|
||||
|
||||
> [!NOTE]
|
||||
> If Copilot is still working on the task, the pull request will contain the **[WIP]** flag. If so, wait for Copilot to complete the work. This may take a few minutes.
|
||||
|
||||
4. Select the **Files changed** tab to review the code it generated.
|
||||
5. Review the implementation, paying particular attention to:
|
||||
- The toggle UI components for switching between modes
|
||||
- The use of local storage to persist user preferences
|
||||
- The CSS or styling changes for high-contrast and light modes
|
||||
- The accessibility attributes (ARIA labels, keyboard navigation, etc.)
|
||||
- Any JavaScript/TypeScript code that manages the mode switching
|
||||
|
||||
6. Once you've reviewed the updates and everything looks good, navigate back to the **Conversation** tab and scroll down.
|
||||
7. You should see an indicator that some workflows are waiting for approval.
|
||||
8. If workflows are waiting for approval, select **Approve and run workflows**.
|
||||
|
||||
|
||||
9. You should see the workflows get queued in the checks section of the pull request. All being well, you should see that the project checks pass for the single Astro app. This may take a few minutes to complete.
|
||||
10. **Optional:** You could switch to this branch in your Codespace to manually test the accessibility features. Navigate to your Codespace, open the terminal, and run the following commands (replace `<branch-name>` with the name of the branch Copilot created):
|
||||
|
||||
```bash
|
||||
git fetch origin
|
||||
git checkout <branch-name>
|
||||
```
|
||||
|
||||
Then start the application and test the high-contrast and light mode toggles in your browser to ensure they work as expected and persist across page reloads.
|
||||
|
||||
Notice how the custom accessibility agent helped guide Copilot to implement these features following accessibility best practices. If you see any accessibility concerns or improvements, you can tag **@copilot** in a comment to request updates, just like you did with the previous PRs.
|
||||
|
||||
## Optional exercise — keep delegating
|
||||
|
||||
Cloud agent works best when you can hand it real backlog items and turn your attention elsewhere. To build the habit, file a few more issues against your repository and assign them to Copilot. Some ideas:
|
||||
|
||||
- Create a backer interest form on the game details page.
|
||||
- Implement pagination on the game list page.
|
||||
- Add input validation and error handling to the data-access helpers.
|
||||
|
||||
## Summary
|
||||
|
||||
You completed the Cloud agent harness. Across these lessons you:
|
||||
|
||||
- **Inspected the custom instruction files this repo ships with** so you could see their effect in cloud agent's output later.
|
||||
- **Assigned issues to Copilot cloud agent** and watched it set up its environment, plan, and execute asynchronously.
|
||||
- **Created and used a custom agent** for accessibility, adding high-contrast and light-mode toggles.
|
||||
- **Used the Copilot agents page as mission control** to monitor and steer the accessibility session mid-flight.
|
||||
- **Reviewed and iterated on cloud agent's pull requests**, tagging `@copilot` to request changes and approving workflows.
|
||||
|
||||
## Review and next steps
|
||||
|
||||
You've completed the Cloud agent harness. If you'd like to keep exploring, the other harnesses complement what you practiced here:
|
||||
|
||||
- 🖥️ **[VS Code harness](/learning-hub/copilot-workshops/vscode/)** — explore Copilot Chat agent mode and MCP integration directly from your IDE.
|
||||
- 💻 **[CLI harness](/learning-hub/copilot-workshops/cli/)** — work the same flows from your terminal with Copilot CLI: plan mode, agent skills, custom agents, and slash commands like `/delegate` to bridge back to the cloud agent you used here.
|
||||
|
||||
In your own repository, try these follow-up ideas:
|
||||
|
||||
- Assign a refactoring or test-coverage issue to cloud agent.
|
||||
- Create a custom agent for another domain.
|
||||
- Set up `copilot-setup-steps.yml` for a different stack.
|
||||
|
||||
## Resources
|
||||
|
||||
- [GitHub Copilot][github-copilot]
|
||||
- [About Copilot agents][copilot-agents]
|
||||
- [Assigning GitHub issues to Copilot][assign-issue]
|
||||
- [Copilot cloud agent setup workflow best practices][cloud-agent-best-practices]
|
||||
- [Configuring Copilot cloud agent firewall][agent-firewall]
|
||||
|
||||
---
|
||||
|
||||
| [← Previous lesson: Managing agents][previous-lesson] |
|
||||
|:--|
|
||||
|
||||
[github-copilot]: https://github.com/features/copilot
|
||||
[cloud-agent-overview]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-cloud-agent
|
||||
[assign-issue]: https://docs.github.com/copilot/how-tos/use-copilot-agents/cloud-agent/start-copilot-sessions
|
||||
[setup-workflow]: https://docs.github.com/copilot/how-tos/copilot-on-github/customize-copilot/customize-cloud-agent/customize-the-agent-environment
|
||||
[copilot-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-cloud-agent
|
||||
[cloud-agent-best-practices]: https://docs.github.com/copilot/how-tos/copilot-on-github/customize-copilot/customize-cloud-agent/customize-the-agent-environment
|
||||
[agent-firewall]: https://docs.github.com/copilot/how-tos/copilot-on-github/customize-copilot/customize-cloud-agent/customize-the-agent-firewall
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/cloud/4-managing-agents/
|
||||
@@ -0,0 +1,50 @@
|
||||
---
|
||||
title: "Copilot cloud agent"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
**[GitHub Copilot cloud agent](https://docs.github.com/copilot/concepts/agents/cloud-agent/about-cloud-agent)** lets GitHub Copilot work asynchronously in the cloud. You assign work on GitHub, and the cloud agent picks it up in the background — exploring the repository, making changes, and opening a pull request — while you stay free to do other things.
|
||||
|
||||
Across these exercises you'll add custom instructions the cloud agent will follow, then assign a GitHub issue and let it implement the work. You'll review and use custom agents to shape its approach, monitor and steer sessions from the agents dashboard, and finish by reviewing its pull requests and iterating on the results.
|
||||
|
||||
## Exercises
|
||||
|
||||
| Exercise | Topic | Description |
|
||||
|----------|-------|-------------|
|
||||
| [0. Prerequisites][ex0] | Setup | Create your repository and codespace |
|
||||
| [1. Custom instructions][ex1] | Context | Add custom instructions cloud agent will follow |
|
||||
| [2. Cloud Agent][ex2] | Async Agent | Assign issues to Copilot cloud agent |
|
||||
| [3. Custom Agents][ex3] | Specialized Agents | Review and use custom agents |
|
||||
| [4. Managing Agents][ex4] | Monitoring | Monitor and steer agent sessions |
|
||||
| [5. Iterating][ex5] | Review | Review PRs, iterate on Copilot's work, and choose next steps |
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before attending this workshop, please ensure you have:
|
||||
|
||||
- [ ] A GitHub account with an active **Copilot Student, Pro, Pro+, Business, or Enterprise** plan
|
||||
- [ ] Copilot cloud agent enabled for your account or organization
|
||||
|
||||
> [!TIP]
|
||||
> No paid plan? Verified students can get GitHub Copilot for free through [GitHub Education][callout-student-plan-education]. The **Copilot Student** plan includes the agent, MCP, code review, and Copilot CLI features this workshop uses — so you can complete every harness with it.
|
||||
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
|
||||
> [!NOTE]
|
||||
> Cloud agent is available on **Copilot Student, Pro, Pro+, Business, and Enterprise** — every plan except Copilot Free. On Copilot Business or Enterprise, an administrator must enable it for your organization.
|
||||
|
||||
> [!NOTE]
|
||||
> MCP isn't covered in this harness. To explore using MCP servers with Copilot, see the [CLI harness](/learning-hub/copilot-workshops/cli/) or the [VS Code harness](/learning-hub/copilot-workshops/vscode/).
|
||||
|
||||
## Get Started
|
||||
|
||||
**[Start with Exercise 0: Prerequisites →][ex0]**
|
||||
|
||||
[ex0]: /learning-hub/copilot-workshops/cloud/0-prerequisites/
|
||||
[ex1]: /learning-hub/copilot-workshops/cloud/1-custom-instructions/
|
||||
[ex2]: /learning-hub/copilot-workshops/cloud/2-cloud-agent/
|
||||
[ex3]: /learning-hub/copilot-workshops/cloud/3-custom-agents/
|
||||
[ex4]: /learning-hub/copilot-workshops/cloud/4-managing-agents/
|
||||
[ex5]: /learning-hub/copilot-workshops/cloud/5-iterating/
|
||||
@@ -0,0 +1,41 @@
|
||||
---
|
||||
title: "Hands-on with GitHub Copilot's agents"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
The recent additions to the capabilities of GitHub Copilot provide powerful tools to the developer across the entire software development lifecycle (SDLC). This includes working with issues and pull requests on GitHub, interacting with external services, and of course code creation. This lab explores the functionality, providing real-world use cases and tips on how to get the most out of the tools.
|
||||
|
||||
> [!CAUTION]
|
||||
> Because GitHub Copilot is probabilistic rather than deterministic, the exact code, files changed, etc., may vary. As a result, you may notice slight differences between screenshots and code snippets in the lab and your experience. This is to be expected, and is just the nature of working with this class of tools.
|
||||
>
|
||||
> If something appears broken or isn't running correctly, please ask a mentor!
|
||||
|
||||
## Choose your harness
|
||||
|
||||
GitHub Copilot meets you wherever you work. Pick the harness that matches how you want to build, and work through its exercises against a shared Tailspin Toys backlog. Each harness starts with its own setup, so you can dive straight into the one you choose.
|
||||
|
||||
### 🖥️ [VS Code](/learning-hub/copilot-workshops/vscode/)
|
||||
|
||||
GitHub Copilot inside **Visual Studio Code** and GitHub Codespaces. Work with Copilot Chat agent mode, MCP servers, and custom agents without leaving the editor you already use — ideal when you want AI assistance woven directly into your IDE.
|
||||
|
||||
### 💻 [Copilot CLI](/learning-hub/copilot-workshops/cli/)
|
||||
|
||||
**GitHub Copilot CLI** — an agentic assistant that runs in your terminal. Install it, connect MCP servers, generate code with plan mode, and build your own skills, custom agents, and slash commands, all from the command line.
|
||||
|
||||
### 🤖 [Copilot App](/learning-hub/copilot-workshops/app/)
|
||||
|
||||
The **GitHub Copilot app** — a desktop application built on Copilot CLI. Run parallel agent sessions, switch session modes, collaborate on canvases, and manage GitHub issues and pull requests natively — including **Agent Merge**, which shepherds a pull request through rebases, review feedback, CI fixes, and merge.
|
||||
|
||||
### ☁️ [Copilot Cloud Agent](/learning-hub/copilot-workshops/cloud/)
|
||||
|
||||
**Copilot cloud agent** — an asynchronous peer programmer that works on GitHub issues in the background. Assign work, guide it with custom agents, monitor progress from the agents dashboard, and review the pull requests it opens.
|
||||
|
||||
## Scenario
|
||||
|
||||
You are a new developer for Tailspin Toys, a fictional company who provides crowdfunding for board games with a developer theme - a huge market! Your team's backlog is already filed as GitHub issues, ready for you to pick up — feature work (like filtering and pagination) alongside quality improvements (like accessibility and coding standards). You'll work iteratively, exploring both the site and Copilot's capabilities, to complete the tasks.
|
||||
|
||||
## Get started
|
||||
|
||||
Choose your harness above to begin — each one opens with the setup it needs to get you building.
|
||||
@@ -0,0 +1,89 @@
|
||||
---
|
||||
title: "Exercise 0: Prerequisites"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Before you start the VS Code exercises, you need to get everything ready. You'll create your own copy of the Tailspin Toys repository, spin up a [codespace][codespaces] to work in, and confirm GitHub Copilot Chat is up and running in your editor.
|
||||
|
||||
## Setting up the lab repository
|
||||
|
||||
To create a copy of the repository for the code you'll create, you'll make an instance from the [template][template-repository]. The new instance will contain all of the necessary files for the lab, and you'll use it as you work through the exercises.
|
||||
|
||||
1. In a new browser window, navigate to the GitHub repository for this lab: `https://github.com/github-samples/tailspin-toys`.
|
||||
2. Create your own copy of the repository by selecting the **Use this template** button on the lab repository page. Then select **Create a new repository**.
|
||||
|
||||
|
||||
|
||||
3. If you are completing the workshop as part of an event being led by GitHub or Microsoft, follow the instructions provided by the mentors. Otherwise, you can create the new repository in an organization where you have access to GitHub Copilot.
|
||||
|
||||
|
||||
|
||||
4. Make a note of the repository path you created (**organization-or-user-name/repository-name**), as you will be referring to this later in the lab.
|
||||
|
||||
> [!NOTE]
|
||||
> **Your backlog is ready**
|
||||
>
|
||||
> When you create your repository from the template, a backlog of GitHub issues is created for you automatically. You'll work from these issues throughout the workshop — there's nothing to file yourself.
|
||||
## Creating a codespace
|
||||
|
||||
Next up, you'll use a codespace to complete the lab exercises.
|
||||
|
||||
[GitHub Codespaces][codespaces] are a cloud-based development environment that allows you to write, run, and debug code directly in your browser. It provides a fully-featured IDE with support for multiple programming languages, extensions, and tools.
|
||||
|
||||
1. Navigate to your newly created repository.
|
||||
2. Select the green **Code** button.
|
||||
|
||||
|
||||
|
||||
3. Select the **Codespaces** tab and select the **+** button to create a new Codespace.
|
||||
|
||||
|
||||
|
||||
The creation of the codespace will take several minutes, although it's still far quicker than having to manually install all the services! That said, you can use this time to explore other features of GitHub Copilot, which we'll turn your attention to next.
|
||||
|
||||
> [!CAUTION]
|
||||
> You'll return to the codespace in a future exercise. For the time being, leave it open in a tab in your browser.
|
||||
|
||||
> [!NOTE]
|
||||
> This workshop is built to run inside a codespace or local [dev container][dev-containers]. Both ensure the environment has all the necessary prerequisites installed for a smooth experience. If you'd prefer to run it locally, open the cloned repository in VS Code and select **Reopen in Container** when prompted — VS Code will build the same dev container the codespace uses.
|
||||
|
||||
[codespaces]: https://github.com/features/codespaces
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
## Using GitHub Copilot Chat and agent mode
|
||||
|
||||
To access GitHub Copilot Chat agent mode, you need to have the GitHub Copilot Chat extension installed in your IDE, which should already be the case if you are using a GitHub Codespace.
|
||||
|
||||
> [!TIP]
|
||||
> If you do not have the GitHub Copilot Chat extension installed, you can [install it from the Visual Studio Code Marketplace][copilot-chat-extension]. Or open the Extensions view in Visual Studio Code, search for **GitHub Copilot Chat**, and select **Install**.
|
||||
|
||||
Once you have the extension installed, you may need to authenticate with your GitHub account to enable it.
|
||||
|
||||
1. Return to your codespace.
|
||||
2. If you don't already see Copilot Chat on the right side of your editor, select the **Copilot Chat** icon at the top of your codespace.
|
||||
3. Type a message like "Hello world" in the Copilot Chat window and press enter. This should activate Copilot Chat.
|
||||
4. Alternatively, if you are not authenticated you will be prompted to sign in to your GitHub account. Follow the instructions to authenticate.
|
||||
|
||||
|
||||
|
||||
5. After authentication, you should see the Copilot Chat window appear.
|
||||
|
||||
## Summary
|
||||
|
||||
Congratulations, you have created a copy of the lab repository! You also began the creation process of your codespace, which you'll use when you begin writing code.
|
||||
|
||||
## Next step
|
||||
|
||||
Let's start putting Copilot to work. Continue to [Exercise 1 - Custom instructions][next-lesson], where you'll teach Copilot your project's conventions.
|
||||
|
||||
## Resources
|
||||
|
||||
- [GitHub Codespaces overview][codespaces]
|
||||
- [Creating a repository from a template][template-repository]
|
||||
- [Getting started with Codespaces][codespaces-quickstart]
|
||||
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[codespaces-quickstart]: https://docs.github.com/codespaces/getting-started/quickstart
|
||||
[copilot-chat-extension]: https://marketplace.visualstudio.com/items?itemName=GitHub.copilot-chat
|
||||
[next-lesson]: /learning-hub/copilot-workshops/vscode/1-custom-instructions/
|
||||
+250
@@ -0,0 +1,250 @@
|
||||
---
|
||||
title: "Exercise 1 - Custom instructions (VS Code)"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[← Previous lesson: Prerequisites][previous-lesson] · [Next lesson: Agent mode →][next-lesson]
|
||||
|
||||
Context is key when working with generative AI. If a task needs to be done a particular way — or there's background information Copilot should know — you want to make sure that context is reachable. There are several ways to share specific context with Copilot. Key among these is [instruction files][instruction-files], which are how you provide that guidance about code generation.
|
||||
|
||||
In this exercise, you will:
|
||||
|
||||
- explore how project-specific context, coding guidelines, and documentation standards reach Copilot through repository custom instructions and path-scoped instruction files,
|
||||
- generate the first data slice for filtering (a publishers helper) with the *current* instructions in place,
|
||||
- add a new repository-wide standard to `.github/copilot-instructions.md`,
|
||||
- re-run the same prompt and watch the generated code adopt the new standard,
|
||||
- commit the instructions update and filtering slice to `main` so Copilot can use the updated guidance in the next exercise.
|
||||
|
||||
> [!CAUTION]
|
||||
> Generated code may diverge from some of the standards you set. Copilot is non-deterministic. The point of this exercise is to see the *trend* in behavior change after updating the instructions, not to match output character-for-character.
|
||||
|
||||
## Instruction files
|
||||
|
||||
### Scenario
|
||||
|
||||
As any good dev shop, Tailspin Toys has a set of guidelines and requirements for development practices. These include:
|
||||
|
||||
- The data layer always needs unit tests.
|
||||
- UI should be in dark mode and have a modern feel.
|
||||
- Documentation should be added to code in the form of TSDoc doc comments.
|
||||
- A block of comments should be added to the head of each file describing what the file does.
|
||||
|
||||
Through the use of instruction files you'll ensure Copilot has the right information to perform the tasks in alignment with the practices highlighted.
|
||||
|
||||
### Custom instructions
|
||||
|
||||
Custom instructions allow you to provide context and preferences to Copilot, so that it can better understand your coding style and requirements. This is a powerful feature that can help you steer Copilot to get more relevant suggestions and code snippets. You can specify your preferred coding conventions, libraries, and even the types of comments you like to include in your code. You can create instructions for your entire repository, or for specific types of files for task-level context.
|
||||
|
||||
There are two types of instructions files:
|
||||
|
||||
- `.github/copilot-instructions.md`, a single instruction file sent to Copilot for **every** request for the repository. This file should contain project-level information — context relevant for most chat or CLI requests sent to Copilot. This could include the tech stack being used, an overview of what's being built, best practices, and other global guidance.
|
||||
- `.github/instructions/*.instructions.md` files can be created for specific tasks or file types. You can use them to provide guidelines for particular languages (like TypeScript or Astro), or for tasks like creating a UI component or a new set of unit tests.
|
||||
|
||||
> [!NOTE]
|
||||
> When working in your IDE, instructions files are only used for code generation in Copilot Chat — not for code completions or next-edit suggestions.
|
||||
>
|
||||
> Copilot Chat, Copilot CLI and Copilot cloud agent use both repository-level and `*.instructions.md` files (with `applyTo` front matter) when generating code.
|
||||
>
|
||||
> Finally, Copilot [supports instructions files using other standards][custom-instructions-support], including AGENTS.md and CLAUDE.md files.
|
||||
|
||||
### Best practices for managing instructions files
|
||||
|
||||
A full conversation about creating instructions files is beyond the scope of the workshop. However, the examples provided in the sample project show a representative approach. At a high level:
|
||||
|
||||
- Keep instructions in `copilot-instructions.md` focused on project-level guidance, such as a description of what's being built, the structure of the project, and global coding standards.
|
||||
- Use `*.instructions.md` files to provide specific instructions for file types (unit tests, Astro components, the data layer), or for specific tasks.
|
||||
- Use natural language. Keep guidance clear. Provide examples of how code should (and shouldn't) look.
|
||||
|
||||
There isn't one specific way to create instructions files, just as there isn't one specific way to use AI. You will find through experimentation what works best for your project.
|
||||
|
||||
> [!TIP]
|
||||
> Every project using GitHub Copilot should have a robust collection of instruction files. As you explore the ones in this project, you may notice there are files for numerous types of tasks, including [UI updates][ui-instructions] and [Astro][astro-instructions].
|
||||
>
|
||||
> Copilot can also help generate instruction files for you. Each surface exposes this differently (for example, **Configure Chat → Generate Agent Instructions** in VS Code, or `/init` in Copilot CLI) — the lesson for the surface you're on will call it out where it's relevant.
|
||||
>
|
||||
> Looking for templates or a starting point? Explore [awesome-copilot][awesome-copilot], a repository full of instruction files, custom agents, and other resources.
|
||||
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[awesome-copilot]: https://github.com/github/awesome-copilot
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
## Explore the custom instructions files in this project
|
||||
|
||||
Take a moment to read the instruction files this repository ships with — there's one core `copilot-instructions.md` and a collection of `*.instructions.md` files for various tasks. Open these in your editor or the GitHub web UI.
|
||||
|
||||
1. Open `.github/copilot-instructions.md`.
|
||||
2. Explore the file, noting the brief description of the project plus sections such as **Agent notes**, **Code standards**, **Scripts**, and **Repository Structure**. Under **Code standards**, note the nested **GitHub Actions Workflows** guidance. These are applicable to any interactions you'd have with Copilot.
|
||||
3. Open the `.github/instructions` folder and look around. Note there are instructions for Astro files, the Drizzle data layer, tests, and more.
|
||||
4. Open `.github/instructions/unit-tests.instructions.md`. Note the `applyTo` field at the top — this sets a glob (relative to the repo root) that determines which files the instructions apply to. Here, any TypeScript test file (for example, one matching `**/*.test.ts`) will match.
|
||||
5. Note the instructions specific to creating unit tests for this project.
|
||||
6. Finally, open `.github/instructions/drizzle.instructions.md` and scroll to the bottom. Note the links to other instruction files (like `unit-tests.instructions.md`) and existing files in the project. This lets you break larger instruction sets into smaller, reusable files, and point Copilot at examples to follow when generating code. (Paths there are relative to the instruction file rather than the repo root.)
|
||||
|
||||
> [!NOTE]
|
||||
> The **Code formatting requirements** section in `copilot-instructions.md` documents the project's coding standards, but it doesn't yet require in-code documentation. In the next steps, you'll add rules for TSDoc doc comments and file comment headers.
|
||||
## Create a branch for our changes
|
||||
|
||||
Let's follow some best practices here and create a branch for our changes.
|
||||
|
||||
1. Return to your codespace from the previous exercise.
|
||||
2. Open a new terminal by selecting <kbd>Ctrl</kbd>+<kbd>`</kbd>.
|
||||
3. Create and switch to a new branch:
|
||||
|
||||
```bash
|
||||
git checkout -b custom-instructions
|
||||
```
|
||||
|
||||
## Use Copilot Chat *before* updating the instructions
|
||||
|
||||
> [!TIP]
|
||||
> **Open Copilot Chat**
|
||||
>
|
||||
> Before you start the exercises below, return to your codespace, open the Copilot Chat panel, and select **New Chat** to start a clean conversation. Mode and model selection vary per exercise — each step calls those out where it matters.
|
||||
To see the impact of custom instructions, start by sending a prompt with the current instruction file in place. Later, you'll update it and re-send the same prompt to see the difference.
|
||||
|
||||
1. Close any open editor tabs from previous exercises so Copilot picks up only the context you want.
|
||||
2. Open `src/lib/publishers.ts` so Copilot knows where the helper should live.
|
||||
3. Select **Agent** from the agents dropdown in the Chat view so Copilot can apply file changes.
|
||||
|
||||
|
||||
|
||||
4. Send the following prompt:
|
||||
|
||||
```plaintext
|
||||
Create or update src/lib/publishers.ts with a data-access helper that returns a list of all publishers with the name and id for each. Apply the file changes.
|
||||
```
|
||||
|
||||
5. Copilot explores the project and applies code updates, often spanning the helper file and its tests.
|
||||
6. Notice the proposed helper is a typed function that takes a `db` client as its first argument and returns a typed array of publishers — that's coming from the data-layer conventions in `.github/instructions/drizzle.instructions.md` (which applies to `src/lib/*.ts`).
|
||||
7. Notice the proposed code **is missing** TSDoc doc comments and a file-level comment header.
|
||||
|
||||
> [!CAUTION]
|
||||
> Because Copilot is probabilistic, there's a chance it'll add doc comments even without being told to. If that happens, that's fine — the *consistency* improvement after the instruction update is still the point.
|
||||
|
||||
## Add a new repository standard
|
||||
|
||||
As highlighted previously, `.github/copilot-instructions.md` is designed to provide project-level information to Copilot. Let's ensure repository coding standards are documented to improve code suggestions.
|
||||
|
||||
1. Re-open `.github/copilot-instructions.md`.
|
||||
2. Locate the **Code formatting requirements** section, which should be near line 27. Note how it documents the project's coding standards — but it has no rule yet for in-code documentation, which is why the generated helper had no doc comments.
|
||||
3. Add the following lines of markdown right below the existing standards to instruct Copilot to add file comment headers and TSDoc doc comments:
|
||||
|
||||
```markdown
|
||||
- Every exported function should have a TSDoc comment describing its purpose, parameters, and return value.
|
||||
- Before imports or any code, add a comment block to the file that explains its purpose.
|
||||
```
|
||||
|
||||
4. Save `copilot-instructions.md`.
|
||||
|
||||
> [!TIP]
|
||||
> As you saw in the previous lesson, instruction files can be created at the repository level (`.github/copilot-instructions.md`) for global guidance, or as `*.instructions.md` files for specific languages, file types, or tasks. The repository-level file is the right home for project-wide standards like the doc comment rule you just added.
|
||||
## Re-run the prompt and observe the change
|
||||
|
||||
1. Return to Copilot Chat and select **New Chat** to clear the buffer.
|
||||
2. Click back into `src/lib/publishers.ts` so Copilot focuses on the right file.
|
||||
3. Send the **same prompt** as before:
|
||||
|
||||
```plaintext
|
||||
Create or update src/lib/publishers.ts with a data-access helper that returns a list of all publishers with the name and id for each. Apply the file changes.
|
||||
```
|
||||
|
||||
4. Notice that the proposed file now opens with a comment block similar to:
|
||||
|
||||
```typescript
|
||||
/**
|
||||
* Publisher data-access helpers for the Tailspin Toys Crowd Funding platform.
|
||||
* Provides functions to retrieve publisher information from the database.
|
||||
*/
|
||||
```
|
||||
|
||||
5. Notice that the proposed function now includes a TSDoc comment similar to:
|
||||
|
||||
```typescript
|
||||
/**
|
||||
* Returns a list of all publishers with their id and name.
|
||||
*
|
||||
* @param db - The Drizzle database client.
|
||||
* @returns A promise that resolves to an array of publisher objects.
|
||||
*/
|
||||
```
|
||||
|
||||
You just steered Copilot to follow a new project standard and apply it to real code that the next exercise will build on.
|
||||
|
||||
## Commit the instructions and push the branch
|
||||
|
||||
Instructions files are just like any asset in the repository, meaning they're managed using the same source control approach you'd take with any other item. So let's commit and push the branch to our repository.
|
||||
|
||||
1. Open a new terminal window in your codespace by selecting <kbd>Ctrl</kbd>+<kbd>\`</kbd>.
|
||||
2. From the terminal, confirm your instructions update and helper changes are present by running:
|
||||
|
||||
```bash
|
||||
git status
|
||||
```
|
||||
|
||||
3. From the terminal, stage and commit the instructions update and every file Copilot changed for the helper foundation:
|
||||
|
||||
```bash
|
||||
git add .github/copilot-instructions.md src/lib/publishers.ts
|
||||
# If git status shows additional supporting updates (for example tests), add those files too.
|
||||
git commit -m "Add doc comment standards and publishers helper foundation"
|
||||
```
|
||||
|
||||
4. From the terminal, push the branch to the repository:
|
||||
|
||||
```bash
|
||||
git push -u origin custom-instructions
|
||||
```
|
||||
|
||||
## Create and merge a pull request
|
||||
|
||||
With our branch pushed, we should create a pull request and tie it to the documentation-standard issue in your backlog. We could manually do that, but Copilot can do it on our behalf using the GitHub tools that are already connected to your project. Let's prompt Copilot to find the issue, create the PR to close the issue, and then merge it.
|
||||
|
||||
> [!NOTE]
|
||||
> This is the first exercise that has Copilot act on GitHub for you. The project template already wires GitHub's tools into your workspace, so there's nothing to set up — the first time Copilot uses one, VS Code may prompt you to sign in to GitHub. Follow the prompts to allow it. You'll learn how this connection works (Model Context Protocol) in a later exercise.
|
||||
|
||||
1. Open Copilot Chat inside of your codespace.
|
||||
2. Select <kbd>Control</kbd>+<kbd>Command</kbd>+<kbd>I</kbd> (Mac) or <kbd>Ctrl</kbd>+<kbd>Alt</kbd>+<kbd>I</kbd> (Windows/Linux) to open the Copilot Chat view, and ensure **Agent** is selected from the agent picker.
|
||||
3. Ask Copilot to find the issue related to updating instructions files and create a PR from the current branch that describes both the instructions updates and the new publishers helper foundation:
|
||||
|
||||
```
|
||||
Find the issue related to updating the instructions file. Create a new PR from the current branch, highlight that the PR closes that issue, and include that we also added the publishers helper foundation for the upcoming filtering work.
|
||||
```
|
||||
|
||||
4. Copilot will begin work on finding the issue and creating the PR.
|
||||
5. As prompted to **Allow** Copilot to perform GitHub actions on your behalf, review the command and select **Allow** as appropriate.
|
||||
6. Once the PR is created, ask Copilot to merge the PR and to return your branch to main by using the following prompt:
|
||||
|
||||
```
|
||||
Merge the PR into main. Then return to main locally, and pull the latest code so we are up to date.
|
||||
```
|
||||
|
||||
7. As prompted to **Allow** Copilot to perform GitHub actions and run shell commands on your behalf, review the command and select **Allow** as appropriate.
|
||||
|
||||
You have now created and merged a pull request with the help of GitHub Copilot!
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You explored how Copilot picks up context from instruction files in this project, then used Copilot Chat in VS Code to:
|
||||
|
||||
- send a code-generation prompt and observe what Copilot produces with the *existing* instructions,
|
||||
- add a new repository-wide standard to `.github/copilot-instructions.md`,
|
||||
- re-run the same prompt and watch the proposed code adopt the new standard,
|
||||
- commit the instructions update and helper foundation to `main` so the next exercise can build on them.
|
||||
|
||||
Next, you'll put those instructions to work in [agent mode][next-lesson] as Copilot adds a new feature across the codebase.
|
||||
|
||||
## Resources
|
||||
|
||||
- [Instruction files for GitHub Copilot customization][instruction-files]
|
||||
- [Best practices for creating custom instructions][instructions-best-practices]
|
||||
- [5 tips for writing better custom instructions for Copilot][copilot-instructions-five-tips]
|
||||
- [Personal custom instructions for GitHub Copilot][personal-instructions]
|
||||
- [Awesome Copilot — a collection of instruction files and other resources][awesome-copilot]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/vscode/0-prerequisites/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/vscode/2-agent-mode/
|
||||
[instruction-files]: https://code.visualstudio.com/docs/copilot/copilot-customization
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[personal-instructions]: https://docs.github.com/copilot/customizing-copilot/adding-personal-custom-instructions-for-github-copilot
|
||||
[copilot-instructions-five-tips]: https://github.blog/ai-and-ml/github-copilot/5-tips-for-writing-better-custom-instructions-for-copilot/
|
||||
@@ -0,0 +1,198 @@
|
||||
---
|
||||
title: "Exercise 2 - Adding new functionality with Copilot Agent Mode"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Even the simplest of updates to an application typically require updates to multiple files and operations to be performed like running tests. As a developer your flow typically involves tracking down all the necessary files, making the changes, running the tests, debugging, figuring out which file was missed, making another update... The list goes on and on.
|
||||
|
||||
This is where Copilot Agent Mode comes into play.
|
||||
|
||||
Copilot Agent Mode is built to act more autonomously in your IDE. It behaves in a similar fashion to a developer, starting by exploring the existing project structure, performing the necessary updates, running tasks like tests, and automatically fixing any discovered mistakes. Let's explore how you can use Agent Mode to introduce new functionality to your site.
|
||||
|
||||
> [!NOTE]
|
||||
> While the names are similar, agent mode and cloud agent are built for two different types of experiences. Agent mode performs its tasks in your IDE, allowing for quick feedback cycles and interaction. Cloud agent is designed as a peer programmer, working asynchronously like a member of the team, interacting with you via issues and pull requests.
|
||||
|
||||
In this exercise, you will learn how:
|
||||
|
||||
- Copilot Agent Mode can explore your project, identify relevant files, and make coordinated changes.
|
||||
- GitHub Copilot Agent Mode can implement new features across the UI and data layer.
|
||||
- to review changes and tests generated by Copilot Agent Mode before merging into your codebase.
|
||||
|
||||
## Scenario
|
||||
|
||||
As the list of games grows, you want to allow users to filter by category and publisher. You already added a publishers helper in the previous exercise, and now you'll finish the remaining data-layer, UI, and test work with Copilot Agent Mode.
|
||||
|
||||
## Running the Tailspin Toys website
|
||||
|
||||
Before you make any changes, let's explore the Tailspin Toys website to understand its current functionality.
|
||||
|
||||
The website is a crowdfunding platform for board games with a developer theme. It allows users to list games and display details about them. The website is a single Astro app that renders its pages as static HTML at build time. Pages query a local SQLite database directly in their frontmatter through Drizzle ORM — there's no separate backend API or client-side UI framework. Reusable data-access helpers live in `src/lib/`, and any interactivity is added with a small, scoped Astro `<script>` using standard DOM APIs.
|
||||
|
||||
### Starting the website
|
||||
|
||||
To make running the website easier, an `npm run dev` task has been provided that starts the single Astro dev server. You can run it in your GitHub Codespace with the following steps:
|
||||
|
||||
1. Return to your codespace. You should be back on `main` after the previous exercise.
|
||||
2. Open a new terminal window inside your codespace by selecting <kbd>Ctrl</kbd> + <kbd>\`</kbd>.
|
||||
3. Create and switch to a new branch for this filtering work:
|
||||
|
||||
```bash
|
||||
git checkout main
|
||||
git pull
|
||||
git checkout -b filtering-vscode
|
||||
```
|
||||
|
||||
4. Run the following command to start the website:
|
||||
|
||||
```bash
|
||||
npm run dev
|
||||
```
|
||||
|
||||
Once the Astro dev server is ready, you should see a banner indicating the URL, similar to the below:
|
||||
|
||||
```bash
|
||||
🚀 Tailspin Toys is ready!
|
||||
Astro server: http://localhost:4321
|
||||
Press Ctrl-C to stop.
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> If a dialog box opens prompting you to open a browser window for `http://localhost:4321` close it by selecting the **x**.
|
||||
|
||||
5. Open the website by holding <kbd>Command</kbd> (Mac) or <kbd>Ctrl</kbd> (Windows/Linux) and selecting the Astro server address `http://localhost:4321` in the terminal.
|
||||
|
||||
> [!NOTE]
|
||||
> When using a codespace, selecting a link for the localhost URL from the Codespace terminal will automatically redirect you to `https://<your-codespace-name>-4321.app.github.dev/`. This is a private tunnel to your codespace, which is now hosting your web server!
|
||||
|
||||
### Exploring the website
|
||||
|
||||
Once the website is running, you can explore its functionality. The main features of the website include:
|
||||
|
||||
- **Home Page**: Displays a list of board games with their titles, images, and descriptions.
|
||||
- **Game Details Page**: When you select a game, you'll be brought to a details page with more information about the game, including its title, description, publisher and category.
|
||||
|
||||
## Explore the backlog with Copilot
|
||||
|
||||
> [!TIP]
|
||||
> **Open Copilot Chat**
|
||||
>
|
||||
> Before you start the exercises below, return to your codespace, open the Copilot Chat panel, and select **New Chat** to start a clean conversation. Mode and model selection vary per exercise — each step calls those out where it matters.
|
||||
The initial implementation of the website is functional, but we want to enhance it by adding new capabilities. Let's start off by reviewing the backlog. When you set up your project from the template, a backlog of issues was created for you automatically — ask GitHub Copilot to show you those items.
|
||||
|
||||
1. Select **Agent** from the agents dropdown in the Chat view. The **Agent** agent autonomously plans and implements changes across files, runs terminal commands, and invokes tools.
|
||||
|
||||
|
||||
|
||||
2. Select **Claude Sonnet 4.5** from the list of available models.
|
||||
|
||||
> [!CAUTION]
|
||||
> The authors of this workshop are not indicating a preference towards one model or another. When building this workshop, we used Claude Sonnet 4.5, and as such are including that in the instructions. The hope is the code suggestions you receive will be relatively consistent to ensure a good experience. However, because LLMs are probabilistic, you may notice the suggestions received differ from what is indicated in the workshop. This is perfectly normal and expected.
|
||||
|
||||
> [!NOTE]
|
||||
> Because of the probabilistic nature of LLMs, Copilot may utilize a different MCP command, but should still be able to complete the task.
|
||||
|
||||
3. Ask Copilot about the backlog of issues by sending the following prompt to Copilot:
|
||||
|
||||
```plaintext
|
||||
Please show me the backlog of items from my GitHub repository. Help me prioritize them based on those which will be most useful to the user.
|
||||
```
|
||||
4. Select **Continue** to run the command to list all issues.
|
||||
5. Review the generated list of issues.
|
||||
|
||||
Notice how Copilot has even prioritized the items for you, based on the ones that it thinks will be most useful to the user.
|
||||
|
||||
## Review instructions files
|
||||
|
||||
Before kicking off the agent to generate the code, it's a good time to review the instructions file you'll use to provide Copilot context for its work. You're going to take advantage of the [user interface (UI)](https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md) file, which contains context on how to approach adding functionality to the website.
|
||||
|
||||
1. In your codespace, navigate to `.github/instructions/ui.instructions.md`.
|
||||
2. Take note of the overall guidance on how to approach adding functionality. This includes:
|
||||
- An overview of the architecture.
|
||||
- Principles for component design, testability and accessibility.
|
||||
- Links to specific instructions files for various file types, including:
|
||||
- Astro
|
||||
- Tailwind CSS
|
||||
- Drizzle
|
||||
|
||||
> [!TIP]
|
||||
> Instructions files allow you to reference both other instructions files and files in your project. The paths are relative to the location of the instructions file. This allows for reuse, breaking down complex instructions into smaller more manageable chunks, and providing examples and templates.
|
||||
|
||||
## Implement the filtering functionality
|
||||
|
||||
To complete filtering, no less than three separate updates will need to be made to the application:
|
||||
|
||||
- Add or refine the remaining filtering logic in the data layer (`src/lib/`)
|
||||
- Add or update tests for filtering behavior
|
||||
- Update the games listing page to introduce the filtering UI
|
||||
|
||||
In addition, the tests need to run (and pass) before you merge everything into your codebase. Copilot Agent Mode can perform these tasks for you! Let's add the functionality.
|
||||
|
||||
1. You can continue in the current conversation with Copilot, or start a new one by selecting **New Chat**.
|
||||
2. Select **Add Context**, **Instructions**, and **ui** as the instructions file.
|
||||
|
||||
|
||||
|
||||
3. Ensure **Agent** is still selected from the agents dropdown in the Chat view.
|
||||
|
||||
|
||||
|
||||
4. Ensure **Claude Sonnet 4.5** is still selected for the model.
|
||||
5. Prompt Copilot to implement the functionality based on the related issue in your backlog by using the following prompt:
|
||||
|
||||
```plaintext
|
||||
Please update the site to include filtering by publisher and category based on the requirements from the related GitHub issue in the backlog. A publishers helper already exists from the previous exercise, so preserve and refine that work as needed while completing the remaining data-layer, UI, and tests. Ensure all tests are passing before completion. The server is already running, so you do not need to start it up.
|
||||
```
|
||||
|
||||
6. Watch as Copilot begins by exploring the project, locating the files associated with the desired functionality. You should see it finding both the data-layer helpers and UI, as well as the tests. It then begins modifying the files and running the tests.
|
||||
|
||||
|
||||
|
||||
> [!NOTE]
|
||||
> You will notice that Copilot will perform several tasks, like exploring the project, modifying files, and running tests. It may take a few minutes depending on the complexity of the task and the codebase. During that process, you may notice **Keep** and **Undo** buttons appear in the code editor. When Copilot is finished, you will have a **Keep** or **Undo** for all of the changes, so you do not need to select them while work is in progress.
|
||||
|
||||
7. As prompted by Copilot, select **Continue** to run the tests.
|
||||
|
||||
|
||||
|
||||
8. You may experience some pauses and even see some tests fail throughout the process. That's okay! Copilot works back and forth between code generation and tests until it completes the task and doesn't detect any errors.
|
||||
|
||||
|
||||
|
||||
9. Explore the generated code for any potential issues.
|
||||
|
||||
> [!CAUTION]
|
||||
> Remember, it's always important to review the code that Copilot or any AI tools generate.
|
||||
|
||||
10. Return to the browser with the website running. Explore the new functionality!
|
||||
11. Once you've confirmed everything works and reviewed the code, select **Keep** in the Copilot Chat window.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
Congratulations! In this exercise, we explored how to use GitHub Copilot Agent Mode to add new capabilities to the Tailspin Toys website. We learned how:
|
||||
|
||||
- GitHub Copilot Agent Mode can implement new features across the UI and data layer.
|
||||
- Copilot Agent Mode can explore your project, identify relevant files, and make coordinated changes.
|
||||
- to review changes and tests generated by Copilot Agent Mode before merging into your codebase.
|
||||
|
||||
Now let's [test your feature with the Playwright MCP server][next-lesson] and open a pull request for it.
|
||||
|
||||
### Bonus exploration exercise – Implement paging
|
||||
|
||||
As the list of games grows there will be a need for paging to be enabled. Using the skills you learned in this exercise, prompt Copilot to update the site to implement paging. Some considerations for the code include:
|
||||
|
||||
- follow the existing best practices, including using the existing instructions files.
|
||||
- consider how you want paging implemented, if you want to allow the user to select the page size or for it to be hard-coded.
|
||||
- as you create the prompt ensure you provide Copilot with the necessary guidance to create the implementation as you desire.
|
||||
- you may need to iterate with GitHub Copilot, asking for changes and providing context. This is the normal flow when working with Copilot!
|
||||
|
||||
## Resources
|
||||
|
||||
- [Copilot ask, edit, and agent modes: What they do and when to use them][choose-mode]
|
||||
- [Agent mode in VS Code][vs-code-agent-mode]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/vscode/1-custom-instructions/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/vscode/3-mcp/
|
||||
[choose-mode]: https://github.blog/ai-and-ml/github-copilot/copilot-ask-edit-and-agent-modes-what-they-do-and-when-to-use-them/
|
||||
[vs-code-agent-mode]: https://code.visualstudio.com/docs/copilot/chat/chat-agent-mode
|
||||
@@ -0,0 +1,173 @@
|
||||
---
|
||||
title: "Exercise 3 - Testing your feature with the Playwright MCP server"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[← Previous lesson: Agent mode][previous-lesson] · [Next lesson: Custom agents →][next-lesson]
|
||||
|
||||
You just built the filtering feature with agent mode. Before you open a pull request, you should confirm it actually works in the browser. Rather than click through the app yourself, you'll connect the **Playwright MCP server** and let Copilot drive a real browser to test the feature for you — then publish your branch and open the PR.
|
||||
|
||||
In this exercise, you will:
|
||||
|
||||
- learn what Model Context Protocol (MCP) is and how MCP servers extend Copilot with new tools,
|
||||
- add the Playwright MCP server to your workspace,
|
||||
- ask Copilot to use it to manually test your filtering feature in a browser,
|
||||
- publish your branch and open a pull request for the filtering work.
|
||||
|
||||
## What is Model Context Protocol (MCP)?
|
||||
|
||||
Agent mode becomes far more powerful when it can reach beyond your editor. Model Context Protocol (MCP) is how Copilot does that — it's a standard way for the agent to talk to external tools and services.
|
||||
|
||||
|
||||
|
||||
[Model Context Protocol (MCP)](https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/) provides AI agents with a way to communicate with external tools and services. By using MCP, AI agents can communicate with external tools and services in real-time. This allows them to access up-to-date information (using resources) and perform actions on your behalf (using tools).
|
||||
|
||||
These tools and resources are accessed through an MCP server, which acts as a bridge between the AI agent and the external tools and services. The MCP server is responsible for managing the communication between the AI agent and the external tools (such as existing APIs or local tools like NPM packages). Each MCP server represents a different set of tools and resources that the AI agent can access.
|
||||
|
||||
A couple of popular existing MCP servers are:
|
||||
|
||||
- **[GitHub MCP Server](https://github.com/github/github-mcp-server)**: This server provides access to a set of APIs for managing your GitHub repositories. It allows the AI agent to perform actions such as creating new repositories, updating existing ones, and managing issues and pull requests.
|
||||
- **[Playwright MCP Server](https://github.com/microsoft/playwright-mcp)**: This server provides browser automation capabilities using Playwright. It allows the AI agent to perform actions such as navigating to web pages, filling out forms, and clicking buttons.
|
||||
|
||||
There are many other MCP servers available that provide access to different tools and resources. GitHub hosts an [MCP registry](https://github.com/mcp) to enhance discoverability and contributions to the ecosystem.
|
||||
|
||||
> [!CAUTION]
|
||||
> With regard to security, treat MCP servers as you would any other dependency in your project. Before using an MCP server, carefully review its source code, verify the publisher, and consider the security implications. Only use MCP servers that you trust and be cautious about granting access to sensitive resources or operations.
|
||||
## Review the MCP configuration
|
||||
|
||||
The `.vscode/mcp.json` file configures the MCP servers available in this VS Code workspace.
|
||||
|
||||
1. Open `.vscode/mcp.json` in your codespace.
|
||||
2. You should see a `github` server already configured for you:
|
||||
|
||||
```json
|
||||
{
|
||||
"servers": {
|
||||
"github": {
|
||||
"type": "http",
|
||||
"url": "https://api.githubcopilot.com/mcp/"
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
This `github` entry ships with the project template, which is why Copilot was able to read your backlog of issues in the previous exercise. It uses the [remote GitHub MCP server][remote-github-mcp-server], so there's nothing to install locally — VS Code connects to it over HTTP and you authenticate with GitHub the first time Copilot uses one of its tools.
|
||||
|
||||
## Add the Playwright MCP server
|
||||
|
||||
Now you'll add a second server. The [Playwright MCP server][playwright-mcp-server] gives Copilot a browser it can control, which is exactly what you need to test your feature.
|
||||
|
||||
1. In `.vscode/mcp.json`, add a `playwright` entry alongside `github` so the file looks like this:
|
||||
|
||||
```json
|
||||
{
|
||||
"servers": {
|
||||
"github": {
|
||||
"type": "http",
|
||||
"url": "https://api.githubcopilot.com/mcp/"
|
||||
},
|
||||
"playwright": {
|
||||
"command": "npx",
|
||||
"args": ["@playwright/mcp@latest", "--headless"]
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
2. Save the file.
|
||||
|
||||
Unlike the remote `github` server, `playwright` is a **local** server: VS Code starts it on your machine by running `npx @playwright/mcp@latest`. The `--headless` flag tells Playwright to run the browser without a visible window, which is required inside a codespace where there's no desktop to display it.
|
||||
|
||||
> [!NOTE]
|
||||
> The Tailspin Toys project already uses Playwright for its end-to-end tests, so the browser Playwright needs is typically already installed. If Copilot later reports that a browser is missing, have it run `npx playwright install chromium` and try again.
|
||||
|
||||
## Start and trust the server
|
||||
|
||||
VS Code starts MCP servers **on demand** — the first time Copilot needs a server's tools, VS Code starts it and asks you to confirm that you trust it.
|
||||
|
||||
1. In `.vscode/mcp.json`, a **Start** action appears above the `playwright` entry. Select it to start the server now and confirm the configuration is correct.
|
||||
2. If VS Code asks you to confirm that you trust the server, review the configuration and choose to trust it so the server can start.
|
||||
|
||||
Starting it by hand is optional — if you skip it, VS Code starts the server (and prompts you to trust it) the first time Copilot needs its tools in the next step.
|
||||
|
||||
## Test the filtering feature
|
||||
|
||||
The [Playwright MCP server][playwright-mcp-server] gives Copilot a real browser to drive. Instead of you clicking through the app to check your work, the agent can open a page, navigate, apply filters, and read the result back to you — then summarize what it saw. It's the fastest way to confirm a feature behaves the way you expect without leaving the conversation.
|
||||
|
||||
Under the hood, the Playwright MCP server works from the page's [accessibility tree][playwright-mcp-server] rather than screenshots. That means the agent reasons over structured, labelled elements (buttons, links, list items) the same way assistive technology does — so a quick functional check doubles as a light accessibility sanity check.
|
||||
|
||||
With the server connected and the app running, ask Copilot to exercise the filtering feature you just built:
|
||||
|
||||
```text
|
||||
Using the Playwright MCP server, open a browser to the running app at http://localhost:4321 and verify the new game filtering feature:
|
||||
|
||||
1. Go to the games page and note how many games are listed.
|
||||
2. Apply a category filter and confirm the list updates to only show games in that category.
|
||||
3. Clear it, then apply a publisher filter and confirm the list updates to that publisher.
|
||||
4. Combine a category and a publisher filter and confirm the results respect both.
|
||||
|
||||
Report what you observe at each step, and call out anything that does not behave as expected.
|
||||
```
|
||||
|
||||
Copilot will launch a browser through the Playwright MCP server, walk through each step, and report back what it found. Read its summary against the acceptance criteria in the issue — if something looks off, ask follow-up questions or send it back to fix the code before you open a pull request.
|
||||
|
||||
> [!NOTE]
|
||||
> The app needs to be running at `http://localhost:4321` for this test. If you stopped the dev server, start it again before sending the prompt. The first time Copilot uses the Playwright MCP server it may need to download a browser — if it reports a missing browser, have it run `npx playwright install chromium` and try again.
|
||||
|
||||
[playwright-mcp-server]: https://github.com/microsoft/playwright-mcp
|
||||
## Publish the branch and create a pull request
|
||||
|
||||
Now that you've confirmed the feature works, you're ready to open a pull request (PR) so your team can review it. The first step is to publish the `filtering-vscode` branch.
|
||||
|
||||
1. Navigate to the **Source Control** panel in the codespace and review the changes made by Copilot.
|
||||
2. Stage the changes by selecting the **+** icon.
|
||||
3. Generate a commit message using the **Sparkle** button.
|
||||
|
||||
|
||||
|
||||
4. Select **Publish** to push the branch to your repository.
|
||||
|
||||
## Create the pull request
|
||||
|
||||
There are several ways to create a pull request, including through github.com and the GitHub command-line interface (CLI). But since you're already working with GitHub Copilot, let's let it create the PR for you! It can find the relevant issue and create the PR with an association to it.
|
||||
|
||||
1. Navigate to the Copilot Chat panel and select **New Chat** to start a new session.
|
||||
2. Ensure **Agent** is selected from the agents dropdown so Copilot can use the GitHub tools.
|
||||
3. Ask Copilot to create a PR for you:
|
||||
|
||||
```plaintext
|
||||
Find the issue in the repo related to filtering by category and publisher. Create a new pull request for the current branch, and associate it with the correct issue.
|
||||
```
|
||||
|
||||
4. As needed, select **Continue** to allow Copilot to perform the tasks necessary to gather information and perform operations. The first time it uses a GitHub tool, you may be prompted to authenticate with GitHub — follow the prompts to allow it.
|
||||
5. Notice how Copilot searches through the issues, finds the right one, and creates the PR.
|
||||
6. Select the link generated by Copilot to review your pull request, but please **don't merge it yet**.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
Congratulations! In this exercise you:
|
||||
|
||||
- learned what Model Context Protocol (MCP) is and how MCP servers extend Copilot with new tools,
|
||||
- added the Playwright MCP server to your workspace,
|
||||
- used it to manually test your filtering feature in a browser before shipping it,
|
||||
- published your branch and opened a pull request for the filtering work.
|
||||
|
||||
You used an MCP server to *test* a feature — but MCP is just one way to extend Copilot. Next, let's [create a custom agent][next-lesson] to streamline focused tasks like accessibility reviews.
|
||||
|
||||
## Resources
|
||||
|
||||
- [What the heck is MCP and why is everyone talking about it?][mcp-blog-post]
|
||||
- [Microsoft Playwright MCP Server][playwright-mcp-server]
|
||||
- [GitHub MCP Server][github-mcp-server]
|
||||
- [GitHub MCP Registry][mcp-registry]
|
||||
- [MCP servers in VS Code][vscode-mcp-config]
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/vscode/2-agent-mode/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/vscode/4-custom-agents/
|
||||
[mcp-blog-post]: https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/
|
||||
[github-mcp-server]: https://github.com/github/github-mcp-server
|
||||
[mcp-registry]: https://github.com/mcp
|
||||
[remote-github-mcp-server]: https://github.blog/changelog/2025-06-12-remote-github-mcp-server-is-now-available-in-public-preview/
|
||||
[vscode-mcp-config]: https://code.visualstudio.com/docs/agents/reference/mcp-configuration
|
||||
@@ -0,0 +1,117 @@
|
||||
---
|
||||
title: "Exercise 4 - Custom agents"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
## What are custom agents?
|
||||
|
||||
[Custom agents][custom-agents-concept] in GitHub Copilot allow you to create specialized AI assistants tailored to specific tasks or domains within your development workflow. By defining agents through markdown files in the `.github/agents` folder of your repository, you can provide Copilot with focused instructions, best practices, coding patterns, and domain-specific knowledge that guide it to perform particular types of work more effectively. Teams can codify their expertise into reusable agents — an accessibility agent that enforces [WCAG][wcag] compliance, a security agent that follows secure coding practices, or a testing agent that maintains consistent test patterns.
|
||||
|
||||
Custom agents are defined by markdown files in the `.github/agents` folder of your project, or globally in `~/.copilot/agents`. Each file has YAML frontmatter with at least a `name` and `description`, followed by a markdown prompt that defines the agent's behavior, expertise, and instructions.
|
||||
|
||||
### Custom agents compared with agent skills
|
||||
|
||||
There's some logical overlap between custom agents and [agent skills][agent-skills-concept]. Both are primarily defined with markdown files and tell an AI how to perform operations. The cleanest way to separate them: a **custom agent** is the worker, and **skills** are tools.
|
||||
|
||||
Custom agents have their own context window and are built to orchestrate skills (and even other agents) as part of doing their work. In this lab, the accessibility custom agent reviews and updates the site against accessibility guidelines; as part of that work it could call skills such as a pull-request workflow skill or one that runs and manages tests.
|
||||
|
||||
> [!NOTE]
|
||||
> There's no single "right" way to author a custom agent. As with anything in AI, test and iterate to find what works for your environments and scenarios.
|
||||
|
||||
[custom-agents-concept]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[agent-skills-concept]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[wcag]: https://www.w3.org/WAI/standards-guidelines/wcag/
|
||||
## Scenario
|
||||
|
||||
Tailspin Toys is committed to ensuring their crowdfunding platform is accessible to all users, regardless of their visual abilities or preferences. Recent user feedback has highlighted that some users find the current dark theme difficult to read due to insufficient contrast between text and background colors. To address this accessibility concern, the design team has requested the implementation of a high-contrast mode that users can toggle on and off.
|
||||
|
||||
Because accessibility is critical, you want to ensure this is implemented as quickly as possible. You're going to utilize a custom agent to generate the functionality.
|
||||
In this exercise, you will:
|
||||
|
||||
- review an existing accessibility custom agent.
|
||||
- use the accessibility agent in Copilot Chat to implement a high-contrast mode.
|
||||
|
||||
## Reviewing the accessibility custom agent
|
||||
|
||||
A custom agent has already been created for you for accessibility. Let's review the contents to understand how it will guide Copilot.
|
||||
|
||||
Return to your codespace, then open a terminal and switch to a fresh branch off `main` for the accessibility work (you'll keep the filtering PR from Exercise 3 separate):
|
||||
|
||||
```bash
|
||||
git checkout main
|
||||
git pull
|
||||
git checkout -b accessibility-vscode
|
||||
```
|
||||
|
||||
1. Open `.github/agents/accessibility.md`.
|
||||
2. Note the YAML frontmatter with the `name` and `description` fields.
|
||||
|
||||
> [!CAUTION]
|
||||
> The frontmatter with `name` and `description` is required for custom agents.
|
||||
|
||||
3. From there, scan and review the next sections which highlight:
|
||||
- Core responsibilities when generating code for an accessible website.
|
||||
- Best practices for accessibility.
|
||||
- Code examples for HTML, CSS, and JavaScript.
|
||||
- A list of common pitfalls and mistakes.
|
||||
## Using the custom agent in Copilot Chat
|
||||
|
||||
VS Code surfaces every custom agent defined in `.github/agents` in the agents dropdown at the bottom of the Copilot Chat view. You can select a custom agent to scope a chat session to that agent's instructions and tooling.
|
||||
|
||||
> [!TIP]
|
||||
> **Open Copilot Chat**
|
||||
>
|
||||
> Before you start the exercises below, return to your codespace, open the Copilot Chat panel, and select **New Chat** to start a clean conversation. Mode and model selection vary per exercise — each step calls those out where it matters.
|
||||
1. Select **Agent** from the agents dropdown in the Chat view if it isn't already selected.
|
||||
|
||||
|
||||
|
||||
2. Select the agents dropdown at the bottom of the chat view (it shows the active agent — by default, this is **default**).
|
||||
3. Select **Accessibility agent** from the list of available agents.
|
||||
4. Send the following prompt to the accessibility agent:
|
||||
|
||||
```
|
||||
Add a high-contrast mode to the site. There should be a toggle for high contrast which the user can set, and the setting should persist across page reloads using local storage on the browser.
|
||||
```
|
||||
|
||||
5. Copilot Chat will get to work — it'll explore the codebase, propose changes, and apply edits to your project files. Each edit will appear inline in the chat with the file path and a diff you can review.
|
||||
6. As edits land, the **Files changed** indicator updates so you can see the working set the agent has modified.
|
||||
|
||||
> [!NOTE]
|
||||
> This process will likely take a few minutes. Copilot is making real changes to your repository — it'll edit existing files such as the Astro components, CSS, and any related tests as it works.
|
||||
|
||||
You'll review and steer this in-flight work in the next exercise.
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
This lesson explored [custom agents][custom-agents] in GitHub Copilot, specialized AI assistants tailored to specific tasks and domains. With custom agents you can codify your team's expertise and standards into reusable agents that guide Copilot to perform particular types of work more effectively.
|
||||
|
||||
You explored these concepts:
|
||||
|
||||
- how custom agents are defined.
|
||||
- using a custom agent in Copilot Chat agent mode.
|
||||
|
||||
Next, you'll [monitor and steer the agent's work][next-lesson] — reviewing the changes as they happen and adding a light-mode toggle to the same session.
|
||||
|
||||
## Resources
|
||||
|
||||
- [About custom agents][custom-agents]
|
||||
- [Creating custom agents in your IDE][creating-custom-agents-ide]
|
||||
- [Custom agents in VS Code][custom-agents-vscode]
|
||||
- [Custom agents configuration][custom-agents-config]
|
||||
- [Custom agents on awesome-copilot][awesome-copilot-agents]
|
||||
|
||||
---
|
||||
|
||||
| [← Previous lesson: Testing your feature with the Playwright MCP server][previous-lesson] | [Next lesson: Monitoring and managing agents →][next-lesson] |
|
||||
|:--|--:|
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/vscode/3-mcp/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/vscode/5-managing-agents/
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[creating-custom-agents-ide]: https://docs.github.com/copilot/how-tos/use-copilot-agents/cloud-agent/create-custom-agents-in-your-ide
|
||||
[custom-agents-vscode]: https://code.visualstudio.com/docs/copilot/customization/custom-agents
|
||||
[custom-agents-config]: https://docs.github.com/copilot/reference/custom-agents-configuration
|
||||
[awesome-copilot-agents]: https://github.com/github/awesome-copilot/tree/main/agents
|
||||
@@ -0,0 +1,87 @@
|
||||
---
|
||||
title: "Exercise 5 - Monitoring and managing agents"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
When you put GitHub Copilot in agent mode, it works autonomously — exploring your codebase, proposing changes, editing files, and running commands. Because that work is happening on your machine in real time, Copilot Chat in VS Code gives you a running view of every tool call and every file edit as it happens. You can review each diff inline, accept or reject individual changes, and steer the conversation with follow-up prompts to refine or extend the work without leaving your editor.
|
||||
|
||||
In this exercise, you will:
|
||||
|
||||
- monitor the accessibility agent's work in real time.
|
||||
- review and accept the proposed file edits.
|
||||
- steer the agent mid-session to add a light-mode toggle alongside high-contrast.
|
||||
|
||||
## Scenario
|
||||
|
||||
The accessibility custom agent you used in [Exercise 4][previous-lesson] is implementing high-contrast mode. While the work is in progress, the design team has come back with an additional request — they'd also like a light-mode toggle for users who find the default theme too dark. Rather than start a new conversation from scratch, you'll steer the existing session to extend the work.
|
||||
|
||||
## Monitor Copilot's progress
|
||||
|
||||
The Copilot Chat view shows each step the agent takes — files it explores, commands it runs, and edits it proposes. Each file edit appears inline in the chat with a diff and **Keep** / **Undo** controls.
|
||||
|
||||
1. Return to the Copilot Chat view from Exercise 4.
|
||||
2. As the agent works, scroll the chat to watch each tool call land. You'll see file reads, file edits, and any terminal commands it asks to run.
|
||||
3. When the agent proposes a file edit, the diff appears inline:
|
||||
- Select **Keep** to accept the change.
|
||||
- Select **Undo** to revert the change and let the agent take another pass.
|
||||
4. You can also open the **Files changed** indicator at the top of the chat to see the full working set the agent has modified during this session.
|
||||
|
||||
> [!NOTE]
|
||||
> If a tool call asks for permission (for example, running a terminal command), the agent will pause and surface an **Allow** prompt. Approve only the commands you're comfortable with.
|
||||
|
||||
5. Wait for the agent to finish implementing high-contrast mode. You should see a final message summarizing the changes it made.
|
||||
|
||||
## Steer the agent to add light mode
|
||||
|
||||
Now that high-contrast mode is in place, you'll extend the same conversation to add a light-mode toggle. Because you're continuing the same chat session, the agent retains all the context from its previous work — including the components it touched, the styling approach it used, and the local-storage pattern it set up.
|
||||
|
||||
1. In the Copilot Chat input, send the following follow-up prompt:
|
||||
|
||||
```
|
||||
Nice work! Now add a light-mode toggle alongside the high-contrast toggle. Light mode should follow the same pattern — persist via local storage and be accessible from the same area of the UI. The user should be able to enable high-contrast and light mode independently.
|
||||
```
|
||||
|
||||
2. The agent will pick up where it left off, exploring the changes it already made and proposing additions for light mode.
|
||||
3. Review each new edit as it lands, just like you did for high-contrast. Use **Keep** or **Undo** on each diff.
|
||||
4. If the agent goes in a direction you don't want — for example, it tries to refactor the toggle UI in a way you don't like — you can stop it with the **Stop** button next to the chat input, then send a clarifying follow-up message.
|
||||
|
||||
> [!TIP]
|
||||
> Steering an in-flight session is faster than starting over. Use follow-up prompts to ask for adjustments ("simplify the CSS — use CSS variables instead of duplicating selectors"), to course-correct ("don't add a third toggle, integrate light mode into the existing settings panel"), or to extend scope ("also add keyboard shortcuts for both toggles").
|
||||
|
||||
## Review the working set
|
||||
|
||||
Before committing the work, take a quick pass over everything the agent touched.
|
||||
|
||||
1. Open the **Source Control** view in VS Code.
|
||||
2. Review the full list of changed files. You should see updates to the Astro components, styles, and any related tests.
|
||||
3. Open a couple of the changed files and walk through the diffs. Confirm the accessibility patterns from the custom agent are reflected — ARIA attributes, keyboard navigation, semantic HTML, and persistence via local storage.
|
||||
4. When you're satisfied, stage and commit the changes from the Source Control panel. You'll publish them in [the next lesson][next-lesson].
|
||||
|
||||
## Summary and next steps
|
||||
|
||||
You used Copilot Chat agent mode to monitor and steer an in-flight session — reviewing each file edit as it landed, accepting or rejecting changes, and sending follow-up prompts to extend the work without losing context.
|
||||
|
||||
In this lesson you explored:
|
||||
|
||||
- monitoring an agent's work in real time.
|
||||
- accepting and rejecting individual file edits.
|
||||
- steering a session mid-flight with follow-up prompts.
|
||||
|
||||
In the [next lesson][next-lesson] you'll publish your accessibility work as a pull request and review the changes the local custom agent has produced throughout this lab.
|
||||
|
||||
## Resources
|
||||
|
||||
- [Copilot Chat in VS Code][copilot-chat-vscode]
|
||||
- [Using agent mode][agent-mode]
|
||||
|
||||
---
|
||||
|
||||
| [← Previous lesson: Custom agents][previous-lesson] | [Next lesson: Iterating on Copilot's work →][next-lesson] |
|
||||
|:--|--:|
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/vscode/4-custom-agents/
|
||||
[next-lesson]: /learning-hub/copilot-workshops/vscode/6-iterating/
|
||||
[copilot-chat-vscode]: https://code.visualstudio.com/docs/copilot/chat/copilot-chat
|
||||
[agent-mode]: https://code.visualstudio.com/docs/copilot/chat/chat-agent-mode
|
||||
@@ -0,0 +1,90 @@
|
||||
---
|
||||
title: "Exercise 6 - Iterating on GitHub Copilot's work"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
| [← Previous lesson: Monitoring and managing agents][previous-lesson] |
|
||||
|:--|
|
||||
|
||||
## Reviewing the work
|
||||
|
||||
Throughout this lab you've worked with GitHub Copilot on several tasks focused on improving the user experience. You used agent mode to add filtering across the client and server, the Playwright MCP server to manually test that work in a browser, then a custom agent to implement accessibility features — high-contrast and light-mode toggles — and steered the session mid-flight to extend the work. Now it's time to publish that local work and review it the same way your team would.
|
||||
|
||||
### Scenario
|
||||
|
||||
The fundamentals of software design and DevOps don't change with the addition of generative AI. You still want a real review cycle on anything Copilot produces. With that in mind, let's push the accessibility changes from your codespace, open a pull request, and walk through the diff before bringing the rest of the team in.
|
||||
## Publish the accessibility features
|
||||
|
||||
The high-contrast and light-mode toggles you implemented with the accessibility custom agent in [Exercise 4][exercise-4] and [Exercise 5][exercise-5] are sitting in your codespace as committed changes. Let's push them to a branch and open a pull request so the rest of your team can review.
|
||||
|
||||
1. Return to your codespace.
|
||||
2. Open the **Source Control** view in VS Code.
|
||||
3. Confirm your accessibility changes are committed. If you have uncommitted changes from Exercise 5, stage and commit them now with a descriptive message such as `Add high-contrast and light-mode toggles`.
|
||||
4. Publish the branch by selecting **Publish Branch** (or use the **...** menu → **Push**).
|
||||
5. VS Code will offer to open the new branch on github.com. Accept the prompt, or navigate to your repository manually and select **Compare & pull request** on the branch banner.
|
||||
6. Set a clear title (for example, `Add high-contrast and light-mode toggles`) and a short description summarizing what was done and why.
|
||||
7. Select **Create pull request**.
|
||||
8. Once the PR is open, select the **Files changed** tab to review your work end-to-end. Pay particular attention to:
|
||||
- The toggle UI components for switching between modes.
|
||||
- The use of local storage to persist user preferences.
|
||||
- The CSS or styling changes for high-contrast and light modes.
|
||||
- The accessibility attributes (ARIA labels, keyboard navigation, etc.).
|
||||
- Any JavaScript/TypeScript code that manages the mode switching.
|
||||
|
||||
9. Return to the **Conversation** tab.
|
||||
10. If workflows are waiting for approval, select **Approve and run workflows**.
|
||||
|
||||
|
||||
11. Wait for the workflows to complete. All being well, you should see them pass.
|
||||
|
||||
> [!TIP]
|
||||
> Want a second opinion on your accessibility work? Tag `@copilot` in a PR comment with a request such as "review this PR for additional WCAG issues" or "suggest improvements to the keyboard navigation". Copilot will start a new session to address the comment.
|
||||
|
||||
## Optional exercise - keep exploring locally
|
||||
|
||||
Working iteratively with an agent in the IDE is a skill, and the only way to build it is repetition. Some ideas for follow-up sessions you can run from VS Code:
|
||||
|
||||
- Add a backer interest form on the game details page.
|
||||
- Implement pagination on the game list page.
|
||||
- Add input validation and error handling to the data-access helpers in `src/lib/`.
|
||||
- Extend the accessibility agent's scope — for example, audit keyboard focus order across the whole site.
|
||||
|
||||
## Summary
|
||||
|
||||
Congratulations — you've completed the VS Code harness! Through this lab you:
|
||||
|
||||
- **Used Playwright MCP to manually test your feature.** You added the Playwright MCP server and let Copilot drive a browser to verify your filtering feature before opening a pull request.
|
||||
- **Drove agent mode through coordinated changes across the stack.** You added a filter feature that touched the client, the server, and the tests in a single session.
|
||||
- **Used a custom agent.** You selected the accessibility-focused custom agent from the agent picker and watched it implement high-contrast mode against the repository.
|
||||
- **Managed and steered an agent session.** You reviewed proposed changes inline, accepted what you wanted, and extended the session with a light-mode follow-up.
|
||||
- **Closed the loop with a pull request.** You published your local work and reviewed it end-to-end the way your team would.
|
||||
|
||||
## Review and next steps
|
||||
|
||||
If you'd like to expand your perspective on Copilot's agent capabilities, the other harnesses cover related scenarios through different surfaces:
|
||||
|
||||
- 💻 **[CLI harness](/learning-hub/copilot-workshops/cli/)** — work similar flows from your terminal with Copilot CLI: plan mode, agent skills, custom agents, and slash commands like `/share`, `/context`, and `/delegate`.
|
||||
- ☁️ **[Cloud agent harness](/learning-hub/copilot-workshops/cloud/)** — focus on assigning issues to cloud agent, monitoring sessions through the agents page, and iterating asynchronously on pull requests.
|
||||
|
||||
You can also keep building on what you started here. [awesome-copilot][awesome-copilot] is a great source for more instruction files, custom agents, and skills you can adapt to your own projects.
|
||||
|
||||
## Resources
|
||||
|
||||
- [GitHub Copilot][github-copilot]
|
||||
- [Copilot Chat in VS Code][copilot-chat-vscode]
|
||||
- [Using agent mode][agent-mode]
|
||||
|
||||
---
|
||||
|
||||
| [← Previous lesson: Managing agents][previous-lesson] |
|
||||
|:--|
|
||||
|
||||
[previous-lesson]: /learning-hub/copilot-workshops/vscode/5-managing-agents/
|
||||
[exercise-4]: /learning-hub/copilot-workshops/vscode/4-custom-agents/
|
||||
[exercise-5]: /learning-hub/copilot-workshops/vscode/5-managing-agents/
|
||||
[github-copilot]: https://github.com/features/copilot
|
||||
[copilot-chat-vscode]: https://code.visualstudio.com/docs/copilot/chat/copilot-chat
|
||||
[agent-mode]: https://code.visualstudio.com/docs/copilot/chat/chat-agent-mode
|
||||
[awesome-copilot]: https://github.com/github/awesome-copilot
|
||||
@@ -0,0 +1,45 @@
|
||||
---
|
||||
title: "VS Code"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
**[GitHub Copilot Chat](https://code.visualstudio.com/docs/copilot/chat/copilot-chat)** in VS Code brings GitHub Copilot into the code editor you already use. Working in Visual Studio Code (and GitHub Codespaces), you'll drive Copilot Chat in agent mode, connect external tools through MCP, and rely on custom agents — all without leaving your IDE, where Copilot has full view of your files, terminal, and problems.
|
||||
|
||||
You'll start by adding custom instructions and watching Copilot follow them, then use agent mode to build a filtering feature across the UI, data layer, and tests. Next you'll connect the Playwright MCP server and let Copilot drive a browser to test your feature before opening a pull request. Finally, you'll review and use a custom agent for accessibility work, then monitor, steer, and iterate on Copilot's changes — all without leaving the editor.
|
||||
|
||||
## Exercises
|
||||
|
||||
| Exercise | Topic | Description |
|
||||
|----------|-------|-------------|
|
||||
| [0. Prerequisites][ex0] | Setup | Create your repository and codespace |
|
||||
| [1. Custom instructions][ex1] | Context | Add and verify custom instructions in VS Code |
|
||||
| [2. Agent Mode][ex2] | Code Generation | Build a filtering feature with agent mode |
|
||||
| [3. MCP with Playwright][ex3] | External Tools | Test your feature in a browser with the Playwright MCP server |
|
||||
| [4. Custom Agents][ex4] | Specialized Agents | Review and use custom agents |
|
||||
| [5. Managing Agents][ex5] | Monitoring | Monitor and steer agent sessions |
|
||||
| [6. Iterating][ex6] | Review | Review Copilot's work locally and choose next steps |
|
||||
|
||||
## Prerequisites
|
||||
|
||||
Before attending this workshop, please ensure you have:
|
||||
|
||||
- [ ] A GitHub account with an active **Copilot Student, Pro, Pro+, Business, or Enterprise** plan
|
||||
- [ ] Access to GitHub Codespaces
|
||||
|
||||
> [!TIP]
|
||||
> No paid plan? Verified students can get GitHub Copilot for free through [GitHub Education][callout-student-plan-education]. The **Copilot Student** plan includes the agent, MCP, code review, and Copilot CLI features this workshop uses — so you can complete every harness with it.
|
||||
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
## Get Started
|
||||
|
||||
**[Start with Exercise 0: Prerequisites →][ex0]**
|
||||
|
||||
[ex0]: /learning-hub/copilot-workshops/vscode/0-prerequisites/
|
||||
[ex1]: /learning-hub/copilot-workshops/vscode/1-custom-instructions/
|
||||
[ex2]: /learning-hub/copilot-workshops/vscode/2-agent-mode/
|
||||
[ex3]: /learning-hub/copilot-workshops/vscode/3-mcp/
|
||||
[ex4]: /learning-hub/copilot-workshops/vscode/4-custom-agents/
|
||||
[ex5]: /learning-hub/copilot-workshops/vscode/5-managing-agents/
|
||||
[ex6]: /learning-hub/copilot-workshops/vscode/6-iterating/
|
||||
@@ -16,6 +16,8 @@ New to GitHub Copilot? Start here to understand the tools available to you.
|
||||
|
||||
**Terminal**: Looking for a guided path into GitHub Copilot from the terminal? Explore the [Copilot CLI for Beginners](cli-for-beginners/) with a text-based experience or the [YouTube video series](https://www.youtube.com/watch?v=BDxRhhs36ns&list=PL0lo9MOBetEHvO-spzKBAITkkTqv4RvNl).
|
||||
|
||||
**Workshop**: Prefer to learn by building? Work through [Hands-on with GitHub Copilot's agents](copilot-workshops/) — a hands-on workshop with four harnesses (VS Code, Copilot CLI, Copilot app, and cloud agent) built around a shared Tailspin Toys backlog.
|
||||
|
||||
## Fundamentals
|
||||
|
||||
Essential concepts to tailor GitHub Copilot beyond its default experience. Start with
|
||||
|
||||
@@ -0,0 +1,85 @@
|
||||
---
|
||||
title: "Lição 0 - Pré-requisitos"
|
||||
description: "Prepare-se para as lições do aplicativo GitHub Copilot: instale o Node.js para o projeto Tailspin Toys e crie sua própria cópia do repositório a partir do modelo."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
O aplicativo GitHub Copilot é um aplicativo para desktop que funciona como ponto central tanto para o Copilot quanto para o GitHub. Ele oferece acesso rápido a issues e pull requests e, naturalmente, permite que você desenvolva usando o GitHub Copilot. Durante este workshop, você trabalhará localmente com o aplicativo Tailspin Toys, criado com Astro, e com o aplicativo GitHub Copilot. Antes de começar, vamos verificar se o Node.js está instalado localmente e depois instalar o aplicativo Copilot.
|
||||
|
||||
Nesta lição, você vai:
|
||||
|
||||
- instalar o Node.js para executar os testes do projeto no seu computador.
|
||||
- criar sua própria cópia do projeto Tailspin Toys a partir do modelo.
|
||||
|
||||
## Instalar o Node.js
|
||||
|
||||
Em várias lições, você pedirá a um agente que crie recursos e execute localmente o conjunto de testes do Tailspin Toys. Para isso, é necessário o [**Node.js**][nodejs], o único ambiente de execução exigido pelo projeto. Instale a versão **22 ou posterior**; a versão **LTS** atual é uma escolha segura.
|
||||
|
||||
A opção mais simples em todas as plataformas é o instalador oficial:
|
||||
|
||||
1. No sistema operacional, abra uma janela de terminal usando o Windows Terminal, o Terminal do macOS ou o aplicativo que você costuma usar.
|
||||
2. Execute o comando a seguir para confirmar que você tem o Node.js 22 ou posterior instalado:
|
||||
|
||||
```shell
|
||||
node --version
|
||||
```
|
||||
|
||||
3. Se você vir `v22` ou um número maior, pule para a próxima seção.
|
||||
|
||||
> [!TIP]
|
||||
> Você só precisa concluir estas etapas se não tiver o Node instalado ou se precisar atualizá-lo.
|
||||
|
||||
4. Abra a [página de download do Node.js][node-download].
|
||||
5. Baixe a versão **LTS** para o seu sistema operacional.
|
||||
6. Execute o instalador e aceite as opções padrão. No Windows, mantenha a opção **Add to PATH** selecionada.
|
||||
7. Após a instalação, abra uma nova janela de terminal.
|
||||
8. Confirme a instalação na nova janela de terminal executando:
|
||||
|
||||
```bash
|
||||
node --version
|
||||
```
|
||||
|
||||
9. Você deve ver `v22.x.x` ou posterior.
|
||||
|
||||
> [!TIP]
|
||||
> Prefere contêineres? Se você tem o [**Docker**][docker], pode usar o [contêiner de desenvolvimento][dev-containers] do repositório em vez de instalar o Node.js localmente. Ele já inclui o Node. Você não precisa dos dois.
|
||||
|
||||
## Configurar o repositório do laboratório
|
||||
|
||||
Você trabalhará na sua própria cópia do projeto Tailspin Toys. Crie-a agora a partir do [repositório de modelo][template-repository]. O novo repositório contém todos os arquivos necessários para o laboratório, e você o conectará ao aplicativo na próxima lição.
|
||||
|
||||
1. Em uma nova janela do navegador, acesse o repositório do GitHub deste laboratório: `https://github.com/github-samples/tailspin-toys`.
|
||||
2. Crie sua própria cópia do repositório selecionando o botão **Use this template** na página do repositório do laboratório. Em seguida, selecione **Create a new repository**.
|
||||
|
||||
|
||||
|
||||
3. Se você estiver fazendo o workshop como parte de um evento conduzido pelo GitHub ou pela Microsoft, siga as instruções dos mentores. Caso contrário, crie o novo repositório em uma organização na qual você tenha acesso ao GitHub Copilot.
|
||||
|
||||
|
||||
|
||||
4. Anote o caminho do repositório que você criou (**organization-or-user-name/repository-name**), pois ele será usado mais adiante no laboratório.
|
||||
|
||||
> [!NOTE]
|
||||
> Quando você cria o repositório a partir do modelo, um backlog de issues do GitHub é criado automaticamente. Você trabalhará com essas issues durante todo o workshop e não precisará criar nenhuma.
|
||||
|
||||
## Resumo e próximos passos
|
||||
|
||||
Tudo pronto! Você instalou o Node.js para criar e testar o projeto no seu computador e criou sua própria cópia do repositório Tailspin Toys a partir do modelo.
|
||||
|
||||
Em seguida, você instalará o aplicativo GitHub Copilot, conectará o repositório que acabou de criar e conhecerá o espaço de trabalho. Continue para a [Lição 1 - Instalar o aplicativo GitHub Copilot][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Baixar o Node.js][node-download]
|
||||
- [Criar um repositório a partir de um modelo][template-repository]
|
||||
- [Sobre o aplicativo GitHub Copilot][about-copilot-app]
|
||||
|
||||
[next-lesson]: /pt-br/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[nodejs]: https://nodejs.org/
|
||||
[node-download]: https://nodejs.org/en/download
|
||||
[docker]: https://www.docker.com/products/docker-desktop/
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
+100
@@ -0,0 +1,100 @@
|
||||
---
|
||||
title: "Lição 1 - Instalar o aplicativo GitHub Copilot"
|
||||
description: "Instale o aplicativo GitHub Copilot, conecte o repositório criado a partir do modelo, conheça o espaço de trabalho e experimente um chat rápido."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
O [**aplicativo GitHub Copilot**][about-copilot-app] é um aplicativo para desktop voltado ao desenvolvimento orientado por agentes. Ele foi criado com base no GitHub Copilot CLI e tem integração nativa com o GitHub, portanto seus repositórios, branches e pipelines de CI funcionam sem configuração adicional. Ele foi projetado para fluxos de trabalho nos quais você orienta vários agentes em paralelo, cada um em seu espaço de trabalho isolado, em vez de fazer todo o trabalho por conta própria, além de automatizar tarefas repetitivas. Com o Node.js instalado e sua cópia do projeto pronta, a próxima etapa é instalar o aplicativo e conectar esse repositório.
|
||||
|
||||
Nesta lição, você vai:
|
||||
|
||||
- instalar o aplicativo GitHub Copilot e entrar na sua conta.
|
||||
- adicionar seu projeto ao aplicativo por meio do repositório do GitHub.
|
||||
- conhecer o espaço de trabalho, incluindo o backlog criado pelo modelo.
|
||||
- experimentar um chat rápido para saber mais sobre o próprio aplicativo.
|
||||
|
||||
## Cenário
|
||||
|
||||
Sua equipe está adotando agentes de IA para trabalhar em um backlog crescente. O aplicativo Copilot oferece um único lugar para orientar esse trabalho: selecionar issues, executar agentes, revisar alterações e fazer merge de pull requests. Nesta lição, você instalará e conectará o aplicativo e aprenderá a iniciar uma conversa sobre o projeto.
|
||||
|
||||
> [!NOTE]
|
||||
> É necessário ter um plano elegível do Copilot: Copilot Student ou qualquer plano pago (Pro, Pro+, Business ou Enterprise). Se você usa o Copilot Business ou o Copilot Enterprise, o administrador deve habilitar a política **Copilot CLI** para que o aplicativo funcione.
|
||||
|
||||
## Instalar e configurar o aplicativo GitHub Copilot
|
||||
|
||||
Como você pode imaginar, a primeira etapa para usar o aplicativo GitHub Copilot é instalá-lo. Há versões disponíveis para Windows, macOS e Linux. Vamos instalar o aplicativo, autenticar a conta e adicionar o repositório Tailspin Toys.
|
||||
|
||||
1. Em um navegador, abra a [página inicial do aplicativo GitHub Copilot][download-app].
|
||||
2. Baixe o aplicativo para sua plataforma e instale-o seguindo as instruções da página.
|
||||
3. Abra o aplicativo após a instalação.
|
||||
4. Selecione **Sign in to GitHub** e siga as instruções para se autenticar. Se você usa o GitHub Enterprise Server, escolha **Use GitHub Enterprise** e informe o endereço do servidor quando solicitado.
|
||||
5. Após a autenticação, o aplicativo perguntará sobre a conexão dos seus repositórios. Selecione o repositório Tailspin Toys que você acabou de criar, cujo nome deve ser `<YOUR_GITHUB_HANDLE>/tailspin-toys`.
|
||||
6. Selecione **Continue** para continuar a integração.
|
||||
7. Quando o aplicativo solicitar um tema, selecione aquele que mais lhe agrada e depois selecione **Finish**.
|
||||
|
||||
> [!NOTE]
|
||||
> Se a sua cópia do Tailspin Toys não aparecer automaticamente na lista, você poderá adicioná-la depois de concluir a integração no aplicativo. Ao final, o aplicativo Copilot exibirá a tela inicial. Nela, selecione **Choose from GitHub**, pesquise o repositório pelo nome (\<YOUR_GITHUB_HANDLE\>/tailspin-toys) e selecione-o. O repositório será adicionado ao aplicativo Copilot.
|
||||
|
||||
## Conhecer o espaço de trabalho
|
||||
|
||||
Com o projeto conectado, reserve um momento para conhecer o espaço de trabalho. O aplicativo organiza tudo em algumas áreas na barra lateral:
|
||||
|
||||
- **Sessions**: onde os agentes trabalham. Cada sessão é executada em seu próprio espaço de trabalho isolado, permitindo executar várias sessões ao mesmo tempo sem que as alterações entrem em conflito. Você iniciará sua primeira sessão na próxima lição.
|
||||
- **Quick chats**: conversas leves para perguntas e brainstorming que não precisam de branch ou espaço de trabalho próprios. Você experimentará uma ao final desta lição.
|
||||
- **My work**: suas issues e pull requests, exibidos por meio da **integração nativa com o GitHub**. Nessa área, você pode procurar e filtrar issues e pull requests, verificar o status da CI, iniciar uma sessão a partir de uma issue e revisar pull requests sem sair do aplicativo.
|
||||
- **Automations**: tarefas de agente salvas que são executadas em uma agenda ou sob demanda. Você criará uma perto do fim deste percurso.
|
||||
|
||||
### Localizar o backlog criado pelo modelo
|
||||
|
||||
Como o aplicativo tem integração nativa com o GitHub, o trabalho pendente no repositório aparece dentro dele. Quando você criou o repositório a partir do modelo, um backlog de issues foi criado. Vamos confirmar que ele está disponível.
|
||||
|
||||
1. Selecione **My work** na barra lateral.
|
||||
2. O modelo criou oito issues no seu backlog. Este módulo foca nas três a seguir — confirme que você consegue vê-las:
|
||||
|
||||
- Allow users to filter games by category and publisher
|
||||
- Update our repository coding standards
|
||||
- Implement pagination on the game list page
|
||||
|
||||
3. Selecione uma issue para ler os detalhes. Cada issue também serve como ponto de partida para uma sessão de agente. Você começará a trabalhar com elas mais adiante neste percurso.
|
||||
|
||||
> [!NOTE]
|
||||
> A lista de itens em My work é filtrada automaticamente para exibir somente itens dos repositórios adicionados ao aplicativo Copilot. Quer ver itens de trabalho de outros repositórios? Adicione-os ao aplicativo.
|
||||
|
||||
## Experimentar um chat rápido
|
||||
|
||||
Uma ótima maneira de se familiarizar com o aplicativo é usá-lo para saber mais sobre o *próprio aplicativo*, e um **chat rápido** é a ferramenta ideal. Os chats rápidos permitem fazer perguntas ou brainstorming sem criar uma branch ou worktree. Por isso, são perfeitos para perguntas rápidas e descartáveis, sem exigir uma sessão.
|
||||
|
||||
1. Na barra lateral, selecione **+** ao lado de **Quick chats** para abrir um novo chat.
|
||||
2. Pergunte ao aplicativo como funcionam as próprias sessões:
|
||||
|
||||
```plaintext
|
||||
How does the GitHub Copilot app use worktrees?
|
||||
```
|
||||
|
||||
3. Leia a resposta na visualização da conversa. Você verá que cada sessão é executada em seu próprio git worktree isolado, o que permite executar vários agentes em paralelo sem que as alterações entrem em conflito. Você pode continuar a conversa ou iniciar um novo chat a qualquer momento.
|
||||
|
||||
## Resumo e próximos passos
|
||||
|
||||
Parabéns! Você instalou o aplicativo GitHub Copilot, conectou o projeto e explorou o espaço de trabalho. Você aprendeu a:
|
||||
|
||||
- instalar o aplicativo e entrar no GitHub.
|
||||
- adicionar um projeto por meio do repositório do GitHub.
|
||||
- conhecer o espaço de trabalho e localizar o backlog criado em **My work**.
|
||||
- usar um chat rápido para fazer uma pergunta rápida e descartável.
|
||||
|
||||
Em seguida, você iniciará sua primeira sessão de agente e fará a primeira alteração no projeto: exibir uma avaliação por estrelas nos cards dos jogos. Continue para a [Lição 2 - Executar sua primeira sessão de agente][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Sobre o aplicativo GitHub Copilot][about-copilot-app]
|
||||
- [Introdução ao aplicativo GitHub Copilot][getting-started]
|
||||
- [Trabalhar com sessões de agente no aplicativo GitHub Copilot][agent-sessions]
|
||||
|
||||
[ex0]: /pt-br/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[next-lesson]: /pt-br/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[download-app]: https://gh.io/app
|
||||
+135
@@ -0,0 +1,135 @@
|
||||
---
|
||||
title: "Lição 2 - Executar sua primeira sessão de agente"
|
||||
description: "Inicie sua primeira sessão de agente no aplicativo GitHub Copilot, faça uma pequena alteração nos cards dos jogos e integre-a como seu primeiro pull request."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Na lição anterior, você conheceu o espaço de trabalho e usou um chat rápido. Agora é hora de iniciar uma **sessão de agente** e fazer sua primeira alteração no projeto. A mudança será pequena: os dados dos jogos já têm uma avaliação por estrelas, mas os cards dos jogos na página inicial ainda não a exibem. Você pedirá ao agente que mostre essa avaliação, revisará a alteração e fará o merge dela como seu primeiro pull request.
|
||||
|
||||
Nesta lição, você vai:
|
||||
|
||||
- iniciar uma sessão de agente e aprender como ela é estruturada.
|
||||
- pedir ao agente que faça uma alteração pequena e específica no projeto.
|
||||
- revisar a alteração na visualização de diff do espaço de trabalho.
|
||||
- executar o aplicativo localmente para confirmar a alteração no navegador.
|
||||
- abrir e fazer merge do seu primeiro pull request.
|
||||
|
||||
## Cenário
|
||||
|
||||
Cada jogo no Tailspin Toys pode ter uma avaliação por estrelas, que já aparece na página de detalhes do jogo. No entanto, os cards dos jogos na página inicial mostram apenas título, categoria, distribuidora e descrição. Como aquecimento, você fará com que o agente exiba em cada card a avaliação existente. Essa alteração pequena e independente é perfeita para sua primeira sessão.
|
||||
|
||||
## Anatomia de uma sessão
|
||||
|
||||
Uma **sessão** é uma conversa com um agente executada em seu próprio espaço de trabalho isolado. Cada sessão recebe um **git worktree e uma branch dedicados**, o que permite executar várias sessões ao mesmo tempo, uma adicionando um recurso e outra corrigindo um bug, sem que as alterações entrem em conflito. Suas sessões aparecem na barra lateral agrupadas por repositório. Selecione qualquer uma delas para acessá-la.
|
||||
|
||||
Em uma sessão, você verá três elementos: a **conversa** com o agente, a **atividade de ferramentas** do agente enquanto ele explora e edita arquivos e a lista de **arquivos alterados** com os respectivos diffs.
|
||||
|
||||
## Iniciar uma sessão e solicitar a alteração
|
||||
|
||||
Vamos iniciar uma nova sessão para começar a explorar o projeto e implementar o recurso. Em uma [lição anterior][prior-lesson], você adicionou o projeto por meio do repositório do GitHub. Criaremos uma nova sessão para esse repositório e solicitaremos a alteração.
|
||||
|
||||
1. Volte ao aplicativo GitHub Copilot ou abra-o.
|
||||
2. Selecione **Home screen**.
|
||||
3. Verifique se `tailspin-toys` está selecionado como repositório.
|
||||
|
||||
|
||||
|
||||
4. Use o prompt a seguir para solicitar a alteração:
|
||||
|
||||
```plaintext
|
||||
On the game cards, show each game's star rating. The Game type already includes a starRating field — it's a number out of 5, or null when a game hasn't been rated yet. Display it on each card in src/components/GameCard.astro, and when starRating is null show "No rating yet" instead. Keep the change small and don't restructure the card layout.
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> Observe que o prompt contém o nome do arquivo que o Copilot deve atualizar. Embora não seja obrigatório especificar os arquivos que o Copilot deve incluir no trabalho, indicar a direção certa ajuda o Copilot a gerar código mais rapidamente e reduz o uso de tokens.
|
||||
|
||||
5. Selecione <kbd>Enter</kbd> para enviar o prompt ao Copilot.
|
||||
|
||||
O aplicativo Copilot começa criando um novo worktree, uma cópia isolada do projeto. Em seguida, ele explora o projeto, localiza os arquivos que precisam ser atualizados e cria o código necessário para adicionar o novo recurso. Você acabou de adicionar um recurso com o aplicativo Copilot.
|
||||
|
||||
## Revisar o diff
|
||||
|
||||
Todas as alterações geradas por IA devem ser revisadas antes do merge, mesmo as pequenas. Vamos explorar as alterações diretamente no aplicativo Copilot.
|
||||
|
||||
1. No canto superior direito do aplicativo, selecione **Toggle review panel**. A tela de diff será aberta com todas as alterações pendentes feitas pelo Copilot.
|
||||
|
||||
|
||||
|
||||
2. Você verá código adicionado a `GameCard.astro`, o arquivo principal usado para exibir os detalhes do jogo. Ele deve ser semelhante ao exemplo a seguir: um pequeno bloco que renderiza a avaliação quando ela existe e usa "No rating yet" quando `starRating` é `null`:
|
||||
|
||||
```astro
|
||||
{game.starRating !== null ? (
|
||||
<span class="text-xs font-medium px-2.5 py-0.5 rounded bg-amber-900/60 text-amber-300" data-testid="game-rating">
|
||||
★ {game.starRating} / 5
|
||||
</span>
|
||||
) : (
|
||||
<span class="text-xs font-medium text-slate-500" data-testid="game-rating-empty">
|
||||
No rating yet
|
||||
</span>
|
||||
)}
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> Como o Copilot, assim como todas as ferramentas de IA generativa, é probabilístico, e não determinístico, o código exato pode ser diferente do exemplo. No entanto, ele deve ser relativamente semelhante.
|
||||
|
||||
## Verificar as alterações
|
||||
|
||||
Não devemos apenas ler o código e presumir que ele funciona. Também precisamos testar tudo visualmente. Para isso, iniciaremos o aplicativo no terminal e confirmaremos o funcionamento. O aplicativo Copilot inclui um terminal.
|
||||
|
||||
1. No painel de revisão à direita do aplicativo Copilot, selecione **Terminal**. Se não houver um botão **Terminal**, selecione **+** (identificado como **Open in panel**) e depois selecione **Terminal**.
|
||||
|
||||
|
||||
|
||||
2. Digite o comando a seguir na janela do terminal para iniciar o servidor de desenvolvimento do aplicativo Web:
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
3. Quando o servidor iniciar, o que levará apenas alguns instantes, abra uma janela do navegador.
|
||||
4. Acesse http://localhost:4321.
|
||||
5. Agora você deve ver avaliações por estrelas em todos os jogos da página inicial.
|
||||
6. Volte à janela do terminal.
|
||||
7. Selecione <kbd>Ctrl</kbd>+<kbd>C</kbd> para interromper o servidor de desenvolvimento.
|
||||
|
||||
## Abrir e fazer merge do primeiro pull request
|
||||
|
||||
A alteração está correta. Agora é hora de entregá-la. Você pedirá ao agente que abra um pull request e depois fará a revisão e o merge no github.com. Por enquanto, gerenciaremos esse processo manualmente. Em uma próxima lição, veremos como o Copilot pode automatizar parte desse trabalho.
|
||||
|
||||
1. No canto superior direito, selecione **Create PR**.
|
||||
2. Se solicitado, selecione **Sign in with your browser** e siga as instruções para se autenticar.
|
||||
3. O Copilot começará a criar o PR.
|
||||
|
||||
Após a criação do PR, o Copilot monitorará os fluxos de trabalho do repositório que precisam ser executados. Depois de alguns instantes, o botão no canto superior direito mudará para **Ready to merge**, indicando que o PR está pronto para o merge.
|
||||
|
||||
4. Selecione o indicador **PR** logo acima do chat para abrir o PR no painel de revisão e visualizá-lo. Faça as revisões necessárias nesse painel.
|
||||
5. Quando estiver tudo pronto, selecione **Ready to merge**.
|
||||
6. Na nova caixa de diálogo, selecione **Merge pull request** para fazer o merge do pull request.
|
||||
|
||||
Você acaba de enviar um novo recurso para o site.
|
||||
|
||||
## Resumo e próximos passos
|
||||
|
||||
Você iniciou sua primeira sessão de agente e entregou sua primeira alteração. Especificamente, você:
|
||||
|
||||
- iniciou uma sessão de agente e aprendeu como as sessões são estruturadas.
|
||||
- orientou o agente a fazer uma alteração pequena e específica nos cards dos jogos.
|
||||
- revisou a alteração na visualização de diff do espaço de trabalho.
|
||||
- executou o aplicativo localmente para confirmar a avaliação por estrelas no navegador.
|
||||
- abriu um pull request e fez o merge por conta própria no github.com.
|
||||
|
||||
Em seguida, você usará o aplicativo para adicionar um padrão de instruções personalizadas ao repositório, começando por uma das issues do backlog. Continue para a [Lição 3 - Orientar o Copilot com instruções personalizadas][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Trabalhar com sessões de agente no aplicativo GitHub Copilot][agent-sessions]
|
||||
- [Sobre o aplicativo GitHub Copilot][about-copilot-app]
|
||||
- [Gerenciar issues e pull requests com o aplicativo GitHub Copilot][managing-issues-prs]
|
||||
|
||||
[prior-lesson]: /pt-br/learning-hub/copilot-workshops/app/1-install-copilot-app/#instalar-e-configurar-o-aplicativo-github-copilot
|
||||
[next-lesson]: /pt-br/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+165
@@ -0,0 +1,165 @@
|
||||
---
|
||||
title: "Lição 3 - Orientar o Copilot com instruções personalizadas"
|
||||
description: "Use o aplicativo GitHub Copilot para adicionar ao repositório um padrão de instruções personalizadas, começando por uma issue do backlog e fazendo o merge da alteração como um pull request."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
O contexto é fundamental ao trabalhar com IA generativa. Se uma tarefa precisa ser realizada de determinada maneira ou se há informações de apoio que o Copilot deve conhecer, esse contexto precisa estar disponível. Uma das ferramentas mais eficientes para isso são os [arquivos de instruções][instruction-files], que descrevem não apenas *qual* código você deseja, mas *como* ele deve ser estruturado. Nesta lição, você adicionará um padrão de documentação ao repositório. Você fará isso da mesma forma que realizará a maior parte do trabalho daqui em diante: começando por uma issue do backlog e permitindo que o agente faça a alteração.
|
||||
|
||||
Nesta lição, você vai:
|
||||
|
||||
- explorar como as instruções do repositório e os arquivos de instruções com escopo de caminho chegam ao agente.
|
||||
- iniciar uma sessão a partir da issue de instruções no backlog.
|
||||
- pedir ao agente que adicione um padrão de documentação a `.github/copilot-instructions.md`.
|
||||
- revisar a alteração e fazer o merge dela como um pull request.
|
||||
|
||||
## Cenário
|
||||
|
||||
Como toda boa equipe de desenvolvimento, a Tailspin Toys tem diretrizes e requisitos para as práticas de desenvolvimento. Entre eles estão:
|
||||
|
||||
- A documentação deve ser adicionada ao código na forma de comentários de documentação TSDoc.
|
||||
- A formatação deve ser documentada e aplicada por meio de linting.
|
||||
|
||||
Com os arquivos de instruções, você garantirá que o Copilot tenha as informações certas para executar as tarefas de acordo com as práticas destacadas.
|
||||
|
||||
## Arquivos de instruções
|
||||
|
||||
As instruções personalizadas permitem fornecer contexto e preferências ao Copilot para que ele compreenda melhor seu estilo de programação e seus requisitos. Esse recurso ajuda a orientar o Copilot para obter sugestões e trechos de código mais relevantes. Você pode especificar convenções de código, bibliotecas e até os tipos de comentários que deseja incluir no código. É possível criar instruções para todo o repositório ou para tipos de arquivo específicos, fornecendo contexto no nível da tarefa.
|
||||
|
||||
Há dois tipos de arquivos de instruções:
|
||||
|
||||
- `.github/copilot-instructions.md`, um único arquivo de instruções enviado ao Copilot em **todas** as solicitações do repositório. Esse arquivo deve conter informações no nível do projeto, ou seja, contexto relevante para a maioria das solicitações enviadas ao Copilot pelo chat ou pela CLI. Isso pode incluir a pilha de tecnologias usada, uma visão geral do que está sendo criado, boas práticas e outras orientações globais.
|
||||
- Os arquivos `.github/instructions/*.instructions.md` podem ser criados para tarefas ou tipos de arquivo específicos. Você pode usá-los para fornecer diretrizes para determinadas linguagens, como TypeScript ou Astro, ou para tarefas como criar um componente de interface ou um novo conjunto de testes de unidade.
|
||||
|
||||
> [!NOTE]
|
||||
> O Copilot também oferece suporte a outros padrões para incorporar orientações por meio de AGENTS.md, CLAUDE.md e GEMINI.md, garantindo que ele sempre tenha o contexto correto.
|
||||
|
||||
### Boas práticas para gerenciar arquivos de instruções
|
||||
|
||||
Uma discussão completa sobre a criação de arquivos de instruções está fora do escopo do workshop. No entanto, os exemplos fornecidos no projeto de amostra demonstram uma abordagem representativa. Em termos gerais:
|
||||
|
||||
- Mantenha as instruções em `copilot-instructions.md` concentradas em orientações no nível do projeto, como uma descrição do que está sendo criado, a estrutura do projeto e os padrões globais de código.
|
||||
- Use arquivos `*.instructions.md` para fornecer instruções específicas para tipos de arquivo, como testes de unidade, componentes Astro e a camada de dados, ou para tarefas específicas.
|
||||
- Use linguagem natural. Mantenha as orientações claras. Forneça exemplos de como o código deve e não deve ser.
|
||||
|
||||
Não existe uma única maneira correta de criar arquivos de instruções, assim como não existe uma única maneira correta de usar IA. Com a experimentação, você descobrirá o que funciona melhor para seu projeto.
|
||||
|
||||
> [!TIP]
|
||||
> Todo projeto que usa o GitHub Copilot deve ter uma coleção robusta de arquivos de instruções. Ao explorar os arquivos deste projeto, você perceberá que há instruções para vários tipos de arquivos de código.
|
||||
>
|
||||
> Procura modelos ou um ponto de partida? Explore o [awesome-copilot][awesome-copilot], um repositório repleto de arquivos de instruções, agentes personalizados e outros recursos.
|
||||
|
||||
## Explorar os arquivos de instruções personalizadas deste projeto
|
||||
|
||||
Reserve um momento para ler os arquivos de instruções incluídos no repositório. Há um arquivo principal `copilot-instructions.md` e uma coleção de arquivos `*.instructions.md` para várias tarefas. Abra-os no editor ou na interface Web do GitHub.
|
||||
|
||||
1. Se o painel de revisão ainda não estiver visível, abra-o selecionando **Toggle review panel** no canto superior direito.
|
||||
|
||||
|
||||
|
||||
2. Selecione **+** para adicionar um novo item ao painel de revisão.
|
||||
3. Selecione **File**.
|
||||
4. Pesquise `copilot-instructions.md`.
|
||||
5. Selecione `copilot-instructions.md` na lista de arquivos para abri-lo.
|
||||
6. Explore o arquivo. Observe a breve descrição do projeto e seções como **Agent notes**, **Code standards**, **Scripts** e **Repository Structure**. Em **Code standards**, observe a orientação aninhada **GitHub Actions Workflows**. Essas instruções se aplicam a qualquer interação com o Copilot.
|
||||
7. Selecione **Show folder view** para abrir o navegador de pastas.
|
||||
|
||||
|
||||
|
||||
8. Acesse a pasta `.github/instructions` e explore os arquivos. Observe que há instruções para arquivos Astro, a camada de dados Drizzle, testes e muito mais.
|
||||
9. Abra `.github/instructions/unit-tests.instructions.md`. Observe o campo `applyTo` na parte superior. Ele define um glob, relativo à raiz do repositório, que determina a quais arquivos as instruções se aplicam. Nesse caso, qualquer arquivo de teste TypeScript, por exemplo um arquivo correspondente a `**/*.test.ts`, será incluído.
|
||||
10. Observe as instruções específicas para criar testes de unidade neste projeto.
|
||||
11. Por fim, abra `.github/instructions/drizzle.instructions.md` e role até o final. Observe os links para outros arquivos de instruções, como `unit-tests.instructions.md`, e para arquivos existentes no projeto. Isso permite dividir conjuntos maiores de instruções em arquivos menores e reutilizáveis e indicar ao Copilot exemplos a serem seguidos ao gerar código. Os caminhos ali são relativos ao arquivo de instruções, e não à raiz do repositório.
|
||||
|
||||
> [!NOTE]
|
||||
> A seção **Code formatting requirements** em `copilot-instructions.md` documenta os padrões de código do projeto, mas ainda não exige documentação no código. Nas próximas etapas, você adicionará regras para comentários de documentação TSDoc e cabeçalhos de comentários nos arquivos.
|
||||
|
||||
## Começar pela issue de instruções
|
||||
|
||||
Na lição anterior, você iniciou uma sessão com um prompt direto. No entanto, a maior parte do trabalho começa com uma issue. Vamos criar uma nova sessão com base em uma issue criada para atualizar os arquivos de instruções e depois solicitar a atualização.
|
||||
|
||||
> [!NOTE]
|
||||
> Como os arquivos de instruções têm grande impacto no código gerado pelo Copilot, é preciso garantir que eles orientem o Copilot com clareza. Permitir que o Copilot crie uma primeira versão, como você fará nesta lição, é uma ótima abordagem. Depois, revise o resultado para confirmar que as atualizações atendem aos requisitos.
|
||||
|
||||
1. Selecione **My work** na barra lateral.
|
||||
2. Selecione a issue intitulada **Update our repository coding standards** para abri-la.
|
||||
3. Selecione **New session** no canto superior direito para iniciar uma nova sessão com base na issue.
|
||||
|
||||
|
||||
|
||||
4. Use o prompt a seguir para solicitar que o Copilot atualize os arquivos de instruções de acordo com os requisitos documentados na issue:
|
||||
|
||||
```plaintext
|
||||
Following this issue, make the updates to the instructions files in this project to meet the requirements documented. Don't create the PR quite yet!
|
||||
```
|
||||
|
||||
O Copilot fará as atualizações.
|
||||
|
||||
## Revisar a alteração
|
||||
|
||||
Vamos ler as atualizações feitas pelo Copilot e também pedir um exemplo do código que ele passará a gerar com base nas instruções atualizadas.
|
||||
|
||||
1. Selecione **Changes** no canto superior direito para abrir as alterações no código.
|
||||
|
||||
|
||||
|
||||
2. Revise o arquivo de instruções atualizado. Confirme se ele contém as diretrizes para adicionar documentação e comentários ao código.
|
||||
|
||||
> [!NOTE]
|
||||
> Como a IA é probabilística, e não determinística, o texto exato pode variar.
|
||||
|
||||
3. Use o prompt a seguir para pedir ao Copilot que crie um exemplo do código que passará a gerar:
|
||||
|
||||
```plaintext
|
||||
Do not make any updates, but show me what the code would look like. Based on the new instructions, if I asked Copilot to create a new library component to return all Publishers what would that code look like?
|
||||
```
|
||||
|
||||
4. Revise o código proposto pelo Copilot. Observe os comentários de documentação TSDoc e o comentário de cabeçalho do arquivo, exatamente como solicitado pelas instruções atualizadas.
|
||||
|
||||
Você atualizou os arquivos de instruções do projeto e viu o impacto que eles terão.
|
||||
|
||||
## Abrir e fazer merge do pull request
|
||||
|
||||
Os arquivos de instruções se tornam ativos do repositório, portanto são compartilhados com o restante da equipe. Vamos criar um PR com esse trabalho, como faríamos com qualquer outro ativo.
|
||||
|
||||
1. No canto superior direito, selecione **Create PR**.
|
||||
2. Se solicitado, selecione **Sign in with your browser** e siga as instruções para se autenticar.
|
||||
3. O Copilot começará a criar o PR.
|
||||
|
||||
Após a criação do PR, o Copilot monitorará os fluxos de trabalho do repositório que precisam ser executados. Depois de alguns instantes, o botão no canto superior direito mudará para **Ready to merge**, indicando que o PR está pronto para o merge.
|
||||
|
||||
4. Selecione **Ready to merge**.
|
||||
5. Na nova caixa de diálogo, selecione **Merge pull request** para fazer o merge do pull request.
|
||||
|
||||
> [!NOTE]
|
||||
> Depois que o padrão for integrado à branch padrão, ele fará parte do projeto para toda a equipe e para cada nova sessão. Quando você iniciar a sessão de filtragem na próxima lição a partir de uma branch padrão atualizada, o agente seguirá esse padrão automaticamente. O código TypeScript gerado incluirá comentários de documentação TSDoc sem que você precise solicitá-los, uma demonstração pequena, mas concreta, de como as instruções moldam o código gerado.
|
||||
|
||||
## Resumo e próximos passos
|
||||
|
||||
Você explorou como o aplicativo obtém contexto dos arquivos de instruções e usou uma sessão para adicionar e integrar um padrão para todo o repositório. Especificamente, você:
|
||||
|
||||
- explorou o arquivo `copilot-instructions.md` do repositório e os arquivos `*.instructions.md` com escopo de caminho.
|
||||
- iniciou uma sessão a partir da issue de instruções no backlog.
|
||||
- pediu ao agente que adicionasse um padrão de documentação a `.github/copilot-instructions.md`.
|
||||
- revisou a alteração e fez o merge dela como um pull request.
|
||||
|
||||
Em seguida, você criará o recurso de filtragem em uma nova sessão e verá como ele adota o padrão que acabou de integrar. Continue para a [Lição 4 - Criar um recurso com o Autopilot][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Arquivos de instruções para personalização do GitHub Copilot][instruction-files]
|
||||
- [Personalizar o aplicativo GitHub Copilot][customize-app]
|
||||
- [Boas práticas para criar instruções personalizadas][instructions-best-practices]
|
||||
- [Awesome Copilot — uma coleção de arquivos de instruções e outros recursos][awesome-copilot]
|
||||
|
||||
[next-lesson]: /pt-br/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[instruction-files]: https://docs.github.com/copilot/customizing-copilot/about-customizing-github-copilot-chat-responses
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[awesome-copilot]: https://awesome-copilot.github.com/
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+186
@@ -0,0 +1,186 @@
|
||||
---
|
||||
title: "Lição 4 - Criar um recurso com o Autopilot"
|
||||
description: "Use os modos Plan e Autopilot no aplicativo GitHub Copilot para criar um recurso estático de filtragem no lado do cliente, observar como ele herda seu padrão de documentação e verificá-lo com uma skill de agente."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Até agora, fizemos algumas pequenas atualizações no projeto. No entanto, alterações mais robustas exigem um processo mais completo. O aplicativo GitHub Copilot foi criado para trabalhar com nosso fluxo existente e ajudar a garantir que criemos as soluções certas da maneira correta. Esta é a primeira de três lições nas quais você seguirá um processo típico de desenvolvimento, começando por usar uma issue para gerar um novo recurso e uma skill de agente para executar os testes de validação e os linters.
|
||||
|
||||
Nesta lição, você vai:
|
||||
|
||||
- iniciar uma nova sessão a partir da issue de filtragem.
|
||||
- usar o modo **Plan** para planejar o recurso e depois o **Autopilot** para criá-lo.
|
||||
- confirmar que o código gerado segue o padrão de documentação integrado anteriormente.
|
||||
- verificar o trabalho com a skill `quality-checks` do projeto.
|
||||
|
||||
## Cenário
|
||||
|
||||
A página inicial lista todos os jogos, mas os visitantes não conseguem restringir a lista. A issue de filtragem solicita que eles possam filtrar jogos por **categoria** e **distribuidora**. Vamos usar o Copilot para implementar essa funcionalidade.
|
||||
|
||||
## Contexto
|
||||
|
||||
Introduzir agentes de programação com IA no fluxo de desenvolvimento não muda os fundamentos. Na verdade, eles se tornam ainda mais importantes. A maioria das pessoas desenvolvedoras segue um fluxo semelhante a este:
|
||||
|
||||
1. Abrir uma issue com os detalhes do que precisa ser feito.
|
||||
2. Criar um plano do que precisa ser desenvolvido.
|
||||
3. Criar e revisar o código.
|
||||
4. Executar os testes para validar o código.
|
||||
5. Validar manualmente a nova funcionalidade.
|
||||
6. Criar um pull request (PR).
|
||||
7. Depois que o código for revisado e o processo de integração contínua for concluído com êxito, fazer o merge do código.
|
||||
|
||||
> [!NOTE]
|
||||
> Os detalhes exatos variam de acordo com sua equipe e organização, mas a maioria dos fluxos será uma variação do processo descrito acima.
|
||||
|
||||
Ao seguir essa abordagem padrão, você garante que o código gerado por IA atenda aos requisitos definidos e passe pelo mesmo processo de avaliação do código escrito manualmente.
|
||||
|
||||
## Modos de sessão
|
||||
|
||||
O **modo de sessão** controla o grau de autonomia do agente. Você pode defini-lo no menu suspenso abaixo do campo de prompt e alterá-lo a qualquer momento:
|
||||
|
||||
- **Interactive**: você e o agente trabalham em conjunto. O agente sugere alterações e aguarda sua orientação antes de prosseguir.
|
||||
- **Plan**: o agente cria primeiro um plano. Você revisa e aprova o plano antes que o agente o execute.
|
||||
- **Autopilot**: o agente trabalha com total autonomia, escrevendo código, executando testes e iterando sem aguardar sua orientação.
|
||||
|
||||
## Planejar o recurso de filtragem
|
||||
|
||||
O melhor momento para detectar um possível problema é antes que qualquer código seja escrito, e a melhor maneira de fazer isso é planejar com antecedência. Ao planejar com o Copilot, você pedirá que ele gere um conjunto de etapas e documente a abordagem que seguirá. Em seguida, poderá revisar o plano e fazer sugestões para melhorá-lo antes de permitir que o Copilot gere o código com base nele.
|
||||
|
||||
Vamos abrir a issue, iniciar uma nova sessão e criar um plano alternando para o modo Plan e fazendo a solicitação.
|
||||
|
||||
1. Selecione **My work** na aba de navegação.
|
||||
2. Selecione a issue intitulada **Allow users to filter games by category and publisher**.
|
||||
3. Selecione **New session** no canto superior direito.
|
||||
|
||||
|
||||
|
||||
4. Selecione <kbd>Shift</kbd>+<kbd>Tab</kbd> até que o modo exibido seja **Plan**.
|
||||
|
||||
|
||||
|
||||
5. Envie o prompt a seguir. A issue de filtragem já está no contexto da sessão porque você iniciou a partir dela:
|
||||
|
||||
```plaintext
|
||||
Plan the work based on the requirements documented in the issue. Please ask any clarifying questions you might have as you build the plan.
|
||||
```
|
||||
|
||||
6. O agente pode fazer perguntas complementares enquanto cria o plano. Responda com base em como você criaria o recurso.
|
||||
|
||||
> [!NOTE]
|
||||
> Como o Copilot é probabilístico, as perguntas complementares exatas podem variar. Na verdade, ele pode não fazer nenhuma pergunta. Isso é perfeitamente normal.
|
||||
|
||||
7. Ao terminar, o Copilot apresentará um resumo do plano. Revise-o. Ele deve propor a criação de consultas, a adição de controles de filtro e, naturalmente, testes. Se desejar, forneça feedback para refiná-lo. O agente incorporará suas sugestões em uma nova versão.
|
||||
|
||||
## Criar com o Autopilot
|
||||
|
||||
Com o plano pronto, vamos permitir que o Copilot crie a implementação.
|
||||
|
||||
1. Na lista de opções da caixa de diálogo **Plan summary**, selecione a opção mais próxima de **Approve and implement with autopilot**.
|
||||
|
||||
O Copilot começará a trabalhar na implementação.
|
||||
|
||||
> [!NOTE]
|
||||
> Se o Copilot não começar a criar automaticamente o código necessário, você poderá solicitar isso com um prompt como "Go ahead and start building out the plan!".
|
||||
>
|
||||
> A criação das atualizações necessárias levará vários minutos. O agente edita e cria arquivos, escreve e executa testes e faz iterações. Este é um bom momento para refletir sobre o que você explorou até agora ou fazer uma pausa.
|
||||
|
||||
## Revisar as alterações
|
||||
|
||||
Todo código gerado por IA precisa ser revisado antes do merge. Vamos revisar o código e executar o site para confirmar que tudo está correto.
|
||||
|
||||
1. Selecione **Changes** no canto superior direito para abrir as alterações no código.
|
||||
|
||||
|
||||
|
||||
2. Revise as alterações. Você deverá ver novos arquivos TypeScript e Astro, além de arquivos de teste. Observe que as novas funções auxiliares incluem comentários de documentação TSDoc e um comentário de cabeçalho do arquivo. O padrão de documentação integrado na Lição 3 foi aplicado automaticamente, sem que você precisasse solicitá-lo.
|
||||
3. No painel de revisão à direita do aplicativo Copilot, selecione **Terminal**. Se não houver um botão **Terminal**, selecione **+** (identificado como **Open in panel**) e depois selecione **Terminal**.
|
||||
|
||||
|
||||
|
||||
4. Digite o comando a seguir na janela do terminal para iniciar o servidor de desenvolvimento do aplicativo Web:
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
5. Quando o servidor iniciar, o que levará apenas alguns instantes, abra uma janela do navegador.
|
||||
6. Acesse http://localhost:4321.
|
||||
7. Agora você deve ver filtros disponíveis na página inicial.
|
||||
8. Se algo não estiver correto, peça ao Copilot que faça as atualizações.
|
||||
9. Quando estiver tudo certo, volte à janela do terminal.
|
||||
10. Selecione <kbd>Ctrl</kbd>+<kbd>C</kbd> para interromper o servidor de desenvolvimento.
|
||||
|
||||
## Verificar o trabalho com a skill quality-checks
|
||||
|
||||
Você poderia apenas examinar o diff e considerar o trabalho concluído, mas a equipe definiu um padrão de qualidade e uma maneira repetível de verificá-lo.
|
||||
|
||||
As **skills de agente** permitem fornecer ao Copilot orientações sobre como executar tarefas repetíveis, como executar testes, gerar builds ou criar pull requests. Uma skill é uma pasta de instruções, scripts e recursos que o agente pode carregar sob demanda. [Agent Skills é um padrão aberto][agent-skills-repo] usado por vários agentes. Por isso, a mesma skill funciona no Copilot Chat em modo de agente, no agente de nuvem do Copilot, no Copilot CLI e no aplicativo GitHub Copilot.
|
||||
|
||||
As skills ficam na pasta `.github/skills` de um projeto ou globalmente em `~/.copilot/skills`. Cada skill é uma pasta que contém um arquivo `SKILL.md` com frontmatter YAML, formado por `name` e `description`, seguido pelas instruções em Markdown:
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: quality-checks
|
||||
description: Run the project's test suites and linter to verify code changes are ready to commit, push, or merge.
|
||||
---
|
||||
```
|
||||
|
||||
As skills também podem incluir subpastas com scripts, ativos e materiais de referência. A estrutura completa é descrita na [especificação de skills de agente][agent-skills-spec].
|
||||
|
||||
> [!TIP]
|
||||
> As skills são carregadas dinamicamente. O agente decide qual skill se aplica com base no campo `description`. Uma descrição clara e específica para o cenário é o que diferencia uma skill usada de uma ignorada.
|
||||
|
||||
## Explorar a skill quality-checks
|
||||
|
||||
Vamos explorar a skill para entender o que ela faz.
|
||||
|
||||
1. Se o painel de revisão ainda não estiver visível, abra-o selecionando **Toggle review panel** no canto superior direito.
|
||||
|
||||
|
||||
|
||||
2. Selecione **+** para adicionar um novo item ao painel de revisão.
|
||||
3. Selecione **File**.
|
||||
4. Pesquise `SKILL.md`.
|
||||
5. Selecione `SKILL.md .github/skills/quality-checks` na lista de arquivos para abri-lo.
|
||||
6. Observe `name` e `description`. A descrição informa ao agente *quando* usar a skill: sempre que alterações no código precisarem ser testadas, verificadas por lint ou validadas antes de um commit, push ou merge.
|
||||
7. Leia a skill. Observe que ela documenta qual script executa cada conjunto, como testes de unidade, testes de ponta a ponta do Playwright e ESLint, em que ordem e como depurar falhas comuns. Assim, o agente executa as verificações da maneira definida pela equipe, em vez de tentar adivinhar.
|
||||
|
||||
## Executar as verificações
|
||||
|
||||
Na mesma sessão de filtragem, peça ao agente que verifique o trabalho. Você não precisará nomear a skill, pois o agente a associará à sua solicitação.
|
||||
|
||||
1. Volte ao aplicativo Copilot.
|
||||
2. Chame diretamente a skill usando o comando de barra `/quality-checks` e selecione <kbd>Enter</kbd>.
|
||||
3. Seguindo a skill, o agente executa os testes de unidade, o linter e os testes de ponta a ponta e relata os resultados. Se algo falhar, peça que ele corrija o problema e execute novamente as verificações até que tudo passe.
|
||||
4. **Mantenha esta sessão aberta.** Na próxima lição, você adicionará o servidor MCP do Playwright e o usará para ver o recurso de filtragem funcionando em um navegador real.
|
||||
|
||||
## Resumo e próximos passos
|
||||
|
||||
Você criou um recurso real de ponta a ponta e o verificou de acordo com o padrão da equipe. Especificamente, você:
|
||||
|
||||
- iniciou uma nova sessão a partir da issue de filtragem em um projeto atualizado.
|
||||
- usou o modo Plan para planejar o recurso e o Autopilot para criá-lo.
|
||||
- confirmou que o código auxiliar gerado seguiu o padrão de documentação integrado na Lição 3.
|
||||
- verificou o trabalho com a skill `quality-checks`.
|
||||
|
||||
Em seguida, você conectará o servidor MCP do Playwright e pedirá ao agente que explore o recurso de filtragem em um navegador real. Continue para a [Lição 5 - Testar com o servidor MCP do Playwright][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Trabalhar com sessões de agente no aplicativo GitHub Copilot][agent-sessions]
|
||||
- [Sobre Agent Skills][about-agent-skills]
|
||||
- [Personalizar o aplicativo GitHub Copilot][customize-app]
|
||||
- [Sobre sandboxes locais e na nuvem para o GitHub Copilot][sandboxes]
|
||||
|
||||
[ex0]: /pt-br/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex2]: /pt-br/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /pt-br/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[next-lesson]: /pt-br/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-agent-skills]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[agent-skills-repo]: https://github.com/agentskills/agentskills
|
||||
[agent-skills-spec]: https://agentskills.io/specification
|
||||
@@ -0,0 +1,86 @@
|
||||
---
|
||||
title: "Lição 5 - Testar com o servidor MCP do Playwright"
|
||||
description: "Adicione o servidor MCP do Playwright ao aplicativo GitHub Copilot e peça ao agente que teste manualmente o recurso de filtragem em um navegador real."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Na lição anterior, você criou e verificou o recurso de filtragem com o conjunto de testes automatizados do projeto. Os testes automatizam a validação do código, mas permitir que o agente confirme o comportamento é uma abordagem eficiente. Assim, o agente pode responder a problemas identificados na própria interface que está criando. Vamos explorar como o MCP dá aos agentes de IA acesso a recursos externos e adicionar o servidor MCP do Playwright para permitir que o Copilot interaja diretamente com o site que você está desenvolvendo.
|
||||
|
||||
Nesta lição, você vai:
|
||||
|
||||
- entender o que é o Model Context Protocol (MCP) e como o aplicativo GitHub Copilot o utiliza.
|
||||
- adicionar o servidor MCP do Playwright nas configurações do aplicativo.
|
||||
- pedir ao agente que controle um navegador e explore o recurso de filtragem.
|
||||
|
||||
## Cenário
|
||||
|
||||
Embora os testes de unidade e de ponta a ponta sejam importantes, validar atualizações na interface exige interagir com ela. Você quer permitir que o Copilot use o site em desenvolvimento como uma pessoa usuária faria, automatizando ainda mais o processo de alteração e aumentando a confiança de que as atualizações se comportam conforme o esperado.
|
||||
|
||||
## O que é o Model Context Protocol (MCP)?
|
||||
|
||||
O [Model Context Protocol (MCP)][mcp-blog-post] oferece aos agentes de IA uma forma de se comunicar com ferramentas e serviços externos em tempo real. Isso permite que eles acessem informações atualizadas, usando recursos, e realizem ações em seu nome, usando ferramentas.
|
||||
|
||||
Essas ferramentas e esses recursos são acessados por meio de um servidor MCP, que funciona como uma ponte entre o agente de IA e as ferramentas e os serviços externos. O servidor MCP é responsável por gerenciar essa comunicação, seja com APIs existentes ou com ferramentas locais, como pacotes NPM. Cada servidor MCP representa um conjunto diferente de ferramentas e recursos que o agente de IA pode acessar.
|
||||
|
||||
Alguns servidores MCP conhecidos são:
|
||||
|
||||
- [**GitHub MCP Server**](https://github.com/github/github-mcp-server): oferece acesso a um conjunto de APIs para gerenciar repositórios do GitHub. Ele permite que o agente de IA realize ações como criar repositórios, atualizar repositórios existentes e gerenciar issues e pull requests.
|
||||
- [**Playwright MCP Server**][playwright-mcp-server]: oferece recursos de automação de navegador usando o Playwright. Ele permite que o agente de IA realize ações como acessar páginas Web, preencher formulários e selecionar botões.
|
||||
|
||||
Há muitos outros servidores MCP que fornecem acesso a diferentes ferramentas e recursos. O GitHub mantém um [registro de MCP](https://github.com/mcp) para facilitar a descoberta e as contribuições ao ecossistema.
|
||||
|
||||
> [!CAUTION]
|
||||
> Trate os servidores MCP como qualquer outra dependência do projeto. Antes de usar um servidor MCP, revise cuidadosamente o código-fonte, verifique quem o publicou e considere as implicações de segurança. Use apenas servidores MCP confiáveis e tenha cuidado ao conceder acesso a recursos ou operações confidenciais.
|
||||
|
||||
## Adicionar o servidor MCP do Playwright
|
||||
|
||||
Você adiciona e gerencia servidores MCP nas configurações do aplicativo. O aplicativo inclui um catálogo de servidores conhecidos, portanto o [servidor MCP do Playwright][playwright-mcp-server] está a poucas seleções de distância.
|
||||
|
||||
1. Selecione <kbd>Ctrl</kbd>+<kbd>,</kbd> para abrir a página de configurações do aplicativo Copilot.
|
||||
2. Selecione **MCP servers**.
|
||||
3. Na caixa de diálogo de pesquisa, digite `Playwright`.
|
||||
4. Selecione **Playwright** na lista de **Popular MCP servers**.
|
||||
5. Selecione **Add server** para adicioná-lo à lista de servidores MCP disponíveis.
|
||||
6. Selecione <kbd>Esc</kbd> para fechar a caixa de diálogo de configurações.
|
||||
|
||||
Você adicionou o servidor MCP do Playwright.
|
||||
|
||||
## Pedir ao Copilot que explore o recurso com o Playwright
|
||||
|
||||
Vamos pedir ao Copilot que teste manualmente o recurso usando o servidor MCP do Playwright.
|
||||
|
||||
1. Use o prompt a seguir para pedir ao Copilot que valide a nova funcionalidade:
|
||||
|
||||
```plaintext
|
||||
Start the dev server then use the Playwright MCP server to validate the functionality you just added exists. Use the details in the issue to ensure the newly added behavior matches the specs.
|
||||
```
|
||||
|
||||
O Copilot iniciará um navegador por meio do servidor MCP do Playwright, percorrerá cada etapa e relatará o que encontrou. Você verá um navegador ser aberto no sistema para executar as tarefas.
|
||||
|
||||
2. Leia o resumo e compare-o aos critérios de aceitação da issue. Se algo parecer incorreto, faça perguntas complementares ou peça que o agente corrija o código antes de abrir um pull request.
|
||||
3. Mantenha esta sessão aberta, pois vamos concluí-la na próxima lição.
|
||||
|
||||
O Copilot também validou a funcionalidade no navegador, explorando o recurso como uma pessoa usuária faria.
|
||||
|
||||
## Resumo e próximos passos
|
||||
|
||||
Parabéns! Você usou o servidor MCP do Playwright para explorar o recurso em um navegador real a partir do aplicativo GitHub Copilot. Recapitulando, você:
|
||||
|
||||
- aprendeu o que é o Model Context Protocol (MCP) e como o aplicativo disponibiliza ferramentas MCP.
|
||||
- adicionou o servidor MCP do Playwright nas configurações do aplicativo.
|
||||
- pediu ao agente que controlasse um navegador e explorasse o recurso de filtragem.
|
||||
|
||||
O recurso está criado, verificado e funcionando. Agora é hora de entregá-lo usando o **Agent Merge** para abrir e fazer o merge do pull request. Continue para a [Lição 6 - Fazer merge com o Agent Merge][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [O que é MCP e por que todos estão falando sobre ele?][mcp-blog-post]
|
||||
- [Servidor MCP do Microsoft Playwright][playwright-mcp-server]
|
||||
- [Configurar servidores MCP no aplicativo GitHub Copilot][customize-app]
|
||||
|
||||
[next-lesson]: /pt-br/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[mcp-blog-post]: https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/
|
||||
[playwright-mcp-server]: https://github.com/microsoft/playwright-mcp
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
@@ -0,0 +1,67 @@
|
||||
---
|
||||
title: "Lição 6 - Fazer merge com o Agent Merge"
|
||||
description: "Abra o pull request de filtragem, revise-o em My work e permita que o Agent Merge corrija o que estiver bloqueando e faça o merge para você, no nível mais alto da automação de merge."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
O recurso de filtragem está criado, verificado e funcionando em um navegador. A última etapa é fazer o merge. Você já fez isso duas vezes neste percurso. Nas duas ocasiões, abriu o pull request e fez o merge por conta própria no github.com. Desta vez, o aplicativo fará o trabalho operacional com o **Agent Merge**, que conduz todo o ciclo de vida de um pull request dentro do aplicativo.
|
||||
|
||||
Nesta lição, você vai:
|
||||
|
||||
- aprender o que é o Agent Merge e como ele automatiza o ciclo de vida do merge.
|
||||
- habilitar o Agent Merge na sessão de filtragem.
|
||||
- observar como ele cria o pull request, executa a CI e faz o merge quando todas as verificações passam.
|
||||
|
||||
## Cenário
|
||||
|
||||
Nos últimos módulos, você explorou vários níveis de automação, desde a criação de código até permitir que o Copilot valide diretamente uma interface. Para acelerar ainda mais o desenvolvimento, a Tailspin Toys quer descobrir se pull requests já avaliados e validados podem ter o merge feito automaticamente.
|
||||
|
||||
## Apresentação do Agent Merge
|
||||
|
||||
O **Agent Merge** permite automatizar a etapa final de integração de um pull request por meio do aplicativo Copilot. Quando você o habilita, a sessão do aplicativo lê o pull request, resolve o que estiver bloqueando o merge, como verificações de CI com falha, comentários de revisão e a necessidade de rebase, e faz o merge assim que o GitHub permite. Ele é executado em segundo plano, continua funcionando após reinicializações do aplicativo e é desativado automaticamente quando o pull request é integrado.
|
||||
|
||||
Até aqui, você selecionou **Merge pull request** no github.com. O Agent Merge transfere essa responsabilidade ao agente, permitindo que você passe para a próxima tarefa enquanto ele conduz o PR até a conclusão. Você ainda revisa e aprova o trabalho; o agente apenas cuida das etapas operacionais finais.
|
||||
|
||||
## Usar o Agent Merge para gerenciar o PR
|
||||
|
||||
Você revisou o código manualmente, executou testes e permitiu que o Copilot validasse a interface. Agora é hora de integrar o novo código à base de código. Vamos permitir que o Agent Merge conduza o PR pela integração contínua (CI) e faça o merge.
|
||||
|
||||
1. Volte à sessão mantida aberta no módulo anterior, na qual você estava adicionando a funcionalidade de filtragem.
|
||||
2. No canto superior direito, selecione o menu suspenso ao lado de **Create PR**.
|
||||
3. Selecione **Agent merge** para habilitá-lo.
|
||||
|
||||
|
||||
|
||||
4. O texto do botão mudará para **Agent merge**.
|
||||
5. Selecione o botão **Agent merge** para iniciar o processo.
|
||||
|
||||
O aplicativo Copilot começará a criar e gerenciar o PR. Primeiro, ele explora o projeto para determinar a melhor maneira de criar um PR e depois cria o novo PR.
|
||||
|
||||
Após alguns instantes, você verá que o Copilot voltou a trabalhar, agora analisando as condições do PR, incluindo o processo de CI que executa todos os testes do repositório. Ele informará o status das revisões deixadas por outras pessoas da equipe, das verificações que precisam ser executadas e da possibilidade de fazer o merge do PR.
|
||||
|
||||
6. Permita que o Agent Merge faça o merge do pull request selecionando o menu suspenso ao lado de **Agent merge** e depois **Merge pull request**.
|
||||
|
||||
|
||||
|
||||
7. Quando todos os processos de CI estiverem verdes, indicando que os testes passaram, o Copilot fará o merge do pull request.
|
||||
|
||||
## Resumo e próximos passos
|
||||
|
||||
Você automatizou várias partes do processo de desenvolvimento, incluindo a geração, o teste e a validação de código e, agora, o processo de pull request. Você:
|
||||
|
||||
- aprendeu o que é o Agent Merge e como ele automatiza o ciclo de vida do merge.
|
||||
- habilitou o Agent Merge na sessão de filtragem.
|
||||
- observou como ele criou o pull request, executou a CI e fez o merge quando todas as verificações passaram.
|
||||
|
||||
Em seguida, você explorará **canvases**, uma maneira mais completa de planejar e visualizar o trabalho com o agente. Continue para a [Lição 7 - Planejar com canvases][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Gerenciar issues e pull requests com o aplicativo GitHub Copilot][managing-issues-prs]
|
||||
- [Sobre o aplicativo GitHub Copilot][about-copilot-app]
|
||||
|
||||
[next-lesson]: /pt-br/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,127 @@
|
||||
---
|
||||
title: "Lição 7 - Planejar com canvases"
|
||||
description: "Crie um canvas compartilhado e orientado por agentes no aplicativo GitHub Copilot para planejar e acompanhar seu trabalho junto com o agente."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Até agora, você orientou agentes pelo chat. No entanto, grande parte do trabalho não acontece em uma conversa, mas em um quadro, documento ou checklist. Os **canvases** oferecem a você e ao agente uma superfície compartilhada exatamente para esse tipo de trabalho, dentro do aplicativo. Nesta lição, você criará um canvas simples para planejar e acompanhar o backlog no qual vem trabalhando.
|
||||
|
||||
Nesta lição, você vai:
|
||||
|
||||
- entender o que é um canvas e quando usá-lo.
|
||||
- criar um canvas compartilhado de quadro Kanban para fazer a triagem do backlog.
|
||||
- salvar o canvas no repositório e integrá-lo para a equipe.
|
||||
- abrir o canvas em uma nova sessão e começar a trabalhar a partir dele.
|
||||
|
||||
## Cenário
|
||||
|
||||
Analisar uma lista de issues pode ser uma tarefa desafiadora, mesmo nas melhores condições. As pessoas desenvolvedoras da Tailspin Toys procuram uma ferramenta que permita fazer rapidamente a triagem de issues e começar a trabalhar nelas no aplicativo Copilot.
|
||||
|
||||
## O que é um canvas?
|
||||
|
||||
Um [canvas][canvas-docs] é uma superfície interativa e compartilhada para um artefato de trabalho, como um plano, um quadro de triagem, um checklist de lançamento, um painel ou um documento. Embora o chat seja ótimo para descrever intenções e analisar ambiguidades, a maior parte do trabalho acontece em uma *superfície*. Os canvases permitem colaborar com o agente diretamente nessa superfície.
|
||||
|
||||
Os canvases são **bidirecionais**: o agente pode atualizar o canvas enquanto trabalha, e você pode editar a mesma superfície. Quando você cria um canvas, o agente o desenvolve com base no prompt e no fluxo de trabalho. Você pode pedir que ele adicione, remova ou revise recursos durante o processo. Depois de criado, o canvas é aberto no painel direito do aplicativo.
|
||||
|
||||
Alguns exemplos comuns incluem:
|
||||
|
||||
- **Canvases Markdown** para planejar o dia e priorizar issues e pull requests.
|
||||
- **Quadros Kanban agênticos** nos quais pessoas e agentes adicionam cards e movem o trabalho entre colunas.
|
||||
- **Quadros de triagem de issues** que resumem as principais issues e os temas recorrentes de um repositório.
|
||||
|
||||
## Por que usar um canvas?
|
||||
|
||||
Use um canvas quando uma tarefa exigir estrutura, iteração e verificação e o chat não for suficiente. Um canvas permite:
|
||||
|
||||
- fundamentar o trabalho do agente em um artefato real adequado ao seu fluxo de trabalho.
|
||||
- orientar ou corrigir o trabalho diretamente na superfície compartilhada e depois permitir que o agente continue a partir das suas alterações.
|
||||
- acompanhar o progresso como alterações visíveis em um artefato, e não apenas como respostas no chat.
|
||||
|
||||
## Criar um canvas para acompanhar o trabalho
|
||||
|
||||
Você já entregou muitos recursos: a avaliação por estrelas, o padrão de documentação e o recurso de filtragem foram integrados. No entanto, ainda há itens no backlog. Vamos criar um canvas para ajudar a fazer rapidamente a triagem do trabalho.
|
||||
|
||||
1. Volte ao aplicativo GitHub Copilot ou abra-o.
|
||||
2. Selecione **Home screen**.
|
||||
3. Verifique se `tailspin-toys` está selecionado como repositório.
|
||||
4. Na caixa de prompt, use o prompt a seguir para criar um canvas que atenda às nossas necessidades:
|
||||
|
||||
```plaintext
|
||||
Create a basic Kanban board canvas that allows me to quickly triage work. Highlight the three issues which are most likely to need attention right now, with the remainder in a second section down below. The top three cards should include a description of the issue's content and a justification of why they're at the top of the list. Each issue should have a button that allows me to add it to the current context for the current session so I can get to work on it straightaway.
|
||||
```
|
||||
|
||||
O Copilot começará a criar o canvas.
|
||||
|
||||
> [!NOTE]
|
||||
> A criação levará alguns minutos. Como essa é uma tarefa complexa, talvez a primeira versão não atenda a todas as suas expectativas. Você pode continuar enviando prompts para criar a ferramenta ideal para suas necessidades.
|
||||
|
||||
## Salvar o canvas e integrá-lo ao repositório
|
||||
|
||||
Os canvases podem se tornar ativos do repositório, assim como arquivos de instruções e skills. Vamos pedir ao Copilot que adicione o canvas ao repositório e faça o merge para que toda a equipe possa usá-lo.
|
||||
|
||||
1. Na mesma sessão, peça ao Copilot que salve o canvas no repositório usando o prompt a seguir:
|
||||
|
||||
```plaintext
|
||||
Let's save this canvas definition to the repository so I can share it with my development team
|
||||
```
|
||||
|
||||
2. Depois que o Copilot salvar os arquivos do canvas, selecione o menu suspenso ao lado de **Create PR** no canto superior direito.
|
||||
3. Selecione **Agent merge** para habilitá-lo.
|
||||
|
||||
|
||||
|
||||
4. O texto do botão mudará para **Agent merge**.
|
||||
5. Selecione o botão **Agent merge** para iniciar o processo.
|
||||
|
||||
O aplicativo Copilot começará a criar e gerenciar o PR. Primeiro, ele explora o projeto para determinar a melhor maneira de criar um PR e depois cria o pull request.
|
||||
|
||||
Após alguns instantes, você verá que o Copilot voltou a trabalhar, agora analisando as condições do PR, incluindo o processo de CI que executa todos os testes do repositório. Ele informará o status das revisões deixadas por outras pessoas da equipe, das verificações que precisam ser executadas e da possibilidade de fazer o merge do PR.
|
||||
|
||||
6. Permita que o Agent Merge faça o merge do pull request selecionando o menu suspenso ao lado de **Agent merge** e depois **Merge pull request**.
|
||||
|
||||
|
||||
|
||||
7. Aguarde até que todos os processos de CI sejam concluídos com êxito e fiquem verdes. Quando isso acontecer, o Copilot fará o merge do pull request automaticamente.
|
||||
|
||||
Você criou um novo canvas compartilhado para a equipe.
|
||||
|
||||
## Trabalhar no canvas
|
||||
|
||||
Com o canvas criado, vamos iniciar uma nova sessão e usá-lo.
|
||||
|
||||
1. No aplicativo Copilot, inicie uma nova sessão selecionando **New session** ao lado de **tailspin-toys**.
|
||||
2. Peça ao Copilot que abra o canvas de triagem usando o prompt a seguir:
|
||||
|
||||
```plaintext
|
||||
Open the triage issues canvas
|
||||
```
|
||||
|
||||
3. O canvas criado será aberto nessa nova sessão.
|
||||
4. Selecione **Add to current context** em uma das issues que mais lhe interessam.
|
||||
5. O Copilot começará a trabalhar na issue.
|
||||
|
||||
Você usou um canvas criado por você para otimizar o processo de desenvolvimento.
|
||||
|
||||
## Resumo e próximos passos
|
||||
|
||||
Você criou uma superfície compartilhada na qual você e o agente podem colaborar. Você:
|
||||
|
||||
- aprendeu o que são canvases e quando usá-los.
|
||||
- criou com o agente um canvas compartilhado de quadro Kanban para triagem.
|
||||
- salvou o canvas no repositório e fez o merge dele com o Agent Merge.
|
||||
- abriu o canvas em uma nova sessão e o usou para começar a trabalhar.
|
||||
|
||||
Com o backlog acompanhado, é hora de revisar tudo o que você criou e decidir os próximos passos. Continue para a [Lição 8 - Revisão e próximos passos][next-lesson].
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Trabalhar com extensões de canvas no aplicativo GitHub Copilot][canvas-docs]
|
||||
- [Canvases no Awesome Copilot][awesome-copilot-canvases]
|
||||
- [Sobre o aplicativo GitHub Copilot][about-copilot-app]
|
||||
|
||||
[next-lesson]: /pt-br/learning-hub/copilot-workshops/app/8-review/
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[awesome-copilot-canvases]: https://awesome-copilot.github.com/extensions/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,83 @@
|
||||
---
|
||||
title: "Lição 8 - Revisão e próximos passos"
|
||||
description: "Recapitule o percurso do aplicativo GitHub Copilot, automatize trabalhos recorrentes e explore os próximos passos."
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
Nas últimas lições, você levou um recurso da ideia ao merge com o aplicativo GitHub Copilot. Nesse processo, você:
|
||||
|
||||
- conectou um repositório e conheceu o espaço de trabalho do aplicativo e o backlog criado pelo modelo.
|
||||
- iniciou sessões a partir de uma tarefa direta e de issues e usou os modos Plan e Autopilot para controlar como o agente trabalha.
|
||||
- orientou o agente com instruções personalizadas e uma skill reutilizável.
|
||||
- testou o trabalho com o servidor MCP do Playwright em um navegador real.
|
||||
- colaborou com o agente em um canvas compartilhado.
|
||||
- entregou alterações avançando por níveis de automação de merge, desde fazer o merge por conta própria no github.com até permitir que o **Agent Merge** integrasse um pull request.
|
||||
|
||||
Vamos automatizar parte do trabalho recorrente, analisar boas práticas e explorar os próximos passos.
|
||||
|
||||
## Automatizar trabalhos recorrentes
|
||||
|
||||
O aplicativo pode executar agentes para você em uma agenda ou sob demanda por meio de **automações**, ideais para tarefas rotineiras como fazer a triagem de novas issues ou recapitular atividades recentes. Vamos criar uma automação simples e não destrutiva.
|
||||
|
||||
1. Selecione **Automations** na barra lateral e depois selecione **New automation**.
|
||||
2. Dê um nome a ela, como `Recap my recent work`.
|
||||
3. Escolha um gatilho. **Manual** permite executá-la sob demanda; **On a schedule** a executa automaticamente; **When an issue is created** reage a novas issues. Escolha **Manual** para esta lição.
|
||||
4. Insira um prompt somente leitura para impedir que a automação faça alterações. Por exemplo:
|
||||
|
||||
```plaintext
|
||||
Summarize the pull requests merged in this repository over the last week, and list any issues still open in the backlog.
|
||||
```
|
||||
|
||||
5. Escolha o projeto, ou seja, seu repositório Tailspin Toys, e crie a automação.
|
||||
6. Execute-a sob demanda para ver o resultado.
|
||||
|
||||
> [!TIP]
|
||||
> As automações podem ser executadas localmente ou na nuvem. Habilite **Run in the cloud** e escolha as **Tools** que uma automação pode usar quando quiser que ela seja executada sem supervisão e de acordo com uma agenda. Mantenha as automações agendadas com escopo limitado e sem ações destrutivas até confiar nos resultados.
|
||||
|
||||
## Boas práticas
|
||||
|
||||
Ao usar qualquer ferramenta de IA, a infraestrutura ao redor dela influencia a qualidade dos resultados. Arquivos de instruções, skills e agentes personalizados tiveram uma função neste workshop. Invista neles e reutilize-os entre as sessões.
|
||||
|
||||
Associe o **modo e o modelo** à tarefa. Use **Plan** para analisar uma abordagem antes de desenvolver, **Interactive** para acompanhar alterações específicas e **Autopilot** somente para tarefas isoladas e com escopo bem definido. Escolha um modelo mais rápido para edições rotineiras e um modelo mais avançado, com maior esforço de raciocínio, para trabalhos complexos.
|
||||
|
||||
O contexto continua tão importante quanto a infraestrutura. Descrever claramente *o que* você quer criar, *por que* e *como* muda significativamente o resultado. Os chats rápidos são ótimos para definir o escopo de uma ideia antes de transformá-la em uma sessão completa.
|
||||
|
||||
## Mais recursos para explorar
|
||||
|
||||
Você percorreu o fluxo de trabalho principal. Veja outros recursos que valem a pena conhecer:
|
||||
|
||||
- **Quick chats** para perguntas rápidas e descartáveis que não exigem uma sessão completa.
|
||||
- **Rubber duck** para analisar um problema e receber feedback relevante antes de começar a desenvolver.
|
||||
- [**Agentes personalizados**][custom-agents] para empacotar uma função, suas ferramentas e instruções para trabalhos especializados e repetíveis.
|
||||
- [`/chronicle`][chronicle] para gerar uma narrativa do que aconteceu em uma sessão.
|
||||
- [Bring your own key (BYOK)][byok] para usar modelos do seu próprio provedor, incluindo modelos locais por meio de Ollama, Foundry Local ou LM Studio.
|
||||
- [Sandboxes na nuvem][sandboxes] para executar sessões em um ambiente isolado hospedado pelo GitHub.
|
||||
- [Deep links][deep-links] para abrir o aplicativo diretamente em um repositório, uma sessão ou um prompt.
|
||||
|
||||
## Próximos passos
|
||||
|
||||
A melhor maneira de melhorar com qualquer ferramenta é continuar usando-a. Use-a em código de produção, em projetos pessoais ou naquele pequeno aplicativo que você planeja criar há anos. Compartilhe o que aprendeu com sua equipe e aprenda com as experiências dela. E, como sempre, explore a documentação.
|
||||
|
||||
Para conhecer melhor o ecossistema do GitHub Copilot, confira o [percurso do VS Code](/pt-br/learning-hub/copilot-workshops/vscode/), o [percurso do Copilot CLI](/pt-br/learning-hub/copilot-workshops/cli/) ou o [percurso do agente de nuvem](/pt-br/learning-hub/copilot-workshops/cloud/).
|
||||
|
||||
## Recursos
|
||||
|
||||
- [Sobre o aplicativo GitHub Copilot][about-copilot-app]
|
||||
- [Introdução ao aplicativo GitHub Copilot][getting-started]
|
||||
- [Personalizar o aplicativo GitHub Copilot][customize]
|
||||
- [Usar automações][using-automations]
|
||||
- [Trabalhar com extensões de canvas][canvas-docs]
|
||||
- [Sobre sandboxes locais e na nuvem][sandboxes]
|
||||
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[customize]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[using-automations]: https://docs.github.com/copilot/how-tos/github-copilot-app/using-automations
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[chronicle]: https://docs.github.com/copilot/how-tos/copilot-cli/use-copilot-cli/chronicle
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[byok]: https://docs.github.com/copilot/how-tos/github-copilot-app/use-byok-models
|
||||
[deep-links]: https://docs.github.com/copilot/how-tos/github-copilot-app/open-with-deep-links
|
||||
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: "Aplicativo GitHub Copilot"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
O [**aplicativo GitHub Copilot**](https://docs.github.com/copilot/concepts/agents/github-copilot-app) é um aplicativo para desktop criado com base no Copilot CLI que reúne o desenvolvimento orientado por agentes em um espaço de trabalho único e focado. Ele oferece sessões paralelas de agentes, modos de sessão alternáveis, canvases compartilhados e gerenciamento nativo de issues e pull requests do GitHub, incluindo o **Agent Merge**, que conduz um pull request por rebases, feedback de revisão, correções de CI e merge.
|
||||
|
||||
Ao longo destas lições, você instalará o aplicativo e configurará o projeto. Depois, conhecerá o espaço de trabalho do aplicativo e o backlog que o modelo criou para você. Você começará com uma pequena alteração, adicionando uma avaliação por estrelas, e então adicionará a partir de uma issue um padrão de instruções personalizadas, criará um recurso de filtragem em uma sessão isolada de agente e o verificará com uma skill reutilizável. Você adicionará o servidor MCP do Playwright para explorar o recurso em um navegador real e, em seguida, avançará por níveis de automação de merge até que o **Agent Merge** conclua o merge do pull request. Por fim, você colaborará em um canvas compartilhado e automatizará trabalhos recorrentes, completando todo o ciclo, da ideia ao recurso integrado.
|
||||
|
||||
## Lições
|
||||
|
||||
| Lição | Tópico | Descrição |
|
||||
|--------|-------|-------------|
|
||||
| [0. Pré-requisitos][ex0] | Configuração | Instale o Node.js e crie sua cópia do projeto Tailspin Toys |
|
||||
| [1. Instalar o aplicativo Copilot][ex1] | Configuração | Instale o aplicativo, conecte seu projeto e conheça o espaço de trabalho |
|
||||
| [2. Executar sua primeira sessão de agente][ex2] | Primeira alteração | Inicie uma sessão e entregue uma pequena alteração como seu primeiro pull request |
|
||||
| [3. Orientar o Copilot com instruções personalizadas][ex3] | Contexto | Adicione a partir de uma issue um padrão de documentação e faça o merge |
|
||||
| [4. Criar um recurso com o Autopilot][ex4] | Recurso principal | Use Plan e Autopilot para criar a filtragem e verifique-a com uma skill |
|
||||
| [5. Testar com o MCP do Playwright][ex5] | Ferramentas externas | Adicione o servidor MCP do Playwright e explore o recurso em um navegador |
|
||||
| [6. Fazer merge com o Agent Merge][ex6] | Merge | Permita que o Agent Merge corrija e integre o pull request de filtragem |
|
||||
| [7. Planejar com canvases][ex7] | Colaboração | Crie um canvas compartilhado para planejar e acompanhar seu trabalho |
|
||||
| [8. Revisão e próximos passos][ex8] | Resumo | Automatize tarefas recorrentes e explore os próximos passos |
|
||||
|
||||
## Pré-requisitos
|
||||
|
||||
Antes de participar deste workshop, verifique se você tem:
|
||||
|
||||
- [ ] Uma conta do GitHub com um plano ativo **Copilot Student, Pro, Pro+, Business ou Enterprise**
|
||||
- [ ] Um computador com **macOS, Linux ou Windows**
|
||||
- [ ] O [Git instalado][install-git] no computador
|
||||
|
||||
> [!TIP]
|
||||
> Não tem um plano pago? Estudantes verificados podem obter o GitHub Copilot gratuitamente por meio do [GitHub Education][callout-student-plan-education]. O plano **Copilot Student** inclui os recursos de agente, MCP, revisão de código e Copilot CLI usados neste workshop. Portanto, você pode concluir todos os percursos com esse plano.
|
||||
|
||||
> [!NOTE]
|
||||
> Como o aplicativo Copilot é executado no seu computador, e não em um codespace, a [Lição 0][ex0] orienta você na instalação do Node.js e na criação da sua cópia do projeto antes da instalação do aplicativo.
|
||||
|
||||
> [!NOTE]
|
||||
> Se você usa o Copilot Business ou o Copilot Enterprise, o administrador deve habilitar a política **Copilot CLI** para que você possa usar o aplicativo.
|
||||
|
||||
## Começar
|
||||
|
||||
[**Comece pela Lição 0: Pré-requisitos →**][ex0]
|
||||
|
||||
[ex0]: /pt-br/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex1]: /pt-br/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[ex2]: /pt-br/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /pt-br/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[ex4]: /pt-br/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[ex5]: /pt-br/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[ex6]: /pt-br/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[ex7]: /pt-br/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[ex8]: /pt-br/learning-hub/copilot-workshops/app/8-review/
|
||||
[install-git]: https://github.com/git-guides/install-git
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
@@ -0,0 +1,41 @@
|
||||
---
|
||||
title: "Mãos à obra com os agentes do GitHub Copilot"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
As adições recentes aos recursos do GitHub Copilot oferecem ferramentas avançadas para apoiar pessoas desenvolvedoras durante todo o ciclo de vida de desenvolvimento de software (SDLC). Isso inclui trabalhar com problemas e solicitações de pull no GitHub, interagir com serviços externos e, é claro, criar código. Este laboratório explora esses recursos e apresenta casos de uso reais e dicas para aproveitar as ferramentas ao máximo.
|
||||
|
||||
> [!CAUTION]
|
||||
> Como o GitHub Copilot é probabilístico, e não determinístico, o código exato, os arquivos alterados e outros detalhes podem variar. Por isso, talvez você perceba pequenas diferenças entre as capturas de tela e os trechos de código do laboratório e o que aparece em sua experiência. Isso é esperado e faz parte da natureza do trabalho com essa categoria de ferramentas.
|
||||
>
|
||||
> Se algo parecer quebrado ou não estiver funcionando corretamente, peça ajuda a uma pessoa mentora!
|
||||
|
||||
## Escolha seu ambiente
|
||||
|
||||
O GitHub Copilot acompanha você onde quer que trabalhe. Escolha o ambiente que corresponde à forma como você quer desenvolver e conclua os exercícios usando um backlog compartilhado da Tailspin Toys. Cada ambiente começa com sua própria configuração, para que você possa ir direto ao que escolheu.
|
||||
|
||||
### 🖥️ [VS Code](/pt-br/learning-hub/copilot-workshops/vscode/)
|
||||
|
||||
GitHub Copilot no **Visual Studio Code** e no GitHub Codespaces. Trabalhe com o modo de agente do Copilot Chat, servidores MCP e agentes personalizados sem sair do editor que você já usa — ideal para integrar a assistência de IA diretamente ao seu IDE.
|
||||
|
||||
### 💻 [Copilot CLI](/pt-br/learning-hub/copilot-workshops/cli/)
|
||||
|
||||
**GitHub Copilot CLI** — um assistente baseado em agentes que é executado no terminal. Instale-o, conecte servidores MCP, gere código com o modo de planejamento e crie suas próprias habilidades, agentes personalizados e comandos de barra, tudo pela linha de comando.
|
||||
|
||||
### 🤖 [Aplicativo Copilot](/pt-br/learning-hub/copilot-workshops/app/)
|
||||
|
||||
O **aplicativo GitHub Copilot** — um aplicativo para desktop criado com base no Copilot CLI. Execute sessões paralelas de agentes, alterne entre modos de sessão, colabore em telas e gerencie problemas e solicitações de pull do GitHub de forma nativa — incluindo o **Agent Merge**, que conduz uma solicitação de pull por rebases, comentários de revisão, correções de CI e mesclagem.
|
||||
|
||||
### ☁️ [Agente de nuvem do Copilot](/pt-br/learning-hub/copilot-workshops/cloud/)
|
||||
|
||||
**Agente de nuvem do Copilot** — um programador parceiro assíncrono que trabalha em problemas do GitHub em segundo plano. Atribua tarefas, oriente-o com agentes personalizados, acompanhe o progresso no painel de agentes e revise as solicitações de pull que ele abre.
|
||||
|
||||
## Cenário
|
||||
|
||||
Você é uma nova pessoa desenvolvedora na Tailspin Toys, uma empresa fictícia que oferece financiamento coletivo para jogos de tabuleiro com tema de desenvolvimento — um mercado enorme! O backlog da sua equipe já está registrado como problemas do GitHub e pronto para você começar — com trabalhos em funcionalidades, como filtragem e paginação, além de melhorias de qualidade, como acessibilidade e padrões de codificação. Você trabalhará de forma iterativa, explorando tanto o site quanto os recursos do Copilot para concluir as tarefas.
|
||||
|
||||
## Comece agora
|
||||
|
||||
Escolha um dos ambientes acima para começar — cada um é aberto com a configuração necessária para você iniciar o desenvolvimento.
|
||||
@@ -0,0 +1,85 @@
|
||||
---
|
||||
title: "第 0 课 - 先决条件"
|
||||
description: "为 GitHub Copilot app 课程做好准备：为 Tailspin Toys 项目安装 Node.js，并通过模板创建自己的存储库副本。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
GitHub Copilot app 是一款桌面应用，作为 Copilot 和 GitHub 的中央枢纽。它支持快速访问议题和拉取请求，也支持使用 GitHub Copilot 进行构建。在本研讨会中，你将在本地使用基于 Astro 构建的 Tailspin Toys 应用和 GitHub Copilot app。开始前，请先确保本地已安装 Node.js，然后再安装 Copilot app。
|
||||
|
||||
本课将介绍如何：
|
||||
|
||||
- 安装 Node.js，以便在本机运行项目测试。
|
||||
- 通过模板创建自己的 Tailspin Toys 项目副本。
|
||||
|
||||
## 安装 Node.js
|
||||
|
||||
多节课程会要求智能体构建功能，并在本地运行 Tailspin Toys 测试套件。这需要项目唯一依赖的运行时 [**Node.js**][nodejs]。请安装 **22 或更高版本**；当前的 **LTS** 版本是稳妥的选择。
|
||||
|
||||
所有平台上最简单的方式都是使用官方安装程序：
|
||||
|
||||
1. 在操作系统中使用 Windows Terminal、macOS 终端或常用工具打开终端窗口。
|
||||
2. 运行以下命令，确认已安装 Node.js 22 或更高版本：
|
||||
|
||||
```shell
|
||||
node --version
|
||||
```
|
||||
|
||||
3. 如果看到 `v22` 或更高版本号，可以跳到下一节。
|
||||
|
||||
> [!TIP]
|
||||
> 仅当尚未安装 Node 或需要更新时，才需要完成以下步骤。
|
||||
|
||||
4. 打开 [Node.js 下载页面][node-download]。
|
||||
5. 下载适用于当前操作系统的 **LTS** 版本。
|
||||
6. 运行安装程序并接受默认设置。在 Windows 上，保留选中的 **Add to PATH** 选项。
|
||||
7. 安装完成后，打开新的终端窗口。
|
||||
8. 在新终端窗口中运行以下命令，确认安装成功：
|
||||
|
||||
```bash
|
||||
node --version
|
||||
```
|
||||
|
||||
9. 应会看到 `v22.x.x` 或更高版本。
|
||||
|
||||
> [!TIP]
|
||||
> 更喜欢容器？如果已安装 [**Docker**][docker]，可以使用存储库的[开发容器][dev-containers]，无需在本地安装 Node.js。开发容器已包含 Node，两种方式无需同时使用。
|
||||
|
||||
## 设置实验存储库
|
||||
|
||||
你将使用自己的 Tailspin Toys 项目副本。现在通过[模板存储库][template-repository]创建副本。新存储库包含实验所需的全部文件，下一课会将其连接到应用。
|
||||
|
||||
1. 在新的浏览器窗口中，转到本实验的 GitHub 存储库：`https://github.com/github-samples/tailspin-toys`。
|
||||
2. 在实验存储库页面选择 **Use this template** 按钮，再选择 **Create a new repository**，创建自己的存储库副本。
|
||||
|
||||
|
||||
|
||||
3. 如果在 GitHub 或 Microsoft 主办的活动中参加本研讨会，请遵循导师提供的说明。否则，可在有权使用 GitHub Copilot 的组织中创建新存储库。
|
||||
|
||||
|
||||
|
||||
4. 记下所创建的存储库路径 (**organization-or-user-name/repository-name**)，后续实验会用到该路径。
|
||||
|
||||
> [!NOTE]
|
||||
> 通过模板创建存储库时，系统会自动创建一组 GitHub 议题作为待办事项。整个研讨会都会使用这些议题，无需自行创建。
|
||||
|
||||
## 总结与后续步骤
|
||||
|
||||
准备工作已完成。你安装了 Node.js，因此可以在本机构建和测试项目；还通过模板创建了自己的 Tailspin Toys 存储库副本。
|
||||
|
||||
接下来，你将安装 GitHub Copilot app、连接刚创建的存储库并熟悉工作区。继续学习[第 1 课 - 安装 GitHub Copilot app][next-lesson]。
|
||||
|
||||
## 资源
|
||||
|
||||
- [下载 Node.js][node-download]
|
||||
- [通过模板创建存储库][template-repository]
|
||||
- [关于 GitHub Copilot app][about-copilot-app]
|
||||
|
||||
[next-lesson]: /zh-cn/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[nodejs]: https://nodejs.org/
|
||||
[node-download]: https://nodejs.org/en/download
|
||||
[docker]: https://www.docker.com/products/docker-desktop/
|
||||
[dev-containers]: https://code.visualstudio.com/docs/devcontainers/containers
|
||||
[template-repository]: https://docs.github.com/repositories/creating-and-managing-repositories/creating-a-template-repository
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
+100
@@ -0,0 +1,100 @@
|
||||
---
|
||||
title: "第 1 课 - 安装 GitHub Copilot app"
|
||||
description: "安装 GitHub Copilot app，连接通过模板创建的存储库，熟悉工作区并尝试快速聊天。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[**GitHub Copilot app**][about-copilot-app] 是一款用于智能体驱动开发的桌面应用。它基于 GitHub Copilot CLI 构建，并与 GitHub 原生集成，因此存储库、分支和 CI 管道均可直接使用。它适用于同时指挥多个智能体的工作流：每个智能体都在隔离的工作区中运行，无需手动完成所有工作，还可自动执行重复性任务。安装 Node.js 并准备好项目副本后，下一步是安装应用并连接该存储库。
|
||||
|
||||
本课将介绍如何：
|
||||
|
||||
- 安装 GitHub Copilot app 并登录。
|
||||
- 从 GitHub 存储库将项目添加到应用。
|
||||
- 熟悉工作区，包括模板创建的待办事项。
|
||||
- 通过快速聊天了解应用本身。
|
||||
|
||||
## 场景
|
||||
|
||||
团队正在采用 AI 智能体来处理不断增加的待办事项。Copilot app 提供了统一的工作位置，可领取议题、运行智能体、审查更改并合并拉取请求。本课将帮助你完成安装和连接，并熟悉如何发起有关项目的对话。
|
||||
|
||||
> [!NOTE]
|
||||
> 必须拥有符合条件的 Copilot 计划，即 Copilot Student 或任一付费计划（Pro、Pro+、Business 或 Enterprise）。如果使用 Copilot Business 或 Copilot Enterprise，管理员必须先启用 **Copilot CLI** 策略，应用才能工作。
|
||||
|
||||
## 安装并配置 GitHub Copilot app
|
||||
|
||||
要使用 GitHub Copilot app，第一步自然是安装它。应用支持 Windows、macOS 和 Linux。接下来安装应用、完成身份验证，并将 Tailspin Toys 存储库添加到应用。
|
||||
|
||||
1. 在浏览器中打开 [GitHub Copilot app 产品页面][download-app]。
|
||||
2. 下载适用于当前平台的应用，并按照产品页面上的说明进行安装。
|
||||
3. 安装完成后打开应用。
|
||||
4. 选择 **Sign in to GitHub**，并按照提示完成身份验证。如果使用 GitHub Enterprise Server，请选择 **Use GitHub Enterprise**，并在提示时输入服务器地址。
|
||||
5. 身份验证后，系统会询问要连接哪些存储库。选择刚创建的 Tailspin Toys 存储库，其名称应为 `<YOUR_GITHUB_HANDLE>/tailspin-toys`。
|
||||
6. 选择 **Continue** 继续加入流程。
|
||||
7. 系统提示选择主题时，选择最喜欢的主题，再选择 **Finish**。
|
||||
|
||||
> [!NOTE]
|
||||
> 如果 Tailspin Toys 副本未自动显示在列表中，可以在应用中完成加入流程后再添加。完成后，Copilot app 会转到主屏幕。在该屏幕选择 **Choose from GitHub**，按名称搜索存储库 (\<YOUR_GITHUB_HANDLE\>/tailspin-toys)，然后将其选中。该存储库随即会添加到 Copilot app。
|
||||
|
||||
## 熟悉工作区
|
||||
|
||||
连接项目后，花一点时间熟悉工作区。应用将功能组织在侧边栏的以下几个区域：
|
||||
|
||||
- **Sessions**：智能体执行工作的区域。每个会话都在独立工作区中运行，因此可以同时运行多个会话，且更改不会发生冲突。下一课将启动第一个会话。
|
||||
- **Quick chats**：适合提问和集思广益的轻量对话，无需单独创建分支或工作区。本课结束时会进行一次快速聊天。
|
||||
- **My work**：通过应用的 **GitHub 原生集成**显示议题和拉取请求。在这里，无需离开应用即可浏览和筛选议题与拉取请求、检查 CI 状态、从议题启动会话以及审查拉取请求。
|
||||
- **Automations**：可按计划或按需运行的已保存智能体任务。本学习路径接近结束时会创建一个自动化任务。
|
||||
|
||||
### 查找模板创建的待办事项
|
||||
|
||||
由于应用与 GitHub 原生集成，存储库中待处理的工作会直接显示在应用内。通过模板创建存储库时，系统已生成一组议题。现在确认它们是否存在。
|
||||
|
||||
1. 在侧边栏中选择 **My work**。
|
||||
2. 模板在待办列表中创建了八个议题。本课程聚焦以下三个，确认它们可见：
|
||||
|
||||
- Allow users to filter games by category and publisher
|
||||
- Update our repository coding standards
|
||||
- Implement pagination on the game list page
|
||||
|
||||
3. 选择一个议题以阅读详细信息。每个议题也可以作为智能体会话的启动点，后续课程会从这些议题开始工作。
|
||||
|
||||
> [!NOTE]
|
||||
> My work 中的项目会自动筛选，仅显示已添加到 Copilot app 的存储库中的项目。要查看其他存储库中的工作项，请将相应存储库添加到应用。
|
||||
|
||||
## 尝试快速聊天
|
||||
|
||||
熟悉应用的一种好方法是用它来了解*应用本身*，而 **Quick chats** 正适合这种场景。通过快速聊天，无需创建分支或工作树即可提问或集思广益，非常适合无需会话的一次性问题。
|
||||
|
||||
1. 在侧边栏中，选择 **Quick chats** 旁的 **+** 以打开新聊天。
|
||||
2. 询问应用自身的会话工作方式：
|
||||
|
||||
```plaintext
|
||||
How does the GitHub Copilot app use worktrees?
|
||||
```
|
||||
|
||||
3. 在对话视图中阅读回复。每个会话都在独立的 git 工作树中运行，因此可以并行运行多个智能体，而不会造成更改冲突。你可以随时继续对话或开始新聊天。
|
||||
|
||||
## 总结与后续步骤
|
||||
|
||||
你已安装 GitHub Copilot app、连接项目并探索工作区。你学习了如何：
|
||||
|
||||
- 安装应用并登录 GitHub。
|
||||
- 从 GitHub 存储库添加项目。
|
||||
- 熟悉工作区，并在 **My work** 中找到模板创建的待办事项。
|
||||
- 使用快速聊天提出一次性问题。
|
||||
|
||||
接下来，你将启动第一个智能体会话，并对项目进行第一次更改，即在游戏卡片上显示星级评分。继续学习[第 2 课 - 运行第一个智能体会话][next-lesson]。
|
||||
|
||||
## 资源
|
||||
|
||||
- [关于 GitHub Copilot app][about-copilot-app]
|
||||
- [GitHub Copilot app 入门][getting-started]
|
||||
- [在 GitHub Copilot app 中使用智能体会话][agent-sessions]
|
||||
|
||||
[ex0]: /zh-cn/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[next-lesson]: /zh-cn/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[download-app]: https://gh.io/app
|
||||
+135
@@ -0,0 +1,135 @@
|
||||
---
|
||||
title: "第 2 课 - 运行第一个智能体会话"
|
||||
description: "在 GitHub Copilot app 中启动第一个智能体会话，对游戏卡片进行一项小改动，并通过第一个拉取请求合并更改。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
在上一课中，你介绍了工作区并使用了快速聊天。现在可以启动**智能体会话**，对项目进行第一次更改。此次改动很小：游戏数据中已有星级评分，但主页上的游戏卡片尚未显示。你将要求智能体显示评分、审查更改，并通过第一个拉取请求合并更改。
|
||||
|
||||
本课将介绍如何：
|
||||
|
||||
- 启动智能体会话，并了解会话的结构。
|
||||
- 要求智能体对项目进行一项范围明确的小改动。
|
||||
- 在工作区差异视图中审查更改。
|
||||
- 在本地运行应用，并在浏览器中确认更改。
|
||||
- 打开并合并第一个拉取请求。
|
||||
|
||||
## 场景
|
||||
|
||||
Tailspin Toys 中的每款游戏都可以有星级评分，该评分已显示在游戏详情页上。但主页的游戏卡片只显示标题、类别、发行商和说明。作为热身，你将让智能体在每张卡片上显示现有评分。这项小型、独立的更改非常适合作为第一个会话任务。
|
||||
|
||||
## 会话剖析
|
||||
|
||||
**会话**是与智能体的对话，在独立工作区中运行。每个会话都有**专用的 git 工作树和分支**，因此可以同时运行多个会话，例如一个添加功能，另一个修复 bug，而不会造成更改冲突。会话按存储库分组显示在侧边栏中，选择任一会话即可切换。
|
||||
|
||||
会话中包含三类内容：与智能体的**对话**、智能体探索和编辑文件时的**工具活动**，以及带有差异的**已更改文件**列表。
|
||||
|
||||
## 启动会话并请求更改
|
||||
|
||||
现在启动新会话，探索项目并实现功能。在[上一课][prior-lesson]中，你从 GitHub 存储库添加了项目。接下来为该存储库创建新会话并请求更改。
|
||||
|
||||
1. 返回（或打开）GitHub Copilot app。
|
||||
2. 选择 **Home screen**。
|
||||
3. 确保为存储库选择了 `tailspin-toys`。
|
||||
|
||||
|
||||
|
||||
4. 使用以下提示词请求更改：
|
||||
|
||||
```plaintext
|
||||
On the game cards, show each game's star rating. The Game type already includes a starRating field — it's a number out of 5, or null when a game hasn't been rated yet. Display it on each card in src/components/GameCard.astro, and when starRating is null show "No rating yet" instead. Keep the change small and don't restructure the card layout.
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> 请注意，提示词包含了 Copilot 要更新的文件名。虽然不要求指定 Copilot 应在工作中包含哪些文件，但指出正确方向既能帮助 Copilot 快速生成代码，也能减少令牌用量。
|
||||
|
||||
5. 选择 <kbd>Enter</kbd> 将提示词发送给 Copilot。
|
||||
|
||||
Copilot app 首先创建新的工作树，即项目的隔离副本。随后，它会探索项目，找到添加新功能所需更新的文件，然后创建必要的代码。现在，你已经使用 Copilot app 添加了一项新功能。
|
||||
|
||||
## 审查差异
|
||||
|
||||
所有 AI 生成的更改在合并前都应接受审查，即使改动很小。接下来直接在 Copilot app 中探索这些更改。
|
||||
|
||||
1. 在应用右上角选择 **Toggle review panel**。差异屏幕会打开，显示 Copilot 所做的所有待处理更改。
|
||||
|
||||
|
||||
|
||||
2. 应会看到核心游戏详情显示文件 `GameCard.astro` 中新增了代码。代码应与以下示例类似：一个小代码块，在评分存在时呈现评分，在 `starRating` 为 `null` 时回退到 "No rating yet"：
|
||||
|
||||
```astro
|
||||
{game.starRating !== null ? (
|
||||
<span class="text-xs font-medium px-2.5 py-0.5 rounded bg-amber-900/60 text-amber-300" data-testid="game-rating">
|
||||
★ {game.starRating} / 5
|
||||
</span>
|
||||
) : (
|
||||
<span class="text-xs font-medium text-slate-500" data-testid="game-rating-empty">
|
||||
No rating yet
|
||||
</span>
|
||||
)}
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot 与所有生成式 AI 工具一样，具有概率性而非确定性，因此实际代码可能与以上示例不同，但应大致相似。
|
||||
|
||||
## 检查更改
|
||||
|
||||
当然，不能只阅读代码就假定它能正常工作，还应进行视觉测试。为此，需要从终端启动应用，再确认一切正常。Copilot app 恰好内置了终端。
|
||||
|
||||
1. 在 Copilot app 右侧的审查面板中选择 **Terminal**。如果没有 **Terminal** 按钮，请选择 **+**（标记为 **Open in panel**），再选择 **Terminal**。
|
||||
|
||||
|
||||
|
||||
2. 在终端窗口中输入以下命令，启动 Web 应用的开发服务器：
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
3. 服务器启动后（只需片刻），打开浏览器窗口。
|
||||
4. 转到 [http://localhost:4321](http://localhost:4321)。
|
||||
5. 现在应能在主页上的所有游戏中看到星级评分。
|
||||
6. 返回终端窗口。
|
||||
7. 选择 <kbd>Ctrl</kbd>+<kbd>C</kbd> 停止开发服务器。
|
||||
|
||||
## 打开并合并第一个拉取请求
|
||||
|
||||
更改看起来没有问题，现在可以交付。你将要求智能体打开拉取请求，然后在 github.com 上自行审查并合并。目前先手动管理此流程，后续课程将探索 Copilot 如何自动处理其中部分工作。
|
||||
|
||||
1. 在右上角选择 **Create PR**。
|
||||
2. 如果系统提示，请选择 **Sign in with your browser**，并按照提示完成身份验证。
|
||||
3. Copilot 开始创建 PR。
|
||||
|
||||
PR 创建后，Copilot 会监视存储库中需要运行的工作流。片刻后，右上角的按钮会变为 **Ready to merge**，表示 PR 已可合并。
|
||||
|
||||
4. 选择聊天上方的 **PR** 气泡，在审查窗格中打开并查看拉取请求。可根据需要在此审查 PR。
|
||||
5. 准备好后，选择 **Ready to merge**。
|
||||
6. 在新对话框窗口中选择 **Merge pull request**，合并拉取请求。
|
||||
|
||||
现在，新功能已推送到网站。
|
||||
|
||||
## 总结与后续步骤
|
||||
|
||||
你已启动第一个智能体会话，并交付了第一次更改。具体而言，你：
|
||||
|
||||
- 启动了智能体会话，并了解了会话的结构。
|
||||
- 指示智能体对游戏卡片进行一项范围明确的小改动。
|
||||
- 在工作区差异视图中审查了更改。
|
||||
- 在本地运行应用，并在浏览器中确认了星级评分。
|
||||
- 打开并自行在 github.com 上合并了拉取请求。
|
||||
|
||||
接下来，你将从待办事项中的一个议题开始，使用应用向存储库添加自定义指令标准。继续学习[第 3 课 - 使用自定义指令引导 Copilot][next-lesson]。
|
||||
|
||||
## 资源
|
||||
|
||||
- [在 GitHub Copilot app 中使用智能体会话][agent-sessions]
|
||||
- [关于 GitHub Copilot app][about-copilot-app]
|
||||
- [使用 GitHub Copilot app 管理议题和拉取请求][managing-issues-prs]
|
||||
|
||||
[prior-lesson]: /zh-cn/learning-hub/copilot-workshops/app/1-install-copilot-app/#安装并配置-github-copilot-app
|
||||
[next-lesson]: /zh-cn/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+165
@@ -0,0 +1,165 @@
|
||||
---
|
||||
title: "第 3 课 - 使用自定义指令引导 Copilot"
|
||||
description: "使用 GitHub Copilot app 向存储库添加自定义指令标准，从待办议题开始，并通过拉取请求合并更改。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
使用生成式 AI 时，上下文至关重要。如果任务需要以特定方式完成，或 Copilot 应了解一些背景信息，就应提供这些上下文。[指令文件][instruction-files]是实现此目的最强大的工具之一，它不仅说明需要什么代码，还说明代码应如何组织。本课将向存储库添加文档标准，并采用后续大多数工作的方式：从待办议题开始，让智能体完成更改。
|
||||
|
||||
本课将介绍如何：
|
||||
|
||||
- 探索存储库指令和路径范围指令文件如何传递给智能体。
|
||||
- 从待办事项中的指令议题启动会话。
|
||||
- 要求智能体向 `.github/copilot-instructions.md` 添加文档标准。
|
||||
- 审查更改，并通过拉取请求合并更改。
|
||||
|
||||
## 场景
|
||||
|
||||
与所有优秀的开发团队一样，Tailspin Toys 针对开发实践制定了一组准则和要求，其中包括：
|
||||
|
||||
- 应以 TSDoc 文档注释的形式向代码添加文档。
|
||||
- 应记录格式规范，并通过 lint 强制执行。
|
||||
|
||||
通过指令文件，可以确保 Copilot 获得正确的信息，按照这些实践完成任务。
|
||||
|
||||
## 指令文件
|
||||
|
||||
自定义指令可向 Copilot 提供上下文和偏好，使其更好地理解编码风格与要求。这项强大功能可引导 Copilot 提供更相关的建议和代码片段。你可以指定首选编码约定、库，甚至希望代码中包含的注释类型。可以为整个存储库创建指令，也可以针对特定文件类型提供任务级上下文。
|
||||
|
||||
指令文件分为两类：
|
||||
|
||||
- `.github/copilot-instructions.md`：每次针对存储库的请求都会发送给 Copilot 的单个指令文件。此文件应包含项目级信息，即与大多数发送给 Copilot 的聊天或 CLI 请求相关的上下文，例如所用技术栈、正在构建的内容概述、最佳实践和其他全局指导。
|
||||
- `.github/instructions/*.instructions.md`：可针对特定任务或文件类型创建。可以用它们为特定语言（如 TypeScript 或 Astro）提供准则，也可以为创建 UI 组件或一组新单元测试等任务提供指导。
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot 还支持通过 AGENTS.md、CLAUDE.md 和 GEMINI.md 等其他标准引入指令指导，确保 Copilot 始终具有正确的上下文。
|
||||
|
||||
### 管理指令文件的最佳实践
|
||||
|
||||
深入讨论如何创建指令文件超出了本研讨会的范围。不过，示例项目提供了具有代表性的方法。总体而言：
|
||||
|
||||
- `copilot-instructions.md` 中的指令应专注于项目级指导，例如所构建内容的说明、项目结构和全局编码标准。
|
||||
- 使用 `*.instructions.md` 文件为文件类型（单元测试、Astro 组件、数据层）或特定任务提供具体指令。
|
||||
- 使用自然语言。保持指导清晰，并提供代码应采用和不应采用的示例。
|
||||
|
||||
创建指令文件没有唯一方法，使用 AI 同样如此。通过不断试验，可以找到最适合项目的方式。
|
||||
|
||||
> [!TIP]
|
||||
> 每个使用 GitHub Copilot 的项目都应拥有一套完善的指令文件。探索本项目中的文件时，可以看到针对多种代码文件类型的指令文件。
|
||||
>
|
||||
> 要查找模板或起点，请探索 [awesome-copilot][awesome-copilot]，其中包含大量指令文件、自定义智能体和其他资源。
|
||||
|
||||
## 探索此项目中的自定义指令文件
|
||||
|
||||
花一点时间阅读此存储库附带的指令文件：一个核心 `copilot-instructions.md`，以及一组用于不同任务的 `*.instructions.md` 文件。在编辑器或 GitHub Web UI 中打开这些文件。
|
||||
|
||||
1. 如果审查面板尚不可见，请选择右上角的 **Toggle review panel** 将其打开。
|
||||
|
||||
|
||||
|
||||
2. 选择 **+**，向审查面板添加新项目。
|
||||
3. 选择 **File**。
|
||||
4. 搜索 `copilot-instructions.md`。
|
||||
5. 从文件列表中选择 `copilot-instructions.md` 将其打开。
|
||||
6. 探索该文件，注意项目的简要说明，以及 **Agent notes**、**Code standards**、**Scripts** 和 **Repository Structure** 等部分。在 **Code standards** 下，注意嵌套的 **GitHub Actions Workflows** 指导。这些内容适用于与 Copilot 的所有交互。
|
||||
7. 选择 **Show folder view** 打开文件夹导航器。
|
||||
|
||||
|
||||
|
||||
8. 转到 `.github/instructions` 文件夹并探索其中的文件。注意，其中包含针对 Astro 文件、Drizzle 数据层和测试等内容的指令。
|
||||
9. 打开 `.github/instructions/unit-tests.instructions.md`。注意顶部的 `applyTo` 字段，它设置了一个相对于存储库根目录的 glob，用于确定指令适用的文件。此处会匹配任何 TypeScript 测试文件，例如匹配 `**/*.test.ts` 的文件。
|
||||
10. 注意此项目中有关创建单元测试的具体指令。
|
||||
11. 最后，打开 `.github/instructions/drizzle.instructions.md` 并滚动到底部。注意其中指向其他指令文件（如 `unit-tests.instructions.md`）和项目现有文件的链接。这样可以将较大的指令集拆分为较小的可复用文件，并让 Copilot 在生成代码时参考示例。（其中的路径相对于指令文件，而非存储库根目录。）
|
||||
|
||||
> [!NOTE]
|
||||
> `copilot-instructions.md` 中的 **Code formatting requirements** 部分记录了项目编码标准，但尚未要求代码内文档。接下来，你将添加 TSDoc 文档注释和文件注释标头的规则。
|
||||
|
||||
## 从指令议题开始
|
||||
|
||||
上一课通过直接提示词启动了会话。不过，大多数工作都从议题开始。接下来，根据用于更新指令文件的议题创建新会话，再请求更新。
|
||||
|
||||
> [!NOTE]
|
||||
> 指令文件对 Copilot 生成的代码影响很大，因此应确保它们能清晰地引导 Copilot。让 Copilot 创建第一版（正如本课将要做的），再由你审查更新是否满足要求，是一种有效方法。
|
||||
|
||||
1. 在侧边栏中选择 **My work**。
|
||||
2. 选择标题为 **Update our repository coding standards** 的议题，将其打开。
|
||||
3. 选择右上角的 **New session**，根据该议题启动新会话。
|
||||
|
||||
|
||||
|
||||
4. 使用以下提示词，请求 Copilot 更新指令文件以满足议题中记录的要求：
|
||||
|
||||
```plaintext
|
||||
Following this issue, make the updates to the instructions files in this project to meet the requirements documented. Don't create the PR quite yet!
|
||||
```
|
||||
|
||||
Copilot 会进行更新。
|
||||
|
||||
## 审查更改
|
||||
|
||||
接下来阅读 Copilot 所做的更新，并要求它提供根据更新后指令生成的代码示例。
|
||||
|
||||
1. 选择右上角的 **Changes**，打开代码更改。
|
||||
|
||||
|
||||
|
||||
2. 审查更新后的指令文件，确认其中包含有关向代码添加文档和注释的准则。
|
||||
|
||||
> [!NOTE]
|
||||
> AI 具有概率性而非确定性，因此实际文本会有所不同。
|
||||
|
||||
3. 使用以下提示词，要求 Copilot 创建它现在会生成的代码示例：
|
||||
|
||||
```plaintext
|
||||
Do not make any updates, but show me what the code would look like. Based on the new instructions, if I asked Copilot to create a new library component to return all Publishers what would that code look like?
|
||||
```
|
||||
|
||||
4. 审查 Copilot 提议的代码。注意其中包含 TSDoc 文档注释和文件标头注释，这正是更新后的指令所要求的内容。
|
||||
|
||||
现在，你已更新项目中的指令文件，并了解了更新带来的影响。
|
||||
|
||||
## 打开并合并拉取请求
|
||||
|
||||
指令文件会成为存储库中的资产，与团队其他成员共享。接下来像处理任何其他资产一样，为此次工作创建 PR。
|
||||
|
||||
1. 在右上角选择 **Create PR**。
|
||||
2. 如果系统提示，请选择 **Sign in with your browser**，并按照提示完成身份验证。
|
||||
3. Copilot 开始创建 PR。
|
||||
|
||||
PR 创建后，Copilot 会监视存储库中需要运行的工作流。片刻后，右上角的按钮会变为 **Ready to merge**，表示 PR 已可合并。
|
||||
|
||||
4. 选择 **Ready to merge**。
|
||||
5. 在新对话框窗口中选择 **Merge pull request**，合并拉取请求。
|
||||
|
||||
> [!NOTE]
|
||||
> 标准合并到默认分支后，便会成为每位成员和每个新会话的项目组成部分。下一课从最新默认分支启动筛选会话时，智能体会自动遵循此标准。生成的 TypeScript 无需提示便会包含 TSDoc 文档注释。这是指令影响代码生成的一个虽小但真实的示例。
|
||||
|
||||
## 总结与后续步骤
|
||||
|
||||
你探索了应用如何从指令文件获取上下文，然后使用会话添加并合并存储库范围的标准。具体而言，你：
|
||||
|
||||
- 探索了存储库中的 `copilot-instructions.md` 和路径范围 `*.instructions.md` 文件。
|
||||
- 从待办事项中的指令议题启动了会话。
|
||||
- 要求智能体向 `.github/copilot-instructions.md` 添加文档标准。
|
||||
- 审查了更改，并通过拉取请求将其合并。
|
||||
|
||||
接下来，你将在新会话中构建筛选功能，并观察它如何采用刚合并的标准。继续学习[第 4 课 - 使用 Autopilot 构建功能][next-lesson]。
|
||||
|
||||
## 资源
|
||||
|
||||
- [用于自定义 GitHub Copilot 的指令文件][instruction-files]
|
||||
- [自定义 GitHub Copilot app][customize-app]
|
||||
- [创建自定义指令的最佳实践][instructions-best-practices]
|
||||
- [Awesome Copilot：指令文件和其他资源集合][awesome-copilot]
|
||||
|
||||
[next-lesson]: /zh-cn/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[instruction-files]: https://docs.github.com/copilot/customizing-copilot/about-customizing-github-copilot-chat-responses
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[instructions-best-practices]: https://docs.github.com/enterprise-cloud@latest/copilot/using-github-copilot/coding-agent/best-practices-for-using-copilot-to-work-on-tasks#adding-custom-instructions-to-your-repository
|
||||
[awesome-copilot]: https://awesome-copilot.github.com/
|
||||
[custom-instructions-support]: https://docs.github.com/copilot/reference/custom-instructions-support
|
||||
[ui-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/ui.instructions.md
|
||||
[astro-instructions]: https://github.com/github-samples/tailspin-toys/blob/main/.github/instructions/astro.instructions.md
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
+186
@@ -0,0 +1,186 @@
|
||||
---
|
||||
title: "第 4 课 - 使用 Autopilot 构建功能"
|
||||
description: "在 GitHub Copilot app 中使用 Plan 和 Autopilot 模式构建静态客户端筛选功能，观察它如何继承文档标准，并使用智能体技能进行验证。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
本项目已完成一些小更新。但更复杂的更改需要更完善的流程。GitHub Copilot app 可以配合现有流程，确保以正确的方式构建正确的内容。这是连续三节课程中的第一节，你将遵循典型开发流程：先使用议题生成新功能，再使用智能体技能运行验证测试和 lint。
|
||||
|
||||
本课将介绍如何：
|
||||
|
||||
- 从筛选议题启动新会话。
|
||||
- 使用 **Plan** 模式规划功能，再通过 **Autopilot** 构建功能。
|
||||
- 确认生成的代码遵循之前合并的文档标准。
|
||||
- 使用项目的 `quality-checks` 技能验证工作。
|
||||
|
||||
## 场景
|
||||
|
||||
主页列出了所有游戏，但访问者无法缩小列表范围。筛选议题要求允许用户按**类别**和**发行商**筛选游戏。接下来使用 Copilot 实现该功能。
|
||||
|
||||
## 背景
|
||||
|
||||
将 AI 编码智能体引入开发流程不会改变基本原则。事实上，这些原则反而更加重要。大多数开发人员遵循类似以下的流程：
|
||||
|
||||
1. 打开已创建的议题，查看需要完成的工作详情。
|
||||
2. 为需要构建的内容制定计划。
|
||||
3. 构建并审查代码。
|
||||
4. 运行测试以验证代码。
|
||||
5. 手动验证新功能。
|
||||
6. 创建拉取请求 (PR)。
|
||||
7. 代码通过审查且持续集成流程成功后，合并代码。
|
||||
|
||||
> [!NOTE]
|
||||
> 具体流程会因团队和组织而异，但大多数流程都是以上主题的变体。
|
||||
|
||||
坚持这种标准方法，可以确保 AI 生成的代码满足既定要求，并经过与手写代码相同的审查流程。
|
||||
|
||||
## 会话模式
|
||||
|
||||
**会话模式**控制智能体的自主程度。可以从提示词字段下方的下拉菜单中设置模式，并随时更改：
|
||||
|
||||
- **Interactive**：你与智能体协同工作。智能体提出更改建议，并等待输入后再继续。
|
||||
- **Plan**：智能体先创建计划。你审查并批准计划后，智能体才会执行。
|
||||
- **Autopilot**：智能体完全自主工作，包括编写代码、运行测试和迭代，无需等待输入。
|
||||
|
||||
## 规划筛选功能
|
||||
|
||||
发现潜在问题的最佳时机是在编写任何代码之前，而提前规划正是最好的方法。让 Copilot 进行规划时，它会生成一组步骤，并记录将采用的方法。你可以审查计划并提出改进建议，然后让 Copilot 根据计划生成代码。
|
||||
|
||||
接下来打开议题、启动新会话，再切换到 Plan 模式并发出请求，以创建计划。
|
||||
|
||||
1. 在导航选项卡中选择 **My work**。
|
||||
2. 选择标题为 **Allow users to filter games by category and publisher** 的议题。
|
||||
3. 选择右上角的 **New session**。
|
||||
|
||||
|
||||
|
||||
4. 选择 <kbd>Shift</kbd>+<kbd>Tab</kbd>，直到模式显示为 **Plan**。
|
||||
|
||||
|
||||
|
||||
5. 发送以下提示词。由于会话从筛选议题启动，因此该议题已在会话上下文中：
|
||||
|
||||
```plaintext
|
||||
Plan the work based on the requirements documented in the issue. Please ask any clarifying questions you might have as you build the plan.
|
||||
```
|
||||
|
||||
6. 智能体在制定计划时可能会提出后续问题。根据你会如何构建功能来回答这些问题。
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot 具有概率性，因此它提出的具体后续问题会有所不同。事实上，它可能不会提出任何问题，这完全正常。
|
||||
|
||||
7. 完成后，Copilot 会提供计划摘要。审查该计划，应会看到构建查询、添加筛选控件和测试的建议。可以根据需要提供反馈来完善计划，智能体会将建议纳入新版本。
|
||||
|
||||
## 使用 Autopilot 构建
|
||||
|
||||
计划创建后，让 Copilot 构建实现。
|
||||
|
||||
1. 在 **Plan summary** 对话框的选项列表中，选择最接近 **Approve and implement with autopilot** 的选项。
|
||||
|
||||
Copilot 将开始实现。
|
||||
|
||||
> [!NOTE]
|
||||
> 如果 Copilot 未自动开始创建所需代码，可以使用类似 "Go ahead and start building out the plan!" 的提示词让它继续。
|
||||
>
|
||||
> 创建所需更新需要几分钟。智能体会编辑和创建文件、编写并运行测试，以及进行迭代。此时可以回顾目前探索的内容，或稍作休息。
|
||||
|
||||
## 审查更改
|
||||
|
||||
所有 AI 生成的代码在合并前都需要审查。接下来审查代码并运行网站，确保一切正常。
|
||||
|
||||
1. 选择右上角的 **Changes**，打开代码更改。
|
||||
|
||||
|
||||
|
||||
2. 审查更改。应会看到新的 TypeScript、Astro 和测试文件。注意，新辅助函数包含 TSDoc 文档注释和文件标头注释。这是第 3 课中合并的文档标准，无需提示便已自动应用。
|
||||
3. 在 Copilot app 右侧的审查面板中选择 **Terminal**。如果没有 **Terminal** 按钮，请选择 **+**（标记为 **Open in panel**），再选择 **Terminal**。
|
||||
|
||||
|
||||
|
||||
4. 在终端窗口中输入以下命令，启动 Web 应用的开发服务器：
|
||||
|
||||
```shell
|
||||
npm run dev
|
||||
```
|
||||
|
||||
5. 服务器启动后（只需片刻），打开浏览器窗口。
|
||||
6. 转到 [http://localhost:4321](http://localhost:4321)。
|
||||
7. 现在应能在主页上看到筛选器。
|
||||
8. 如果有任何问题，可以要求 Copilot 进行更新。
|
||||
9. 满意后，返回终端窗口。
|
||||
10. 选择 <kbd>Ctrl</kbd>+<kbd>C</kbd> 停止开发服务器。
|
||||
|
||||
## 使用 quality-checks 技能验证工作
|
||||
|
||||
可以仅查看差异就认为工作完成，但团队已经定义了质量标准和可重复的检查方式。
|
||||
|
||||
**智能体技能**可指导 Copilot 如何执行重复性任务，例如运行测试、生成构建或创建拉取请求。技能是一个包含指令、脚本和资源的文件夹，智能体可以按需加载。[Agent Skills 是一项开放标准][agent-skills-repo]，适用于多种智能体，因此同一技能可在智能体模式下的 Copilot Chat、Copilot cloud agent、Copilot CLI 和 GitHub Copilot app 中使用。
|
||||
|
||||
技能位于项目的 `.github/skills` 文件夹或全局 `~/.copilot/skills` 中。每个技能都在一个文件夹中，其中包含具有 YAML frontmatter（`name` 和 `description`）及 Markdown 指令的 `SKILL.md` 文件：
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: quality-checks
|
||||
description: Run the project's test suites and linter to verify code changes are ready to commit, push, or merge.
|
||||
---
|
||||
```
|
||||
|
||||
技能还可包含脚本、资产和参考资料子文件夹。[智能体技能规范][agent-skills-spec]介绍了完整结构。
|
||||
|
||||
> [!TIP]
|
||||
> 技能会动态加载。智能体根据 `description` 字段决定适用的技能。清晰且针对具体场景的说明决定了技能是会被使用还是被忽略。
|
||||
|
||||
## 探索 quality-checks 技能
|
||||
|
||||
接下来探索该技能，了解其作用。
|
||||
|
||||
1. 如果审查面板尚不可见，请选择右上角的 **Toggle review panel** 将其打开。
|
||||
|
||||
|
||||
|
||||
2. 选择 **+**，向审查面板添加新项目。
|
||||
3. 选择 **File**。
|
||||
4. 搜索 `SKILL.md`。
|
||||
5. 从文件列表中选择 `SKILL.md .github/skills/quality-checks` 将其打开。
|
||||
6. 注意 `name` 和 `description`。说明会告知智能体*何时*使用该技能，即每当代码更改需要在提交、推送或合并前进行测试、lint 或验证时。
|
||||
7. 阅读该技能。它记录了哪个脚本运行哪个套件（单元测试、Playwright 端到端测试、ESLint）、运行顺序，以及如何调试常见故障。因此，智能体会按团队规定的方式运行检查，而不是猜测。
|
||||
|
||||
## 运行检查
|
||||
|
||||
在同一筛选会话中，要求智能体验证工作。你无需说出技能名称，智能体会根据请求进行匹配。
|
||||
|
||||
1. 返回 Copilot app。
|
||||
2. 使用 slash command `/quality-checks` 直接调用技能，然后选择 <kbd>Enter</kbd>。
|
||||
3. 智能体按照技能运行单元测试、lint 和端到端测试，并报告结果。如果有任何失败，请要求它修复问题并重新运行检查，直到全部通过。
|
||||
4. **保持此会话打开。**下一课将添加 Playwright MCP 服务器，并使用它在真实浏览器中查看筛选功能。
|
||||
|
||||
## 总结与后续步骤
|
||||
|
||||
你端到端构建了一项真实功能，并按照团队的质量标准进行了验证。具体而言，你：
|
||||
|
||||
- 从最新项目的筛选议题启动了新会话。
|
||||
- 使用 Plan 模式规划功能，并使用 Autopilot 构建功能。
|
||||
- 确认生成的辅助函数遵循第 3 课中合并的文档标准。
|
||||
- 使用 `quality-checks` 技能验证了工作。
|
||||
|
||||
接下来，你将连接 Playwright MCP 服务器，并要求智能体在真实浏览器中探索筛选功能。继续学习[第 5 课 - 使用 Playwright MCP 服务器测试][next-lesson]。
|
||||
|
||||
## 资源
|
||||
|
||||
- [在 GitHub Copilot app 中使用智能体会话][agent-sessions]
|
||||
- [关于 Agent Skills][about-agent-skills]
|
||||
- [自定义 GitHub Copilot app][customize-app]
|
||||
- [关于 GitHub Copilot 的云沙盒和本地沙盒][sandboxes]
|
||||
|
||||
[ex0]: /zh-cn/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex2]: /zh-cn/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /zh-cn/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[next-lesson]: /zh-cn/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[agent-sessions]: https://docs.github.com/copilot/how-tos/github-copilot-app/agent-sessions
|
||||
[about-agent-skills]: https://docs.github.com/copilot/concepts/agents/about-agent-skills
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[agent-skills-repo]: https://github.com/agentskills/agentskills
|
||||
[agent-skills-spec]: https://agentskills.io/specification
|
||||
@@ -0,0 +1,86 @@
|
||||
---
|
||||
title: "第 5 课 - 使用 Playwright MCP 服务器测试"
|
||||
description: "将 Playwright MCP 服务器添加到 GitHub Copilot app，并要求智能体在真实浏览器中手动测试筛选功能。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
上一课使用项目的自动化测试套件创建并验证了筛选功能。测试可以自动验证代码，但让智能体确认行为同样很有价值。智能体可以对它在实际 UI 中发现的问题作出响应。接下来探索 MCP 如何让 AI 智能体访问外部功能，并添加 Playwright MCP 服务器，使 Copilot 可以直接与正在构建的网站交互。
|
||||
|
||||
本课将介绍如何：
|
||||
|
||||
- 了解模型上下文协议 (MCP) 及 GitHub Copilot app 如何使用它。
|
||||
- 从应用设置中添加 Playwright MCP 服务器。
|
||||
- 要求智能体操控浏览器并探索筛选功能。
|
||||
|
||||
## 场景
|
||||
|
||||
单元测试和端到端测试很重要，但验证 UI 更新需要实际与 UI 交互。你希望 Copilot 能像用户一样使用正在开发的网站，以进一步自动执行更改并提高对更新符合预期的信心。
|
||||
|
||||
## 什么是模型上下文协议 (MCP)？
|
||||
|
||||
[模型上下文协议 (MCP)][mcp-blog-post] 为 AI 智能体提供了与外部工具和服务通信的方式。借助 MCP，AI 智能体可以实时与外部工具和服务通信。这让它们既能访问最新信息（使用资源），也能代表你执行操作（使用工具）。
|
||||
|
||||
这些工具和资源通过 MCP 服务器访问。MCP 服务器是 AI 智能体与外部工具和服务之间的桥梁，负责管理双方的通信。外部工具可以是现有 API，也可以是 NPM 包等本地工具。每个 MCP 服务器代表 AI 智能体可访问的一组不同工具和资源。
|
||||
|
||||
以下是两种常用的现有 MCP 服务器：
|
||||
|
||||
- [**GitHub MCP Server**](https://github.com/github/github-mcp-server)：提供一组用于管理 GitHub 存储库的 API。AI 智能体可以创建新存储库、更新现有存储库，以及管理议题和拉取请求。
|
||||
- [**Playwright MCP Server**][playwright-mcp-server]：使用 Playwright 提供浏览器自动化功能。AI 智能体可以转到网页、填写表单和选择按钮。
|
||||
|
||||
还有许多其他 MCP 服务器可用于访问不同的工具和资源。GitHub 托管了一个 [MCP registry](https://github.com/mcp)，以提高生态系统的可发现性并促进贡献。
|
||||
|
||||
> [!CAUTION]
|
||||
> 应像对待项目中的任何其他依赖项一样对待 MCP 服务器。使用前请仔细审查其源代码、验证发布者并考虑安全影响。仅使用可信的 MCP 服务器，并谨慎授予对敏感资源或操作的访问权限。
|
||||
|
||||
## 添加 Playwright MCP 服务器
|
||||
|
||||
可以在应用设置中添加和管理 MCP 服务器。应用内置了常用服务器目录，只需几个步骤即可添加 [Playwright MCP 服务器][playwright-mcp-server]。
|
||||
|
||||
1. 选择 <kbd>Ctrl</kbd>+<kbd>,</kbd> 打开 Copilot app 设置页面。
|
||||
2. 选择 **MCP servers**。
|
||||
3. 在搜索对话框中输入 `Playwright`。
|
||||
4. 从 **Popular MCP servers** 列表中选择 **Playwright**。
|
||||
5. 选择 **Add server**，将其添加到可用 MCP 服务器列表。
|
||||
6. 选择 <kbd>Esc</kbd> 关闭设置对话框。
|
||||
|
||||
现在，Playwright MCP 服务器已添加。
|
||||
|
||||
## 要求 Copilot 通过 Playwright 探索功能
|
||||
|
||||
接下来要求 Copilot 使用 Playwright MCP 服务器手动测试该功能。
|
||||
|
||||
1. 使用以下提示词，要求 Copilot 验证新功能：
|
||||
|
||||
```plaintext
|
||||
Start the dev server then use the Playwright MCP server to validate the functionality you just added exists. Use the details in the issue to ensure the newly added behavior matches the specs.
|
||||
```
|
||||
|
||||
Copilot 将通过 Playwright MCP 服务器启动浏览器、逐步执行每项操作并报告发现的结果。你会实际看到它在系统上打开浏览器执行任务。
|
||||
|
||||
2. 对照议题中的验收标准阅读摘要。如果发现问题，请提出后续问题，或要求它在打开拉取请求前修复代码。
|
||||
3. 保持此会话打开，下一课将完成该会话。
|
||||
|
||||
现在，Copilot 已像用户一样探索功能，并在浏览器中验证了其行为。
|
||||
|
||||
## 总结与后续步骤
|
||||
|
||||
你使用 Playwright MCP 服务器，从 GitHub Copilot app 在真实浏览器中探索了功能。总结来说，你：
|
||||
|
||||
- 了解了模型上下文协议 (MCP)，以及应用如何提供 MCP 工具。
|
||||
- 从应用设置中添加了 Playwright MCP 服务器。
|
||||
- 要求智能体操控浏览器并探索筛选功能。
|
||||
|
||||
功能已构建、验证并确认可以正常工作。现在可以使用 **Agent Merge** 打开并合并拉取请求。继续学习[第 6 课 - 使用 Agent Merge 合并][next-lesson]。
|
||||
|
||||
## 资源
|
||||
|
||||
- [MCP 是什么？为什么每个人都在谈论它？][mcp-blog-post]
|
||||
- [Microsoft Playwright MCP Server][playwright-mcp-server]
|
||||
- [在 GitHub Copilot app 中配置 MCP 服务器][customize-app]
|
||||
|
||||
[next-lesson]: /zh-cn/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[mcp-blog-post]: https://github.blog/ai-and-ml/llms/what-the-heck-is-mcp-and-why-is-everyone-talking-about-it/
|
||||
[playwright-mcp-server]: https://github.com/microsoft/playwright-mcp
|
||||
[customize-app]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
@@ -0,0 +1,67 @@
|
||||
---
|
||||
title: "第 6 课 - 使用 Agent Merge 合并"
|
||||
description: "打开筛选功能的拉取请求，在 My work 中进行审查，并让 Agent Merge 修复阻塞项并完成合并，这是合并自动化阶梯的最高一级。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
筛选功能已构建、验证，并确认可以在浏览器中正常工作。最后一步是将其合并。在本学习路径中，你已经合并过两次，每次都是自行打开拉取请求并在 github.com 上合并。这一次将使用 **Agent Merge** 让应用处理繁重工作。它可以在应用内管理拉取请求的整个生命周期。
|
||||
|
||||
本课将介绍如何：
|
||||
|
||||
- 了解 Agent Merge 及其如何自动执行合并生命周期。
|
||||
- 在筛选会话中启用 Agent Merge。
|
||||
- 观察它创建拉取请求、运行 CI，并在所有检查通过后合并。
|
||||
|
||||
## 场景
|
||||
|
||||
在前几课中，你探索了不同程度的自动化，从创建代码到让 Copilot 直接验证 UI。为了进一步加快开发速度，Tailspin Toys 希望了解是否可以自动合并经过审查和验证的拉取请求。
|
||||
|
||||
## Agent Merge 简介
|
||||
|
||||
通过 **Agent Merge**，可以使用 Copilot app 自动执行拉取请求落地前的最后阶段。启用后，应用会话会读取拉取请求并处理阻塞项，包括修复失败的 CI 检查、响应审查意见，以及在需要时变基。GitHub 允许后，它会立即合并。该功能在后台运行，应用重启后仍会继续，并在拉取请求合并后自动关闭。
|
||||
|
||||
此前，你一直在 github.com 上自行选择 **Merge pull request**。Agent Merge 将这项责任交给智能体，因此它可以管理 PR 直至完成，而你可以继续处理下一项任务。你仍需审查并批准工作，智能体只负责机械性的收尾步骤。
|
||||
|
||||
## 使用 Agent Merge 管理 PR
|
||||
|
||||
你已手动审查代码、运行测试，甚至让 Copilot 验证了 UI。现在可以将新代码合并到代码库。接下来让 agent merge 管理 PR 的持续集成 (CI) 流程并完成合并。
|
||||
|
||||
1. 返回上一课中用于添加筛选功能且仍保持打开的会话。
|
||||
2. 在右上角选择 **Create PR** 旁的下拉菜单。
|
||||
3. 选择 **Agent merge** 以启用 agent merge。
|
||||
|
||||
|
||||
|
||||
4. 按钮文本现在会变为 **Agent merge**。
|
||||
5. 选择 **Agent merge** 按钮，启动 agent merge 流程。
|
||||
|
||||
Copilot app 随即开始创建并管理 PR。它先探索项目以确定创建 PR 的最佳方式，然后创建新 PR。
|
||||
|
||||
片刻后，Copilot 会再次开始工作并查看 PR 条件，即运行存储库全部测试的 CI 流程。它会报告其他团队成员留下的审查状态、需要运行的检查（CI 流程），以及 PR 是否可合并。
|
||||
|
||||
6. 选择 **Agent merge** 旁的下拉菜单，再选择 **Merge pull request**，允许 agent merge 合并拉取请求。
|
||||
|
||||
|
||||
|
||||
7. 所有 CI 流程变为绿色（表示测试通过）后，Copilot 会合并拉取请求。
|
||||
|
||||
## 总结与后续步骤
|
||||
|
||||
你已自动执行开发流程中的多个环节，包括生成代码、测试和验证代码，以及拉取请求流程。你：
|
||||
|
||||
- 了解了 Agent Merge 及其如何自动执行合并生命周期。
|
||||
- 在筛选会话中启用了 Agent Merge。
|
||||
- 观察了它创建拉取请求、运行 CI，并在所有检查通过后完成合并。
|
||||
|
||||
接下来，你将探索**画布**，这是一种与智能体共同规划和可视化工作的更丰富方式。继续学习[第 7 课 - 使用画布规划][next-lesson]。
|
||||
|
||||
## 资源
|
||||
|
||||
- [使用 GitHub Copilot app 管理议题和拉取请求][managing-issues-prs]
|
||||
- [关于 GitHub Copilot app][about-copilot-app]
|
||||
|
||||
[next-lesson]: /zh-cn/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[managing-issues-prs]: https://docs.github.com/copilot/how-tos/github-copilot-app/managing-issues-and-pull-requests
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,127 @@
|
||||
---
|
||||
title: "第 7 课 - 使用画布规划"
|
||||
description: "在 GitHub Copilot app 中创建智能体驱动的共享画布，与智能体共同规划和跟踪工作。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
此前，你通过聊天指挥智能体。但许多工作并不只存在于对话中，而是呈现在看板、文档或检查清单上。借助**画布**，你和智能体可以直接在应用内共享一个适合此类工作的界面。本课将创建一个简单画布，用于规划和跟踪一直在处理的待办事项。
|
||||
|
||||
本课将介绍如何：
|
||||
|
||||
- 了解画布是什么以及何时使用画布。
|
||||
- 创建共享的看板画布以对待办事项进行分类。
|
||||
- 将画布保存到存储库，并为团队合并更改。
|
||||
- 在新会话中打开画布，并从中开始工作。
|
||||
|
||||
## 场景
|
||||
|
||||
即使一切顺利，查看一长串议题也可能让人望而生畏。Tailspin Toys 的开发人员一直在寻找一种工具，用于快速对议题进行分类，并在 Copilot app 中着手处理。
|
||||
|
||||
## 什么是画布？
|
||||
|
||||
[画布][canvas-docs]是用于工作工件的共享交互式界面，例如计划、分类看板、发布检查清单、仪表板或文档。聊天非常适合描述意图和分析模糊问题，但大多数工作发生在具体的*界面*上。画布让你可以直接在该界面上与智能体协作。
|
||||
|
||||
画布支持**双向交互**：智能体可以在工作过程中更新画布，你也可以自行编辑同一个界面。创建画布时，智能体会根据提示词和工作流进行构建；之后，可以要求它添加、删除或修改功能。画布创建后会在应用右侧面板中打开。
|
||||
|
||||
常见示例包括：
|
||||
|
||||
- 用于规划当天工作以及确定议题和拉取请求优先级的 **Markdown 画布**。
|
||||
- 由人员和智能体添加卡片并在列之间移动工作的**智能体看板**。
|
||||
- 汇总存储库重要议题和重复出现主题的**议题分类看板**。
|
||||
|
||||
## 为什么使用画布？
|
||||
|
||||
当任务需要结构、迭代和验证，且仅靠聊天不足以完成时，可以使用画布。画布让你能够：
|
||||
|
||||
- 让智能体基于符合工作流的实际工件开展工作。
|
||||
- 直接在共享界面上引导或纠正工作，再让智能体从更改处继续。
|
||||
- 通过工件的可见更改检查进度，而不只是查看聊天回复。
|
||||
|
||||
## 创建画布来跟踪工作
|
||||
|
||||
你已经交付了许多内容：星级评分、文档标准和筛选功能都已合并。但待办事项中仍有其他工作。接下来创建画布，以便快速对这些工作进行分类。
|
||||
|
||||
1. 返回（或打开）GitHub Copilot app。
|
||||
2. 选择 **Home screen**。
|
||||
3. 确保为存储库选择了 `tailspin-toys`。
|
||||
4. 在提示框中使用以下提示词，创建满足需求的画布：
|
||||
|
||||
```plaintext
|
||||
Create a basic Kanban board canvas that allows me to quickly triage work. Highlight the three issues which are most likely to need attention right now, with the remainder in a second section down below. The top three cards should include a description of the issue's content and a justification of why they're at the top of the list. Each issue should have a button that allows me to add it to the current context for the current session so I can get to work on it straightaway.
|
||||
```
|
||||
|
||||
Copilot 将开始创建画布。
|
||||
|
||||
> [!NOTE]
|
||||
> 此过程需要几分钟。由于任务较复杂，第一版可能无法完全令人满意。可以继续发送提示词，逐步构建理想的工具。
|
||||
|
||||
## 保存画布并合并到存储库
|
||||
|
||||
与指令文件和技能一样，画布也可以成为存储库中的资产。接下来要求 Copilot 将画布添加到存储库并合并，让整个团队都能使用。
|
||||
|
||||
1. 在同一会话中使用以下提示词，要求 Copilot 将画布保存到存储库：
|
||||
|
||||
```plaintext
|
||||
Let's save this canvas definition to the repository so I can share it with my development team
|
||||
```
|
||||
|
||||
2. Copilot 保存画布文件后，选择右上角 **Create PR** 旁的下拉菜单。
|
||||
3. 选择 **Agent merge** 以启用 agent merge。
|
||||
|
||||
|
||||
|
||||
4. 按钮文本现在会变为 **Agent merge**。
|
||||
5. 选择 **Agent merge** 按钮，启动 agent merge 流程。
|
||||
|
||||
Copilot app 会开始创建并管理 PR。它先探索项目以确定创建 PR 的最佳方式，然后创建 PR。
|
||||
|
||||
片刻后，Copilot 会再次开始工作并查看 PR 条件，即运行存储库全部测试的 CI 流程。它会报告其他团队成员留下的审查状态、需要运行的检查（CI 流程），以及 PR 是否可合并。
|
||||
|
||||
6. 选择 **Agent merge** 旁的下拉菜单，再选择 **Merge pull request**，允许 agent merge 合并拉取请求。
|
||||
|
||||
|
||||
|
||||
7. 等待所有 CI 流程通过（变为绿色）。全部通过后，Copilot 会自动合并拉取请求。
|
||||
|
||||
现在，你已经为团队创建了新的共享画布。
|
||||
|
||||
## 在画布中工作
|
||||
|
||||
画布创建后，接下来启动新会话并开始使用。
|
||||
|
||||
1. 在 Copilot app 中，选择 **tailspin-toys** 旁的 **New session** 启动新会话。
|
||||
2. 使用以下提示词，要求 Copilot 打开分类画布：
|
||||
|
||||
```plaintext
|
||||
Open the triage issues canvas
|
||||
```
|
||||
|
||||
3. 现在应会看到所构建的画布已在新会话中打开。
|
||||
4. 在最感兴趣的一个议题上选择 **Add to current context**。
|
||||
5. Copilot 将开始处理该议题。
|
||||
|
||||
现在，你已使用自己创建的画布简化了开发流程。
|
||||
|
||||
## 总结与后续步骤
|
||||
|
||||
你创建了一个可与智能体协作的共享界面。你：
|
||||
|
||||
- 了解了画布是什么以及何时使用画布。
|
||||
- 与智能体共同创建了共享的看板分类画布。
|
||||
- 使用 Agent Merge 将画布保存并合并到存储库。
|
||||
- 在新会话中打开画布，并使用它开始工作。
|
||||
|
||||
待办事项现已得到跟踪。接下来回顾已构建的所有内容，并了解后续方向。继续学习[第 8 课 - 回顾与后续步骤][next-lesson]。
|
||||
|
||||
## 资源
|
||||
|
||||
- [在 GitHub Copilot app 中使用画布扩展][canvas-docs]
|
||||
- [Awesome Copilot 上的画布][awesome-copilot-canvases]
|
||||
- [关于 GitHub Copilot app][about-copilot-app]
|
||||
|
||||
[next-lesson]: /zh-cn/learning-hub/copilot-workshops/app/8-review/
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[awesome-copilot-canvases]: https://awesome-copilot.github.com/extensions/
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
@@ -0,0 +1,83 @@
|
||||
---
|
||||
title: "第 8 课 - 回顾与后续步骤"
|
||||
description: "回顾 GitHub Copilot app 学习路径，自动执行重复性工作，并探索后续方向。"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
在过去几节课程中，你使用 GitHub Copilot app 将一项功能从构想推进到合并，包括：
|
||||
|
||||
- 连接存储库，并熟悉应用工作区和模板创建的待办事项。
|
||||
- 从直接任务和议题启动会话，并使用 Plan 和 Autopilot 模式控制智能体的工作方式。
|
||||
- 使用自定义指令和可复用技能引导智能体。
|
||||
- 使用 Playwright MCP 服务器在真实浏览器中测试工作。
|
||||
- 在共享画布上与智能体协作。
|
||||
- 逐步提高更改交付的合并自动化程度，从自行在 github.com 上合并，到让 **Agent Merge** 完成拉取请求。
|
||||
|
||||
接下来自动执行一些重复性工作、讨论最佳实践，并了解后续方向。
|
||||
|
||||
## 自动执行重复性工作
|
||||
|
||||
应用可通过**自动化**按计划或按需运行智能体，非常适合对新议题进行分类或汇总近期活动等日常任务。接下来创建一个简单的非破坏性自动化任务。
|
||||
|
||||
1. 在侧边栏中选择 **Automations**，再选择 **New automation**。
|
||||
2. 为其指定名称，例如 `Recap my recent work`。
|
||||
3. 选择触发器。**Manual** 支持按需运行；**On a schedule** 会自动运行；**When an issue is created** 会在创建新议题时响应。本课请选择 **Manual**。
|
||||
4. 输入只读提示词，确保自动化任务无法更改任何内容，例如：
|
||||
|
||||
```plaintext
|
||||
Summarize the pull requests merged in this repository over the last week, and list any issues still open in the backlog.
|
||||
```
|
||||
|
||||
5. 选择项目（你的 Tailspin Toys 存储库）并创建自动化任务。
|
||||
6. 按需运行该任务以查看结果。
|
||||
|
||||
> [!TIP]
|
||||
> 自动化任务可以在本地或云中运行。如果希望自动化任务按计划无人值守运行，请启用 **Run in the cloud**，并选择允许它使用的 **Tools**。在信任其输出之前，应确保计划任务范围明确且不具破坏性。
|
||||
|
||||
## 最佳实践
|
||||
|
||||
使用任何 AI 工具时，其周边基础设施都会影响输出质量。指令文件、技能和自定义智能体都在本研讨会中发挥了作用。应投入精力完善这些资产，并在会话间复用。
|
||||
|
||||
根据任务选择适合的**模式和模型**。使用 **Plan** 在构建前思考方法；使用 **Interactive** 参与范围明确的更改；仅对范围清晰且彼此隔离的任务使用 **Autopilot**。日常编辑可选择更快的模型，复杂工作则选择推理能力更强的模型并提高推理强度。
|
||||
|
||||
上下文与基础设施同样重要。清楚说明要构建*什么*、*为什么*构建，以及*如何*构建，会显著影响输出。在决定创建完整会话前，可以先通过快速聊天下一步界定想法范围。
|
||||
|
||||
## 更多探索内容
|
||||
|
||||
你已经了解核心工作流。以下功能也值得探索：
|
||||
|
||||
- **Quick chats**：适合不需要完整会话的一次性问题。
|
||||
- **Rubber duck**：用于分析问题，并在构建前获得高信噪比反馈。
|
||||
- [**Custom agents**][custom-agents]：将角色、工具和指令打包，以便重复执行专业工作。
|
||||
- [`/chronicle`][chronicle]：生成会话过程的叙述。
|
||||
- [Bring your own key (BYOK)][byok]：使用自己提供商的模型，包括通过 Ollama、Foundry Local 或 LM Studio 使用本地模型。
|
||||
- [Cloud sandboxes][sandboxes]：在 GitHub 托管的隔离环境中运行会话。
|
||||
- [Deep links][deep-links]：直接在应用中打开存储库、会话或提示词。
|
||||
|
||||
## 后续步骤
|
||||
|
||||
熟练使用任何工具的最佳方式都是持续使用。可将它用于生产代码、业余项目，或那个构思多年却始终没有动手构建的小应用。与团队分享经验，也向团队学习。并且一如既往地探索文档。
|
||||
|
||||
要探索 GitHub Copilot 生态系统的更多内容，请查看 [VS Code 学习路径](/zh-cn/learning-hub/copilot-workshops/vscode/)、[Copilot CLI 学习路径](/zh-cn/learning-hub/copilot-workshops/cli/)或 [Cloud agent 学习路径](/zh-cn/learning-hub/copilot-workshops/cloud/)。
|
||||
|
||||
## 资源
|
||||
|
||||
- [关于 GitHub Copilot app][about-copilot-app]
|
||||
- [GitHub Copilot app 入门][getting-started]
|
||||
- [自定义 GitHub Copilot app][customize]
|
||||
- [使用自动化][using-automations]
|
||||
- [使用画布扩展][canvas-docs]
|
||||
- [关于云沙盒和本地沙盒][sandboxes]
|
||||
|
||||
[about-copilot-app]: https://docs.github.com/copilot/concepts/agents/github-copilot-app
|
||||
[getting-started]: https://docs.github.com/copilot/how-tos/github-copilot-app/getting-started
|
||||
[customize]: https://docs.github.com/copilot/how-tos/github-copilot-app/customize-github-copilot-app
|
||||
[using-automations]: https://docs.github.com/copilot/how-tos/github-copilot-app/using-automations
|
||||
[canvas-docs]: https://docs.github.com/copilot/how-tos/github-copilot-app/working-with-canvas-extensions
|
||||
[sandboxes]: https://docs.github.com/copilot/concepts/about-cloud-and-local-sandboxes
|
||||
[chronicle]: https://docs.github.com/copilot/how-tos/copilot-cli/use-copilot-cli/chronicle
|
||||
[custom-agents]: https://docs.github.com/copilot/concepts/agents/cloud-agent/about-custom-agents
|
||||
[byok]: https://docs.github.com/copilot/how-tos/github-copilot-app/use-byok-models
|
||||
[deep-links]: https://docs.github.com/copilot/how-tos/github-copilot-app/open-with-deep-links
|
||||
@@ -0,0 +1,57 @@
|
||||
---
|
||||
title: "GitHub Copilot app"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
[**GitHub Copilot app**](https://docs.github.com/copilot/concepts/agents/github-copilot-app) 是一款基于 Copilot CLI 构建的桌面应用，可将智能体驱动的开发集中到一个专注的工作区。它支持并行智能体会话、可切换的会话模式、共享画布，以及原生的 GitHub 议题和拉取请求管理功能。其中包括 **Agent Merge**，可处理拉取请求的变基、审查反馈、CI 修复与合并。
|
||||
|
||||
在这些课程中，你将安装应用并设置项目，然后熟悉应用工作区和模板为你创建的待办事项。你会先完成一项小改动，即添加星级评分；再根据议题添加自定义指令标准，在隔离的智能体会话中构建筛选功能，并使用可复用技能进行验证。随后，你将添加 Playwright MCP 服务器，在真实浏览器中探索该功能，并逐步提高合并自动化程度，最终由 **Agent Merge** 合并拉取请求。最后，你将通过共享画布协作并自动执行重复性工作，完整体验从构想到功能合并的流程。
|
||||
|
||||
## 课程
|
||||
|
||||
| 课程 | 主题 | 说明 |
|
||||
|--------|-------|-------------|
|
||||
| [0. 先决条件][ex0] | 设置 | 安装 Node.js，并创建自己的 Tailspin Toys 项目副本 |
|
||||
| [1. 安装 Copilot app][ex1] | 设置 | 安装应用、连接项目并熟悉工作区 |
|
||||
| [2. 运行第一个智能体会话][ex2] | 首次更改 | 启动会话，并通过第一个拉取请求交付一项小改动 |
|
||||
| [3. 使用自定义指令引导 Copilot][ex3] | 上下文 | 根据议题添加文档标准并合并更改 |
|
||||
| [4. 使用 Autopilot 构建功能][ex4] | 核心功能 | 使用 Plan 和 Autopilot 构建筛选功能，再通过技能进行验证 |
|
||||
| [5. 使用 Playwright MCP 测试][ex5] | 外部工具 | 添加 Playwright MCP 服务器，并在浏览器中探索功能 |
|
||||
| [6. 使用 Agent Merge 合并][ex6] | 合并 | 让 Agent Merge 修复并合并筛选功能的拉取请求 |
|
||||
| [7. 使用画布规划][ex7] | 协作 | 创建共享画布来规划和跟踪工作 |
|
||||
| [8. 回顾与后续步骤][ex8] | 总结 | 自动执行重复性任务，并探索后续内容 |
|
||||
|
||||
## 先决条件
|
||||
|
||||
参加本次研讨会前，请确保具备：
|
||||
|
||||
- [ ] 拥有有效 **Copilot Student、Pro、Pro+、Business 或 Enterprise** 计划的 GitHub 帐户
|
||||
- [ ] 一台运行 **macOS、Linux 或 Windows** 的计算机
|
||||
- [ ] 计算机上已[安装 Git][install-git]
|
||||
|
||||
> [!TIP]
|
||||
> 没有付费计划？经过验证的学生可通过 [GitHub Education][callout-student-plan-education] 免费获取 GitHub Copilot。**Copilot Student** 计划包含本研讨会所需的智能体、MCP、代码审查和 Copilot CLI 功能，因此可以完成所有学习路径。
|
||||
|
||||
> [!NOTE]
|
||||
> Copilot app 在本地计算机而非 codespace 中运行，因此[第 0 课][ex0]会先指导你安装 Node.js 并创建项目副本，然后再安装应用。
|
||||
|
||||
> [!NOTE]
|
||||
> 如果使用 Copilot Business 或 Copilot Enterprise，管理员必须先启用 **Copilot CLI** 策略，你才能使用该应用。
|
||||
|
||||
## 开始学习
|
||||
|
||||
[**从第 0 课“先决条件”开始 →**][ex0]
|
||||
|
||||
[ex0]: /zh-cn/learning-hub/copilot-workshops/app/0-prerequisites/
|
||||
[ex1]: /zh-cn/learning-hub/copilot-workshops/app/1-install-copilot-app/
|
||||
[ex2]: /zh-cn/learning-hub/copilot-workshops/app/2-add-star-rating/
|
||||
[ex3]: /zh-cn/learning-hub/copilot-workshops/app/3-custom-instructions/
|
||||
[ex4]: /zh-cn/learning-hub/copilot-workshops/app/4-build-filtering/
|
||||
[ex5]: /zh-cn/learning-hub/copilot-workshops/app/5-mcp-playwright/
|
||||
[ex6]: /zh-cn/learning-hub/copilot-workshops/app/6-agent-merge/
|
||||
[ex7]: /zh-cn/learning-hub/copilot-workshops/app/7-canvases/
|
||||
[ex8]: /zh-cn/learning-hub/copilot-workshops/app/8-review/
|
||||
[install-git]: https://github.com/git-guides/install-git
|
||||
[callout-student-plan-education]: https://github.com/education/students
|
||||
@@ -0,0 +1,41 @@
|
||||
---
|
||||
title: "动手实践 GitHub Copilot 智能体"
|
||||
authors:
|
||||
- GitHub Copilot Learning Hub Team
|
||||
lastUpdated: 2026-08-03
|
||||
---
|
||||
|
||||
GitHub Copilot 最近新增的功能为开发人员提供了贯穿整个软件开发生命周期 (SDLC) 的强大工具，包括处理 GitHub 上的议题和拉取请求、与外部服务交互，当然也包括创建代码。本实验将探索这些功能，并通过实际用例和技巧，帮助你充分发挥这些工具的价值。
|
||||
|
||||
> [!CAUTION]
|
||||
> GitHub Copilot 具有概率性而非确定性，因此生成的具体代码、修改的文件等可能有所不同。因此，实验中的屏幕截图和代码片段可能与你的实际体验略有差异。这是正常现象，也是使用此类工具的固有特点。
|
||||
>
|
||||
> 如果内容似乎有误或无法正常运行，请向导师求助！
|
||||
|
||||
## 选择操作环境
|
||||
|
||||
无论在哪里工作，都可以使用 GitHub Copilot。请选择符合开发方式的操作环境，并基于共用的 Tailspin Toys 待办事项完成相应练习。每种操作环境都有专属的设置步骤，可以直接开始所选路径。
|
||||
|
||||
### 🖥️ [VS Code](/zh-cn/learning-hub/copilot-workshops/vscode/)
|
||||
|
||||
在 **Visual Studio Code** 和 GitHub Codespaces 中使用 GitHub Copilot。无需离开熟悉的编辑器，即可使用 Copilot Chat 智能体模式、MCP 服务器和自定义智能体。如果希望将 AI 辅助直接融入 IDE，这是理想选择。
|
||||
|
||||
### 💻 [Copilot CLI](/zh-cn/learning-hub/copilot-workshops/cli/)
|
||||
|
||||
**GitHub Copilot CLI** 是一款在终端中运行的智能体助手。安装后，可以连接 MCP 服务器、使用计划模式生成代码，还能完全通过命令行构建自己的技能、自定义智能体和斜杠命令。
|
||||
|
||||
### 🤖 [Copilot App](/zh-cn/learning-hub/copilot-workshops/app/)
|
||||
|
||||
**GitHub Copilot app** 是一款基于 Copilot CLI 构建的桌面应用。它支持并行运行智能体会话、切换会话模式、在画布上协作，以及直接管理 GitHub 议题和拉取请求。其中包括 **Agent Merge**，可引导拉取请求完成变基、处理审查反馈、修复 CI 问题并最终合并。
|
||||
|
||||
### ☁️ [Copilot Cloud Agent](/zh-cn/learning-hub/copilot-workshops/cloud/)
|
||||
|
||||
**Copilot 云智能体** 是一位异步结对编程伙伴，可在后台处理 GitHub 议题。可以分配工作、通过自定义智能体提供指导、在智能体仪表板中监控进度，并审查它创建的拉取请求。
|
||||
|
||||
## 场景
|
||||
|
||||
你是 Tailspin Toys 的新开发人员。这是一家虚构公司，为开发人员主题的桌游提供众筹服务，而这可是一个巨大的市场！团队的待办事项已经创建为 GitHub 议题，等待处理。其中既有筛选和分页等功能开发，也有无障碍支持和编码标准等质量改进。你将通过迭代完成这些任务，同时探索网站和 Copilot 的功能。
|
||||
|
||||
## 开始使用
|
||||
|
||||
选择上述操作环境即可开始。每种环境都会先引导完成所需设置，让你立即开始构建。
|
||||
Reference in New Issue
Block a user