docs: update Learning Hub for CLI v1.0.71-1.0.72 features

- automating-with-hooks.md: document stop_hook_active flag for agentStop
  hooks (v1.0.72) and the 8-consecutive-block limit to prevent infinite loops
- working-with-canvas-extensions.md: add canvas support in CLI (v1.0.71),
  update prerequisites to include CLI users
- installing-and-using-plugins.md: document direct skill installation via
  copilot plugins install --skill (v1.0.72) with project scope support

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

website/src/content/docs/learning-hub/automating-with-hooks.md

@@ -3,7 +3,7 @@ title: 'Automating with Hooks'
 description: 'Learn how to use hooks to automate lifecycle events like formatting, linting, and governance checks during Copilot agent sessions.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-13
+lastUpdated: 2026-07-21
 estimatedReadingTime: '8 minutes'
 tags:
   - hooks
@@ -369,6 +369,25 @@ Run ESLint after the agent finishes responding and block if there are errors:
 
 If the lint command exits with a non-zero status, the action is blocked.
 
+#### Preventing agentStop loops (v1.0.72+)
+
+An `agentStop` hook that **always blocks** would previously cause the CLI to loop indefinitely. Starting with v1.0.72, the CLI automatically ends the turn after **8 consecutive blocks** and passes a `stop_hook_active` flag to the hook input, so your script can detect a forced continuation and self-limit.
+
+```bash
+#!/usr/bin/env bash
+# scripts/lint-and-stop.sh
+INPUT=$(cat)
+
+# Detect forced continuation — skip the blocking check to avoid looping
+if echo "$INPUT" | jq -e '.stop_hook_active == true' > /dev/null 2>&1; then
+  exit 0
+fi
+
+npx eslint . --max-warnings 0
+```
+
+This pattern lets your `agentStop` hook enforce quality checks without locking the agent in an infinite retry loop.
+
 ### Security Gating with preToolUse
 
 Block dangerous commands before they execute. Use the `matcher` field to target only the `bash` tool, so the hook doesn't fire for file edits or other tools:

website/src/content/docs/learning-hub/installing-and-using-plugins.md

@@ -3,7 +3,7 @@ title: 'Installing and Using Plugins'
 description: 'Learn how to find, install, and manage plugins that extend GitHub Copilot CLI with reusable agents, skills, hooks, and integrations.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-13
+lastUpdated: 2026-07-21
 estimatedReadingTime: '8 minutes'
 tags:
   - plugins
@@ -182,6 +182,31 @@ Pinning to a SHA guarantees that everyone on the team installs plugins from exac
 - **Change control** — review and approve plugin updates before rolling them out team-wide
 - **Stability** — prevent breaking changes in upstream marketplaces from impacting your team without notice
 
+## Installing Skills Directly (v1.0.72+)
+
+As of v1.0.72, you can install individual skills without creating or installing a full plugin. This is useful when you find a single useful skill and don't want to install an entire plugin:
+
+```bash
+# Install a skill from a local directory
+copilot plugins install --skill ./path/to/my-skill/
+
+# Install a skill from a URL
+copilot plugins install --skill https://raw.githubusercontent.com/owner/repo/main/skills/my-skill/SKILL.md
+
+# Install a skill into the current project (repository scope)
+copilot plugins install --skill ./path/to/my-skill/ --scope project
+```
+
+Or from within an interactive session:
+
+```
+/plugins install --skill https://example.com/skills/my-skill/SKILL.md
+```
+
+Skills installed this way are available immediately and appear in `copilot skill list`. Use `copilot plugins remove --skill <name>` to uninstall them.
+
+> **Tip**: Skills from this repository can be installed individually this way. Browse the [Skills Directory](../../skills/) for available skills and use the raw GitHub URL of a skill's `SKILL.md` to install it directly.
+
 ## Installing Plugins
 
 ### From Copilot CLI

website/src/content/docs/learning-hub/working-with-canvas-extensions.md

@@ -3,7 +3,7 @@ title: 'Working with Canvas Extensions'
 description: 'Create and iterate on GitHub Copilot app canvases using /create-canvas, then shape them into reusable project or personal extensions.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-06-17
+lastUpdated: 2026-07-21
 estimatedReadingTime: '8 minutes'
 tags:
   - copilot-app
@@ -14,14 +14,16 @@ relatedArticles:
   - ./agents-and-subagents.md
   - ./using-copilot-coding-agent.md
 prerequisites:
-  - Access to the GitHub Copilot app
+  - Access to the GitHub Copilot app or GitHub Copilot CLI (v1.0.71+)
   - Basic familiarity with GitHub Copilot agent sessions
 ---
 
-Canvas extensions give you shared, interactive work surfaces inside the GitHub Copilot app. Instead of keeping all progress in chat, you can move work into a visible artifact (such as a board, document, checklist, or browser-oriented surface) that both people and agents can update.
+Canvas extensions give you shared, interactive work surfaces inside the GitHub Copilot app and GitHub Copilot CLI. Instead of keeping all progress in chat, you can move work into a visible artifact (such as a board, document, checklist, or browser-oriented surface) that both people and agents can update.
 
 This guide explains what canvases can do, how to create one with `/create-canvas`, and how to use patterns from this repository as reference implementations.
 
+> **CLI support (v1.0.71+)**: Canvas extensions are now available in the GitHub Copilot CLI in addition to the Copilot app. Create and interact with canvases directly from terminal sessions — the same `/create-canvas` skill and extension structure work across both surfaces.
+
 ## What canvases can do
 
 A canvas is a bidirectional surface: