mirror of
https://github.com/github/awesome-copilot.git
synced 2026-05-04 22:25:57 +00:00
ebd22496dd
* Add acreadiness-cockpit plugin
Adds a new plugin that drives Microsoft AgentRC from Copilot chat,
framing every interaction inside AgentRC's Measure -> Generate ->
Maintain loop.
Custom agent (agents/ai-readiness-reporter.agent.md):
Runs `agentrc readiness --json`, interprets every result against
the 9-pillar / 5-level maturity model, then renders a self-contained
reports/index.html from a fixed HTML/CSS template (bundled with the
acreadiness-assess skill) so every user gets an identically styled
dashboard. Honours policies (disabled criteria, overrides, pass-rate
thresholds) and surfaces extras separately.
Skills:
- acreadiness-assess: Measure step. Wraps `agentrc readiness --json`
and hands off to the @ai-readiness-reporter agent. Bundles the
canonical report-template.html.
- acreadiness-generate-instructions: Generate step. Wraps
`agentrc instructions`. Defaults to .github/copilot-instructions.md
(Copilot-native). Asks flat vs nested. For monorepos, emits per-area
.github/instructions/<area>.instructions.md files with applyTo
globs taken from agentrc.config.json.
- acreadiness-policy: Maintain step. Helps pick, scaffold, or apply an
AgentRC policy (criteria.disable, criteria.override, extras,
thresholds) and wire it into CI via --fail-level.
Plugin (plugins/acreadiness-cockpit/):
Declarative plugin.json referencing the agent and three skills.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address PR review feedback
- Align documented slash-command names with plugin manifest:
/acreadiness-assess, /acreadiness-generate-instructions,
/acreadiness-policy (was /assess, /generate-instructions, /policy
inside SKILL bodies and argument-hints).
- Move the literal % from the report template into the substituted
values for {{passRate}} and {{threshold}} so an N/A value of '—'
no longer renders as '—%'. Updated the agent placeholder contract
accordingly.
- Point the report footer at the canonical plugin folder under
github/awesome-copilot instead of the personal source fork.
- Add explicit HTML-escaping rules to the agent: HTML-escape every
{{placeholder}} substitution, and replace </script with <\/script
inside the embedded JSON block so untrusted repo content cannot
break the markup or inject scripts.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
3.3 KiB
3.3 KiB
name, description, argument-hint
| name | description | argument-hint |
|---|---|---|
| acreadiness-assess | Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo. | [--policy <path-or-pkg>] [--per-area] — e.g. /acreadiness-assess, /acreadiness-assess --policy ./policies/strict.json |
/acreadiness-assess — AI-readiness assessment
Use this skill whenever the user asks for an AI-readiness assessment, a readiness check, an audit, or wants to see how AI-ready their repository is.
This skill is the Measure step in AgentRC's Measure → Generate → Maintain loop. The result is a self-contained HTML dashboard the user can open with file:// or commit to the repo.
Steps
-
Confirm prerequisites. Node 20+ must be on PATH. If unsure, run
node --version. -
Decide on a policy (optional but encouraged):
- If the user provided
--policy <source>, capture it. - Otherwise check
agentrc.config.jsonfor apoliciesarray. - If neither, run with no policy (built-in defaults).
- For a primer on policies, suggest the
acreadiness-policyskill.
- If the user provided
-
Run the readiness scan in the repo root with structured output:
npx -y github:microsoft/agentrc readiness --json [--policy <source>] [--per-area]The
CommandResult<T>JSON envelope is your input for the next step. -
Hand off to the
ai-readiness-reportercustom agent to interpret the JSON and producereports/index.html. The agent renders via the bundled templatereport-template.html(shipped alongside this skill) so every report has an identical look & feel. The agent:- Reads the bundled
report-template.htmland substitutes placeholders with real data. - Inlines all CSS, ships a single static file (works under
file://). - Renders maturity level, overall score, grade, pass-rate vs threshold.
- Breaks down all 9 pillars across Repo Health (8) and AI Setup (1) with what it measures, why it matters for AI, current state, and a specific recommendation.
- Tags every pillar with an AI relevance badge (High / Medium / Low).
- Surfaces Extras separately (they never affect the score).
- Shows the Active Policy including any disabled/overridden criteria and thresholds.
- Produces a Prioritised Remediation Plan (🔴 Fix First / 🟡 Fix Next / 🔵 Plan).
- Embeds the raw AgentRC JSON for reuse.
- Reads the bundled
-
Tell the user where the report lives (
reports/index.html) and how to open it. Summarise in chat: maturity level, overall score, top three lowest pillars, and the single highest-leverage next action (almost always: run theacreadiness-generate-instructionsskill).
Notes
- AgentRC also has a built-in HTML renderer (
--visual/--output report.html) but its output is intentionally generic. This skill produces a tailored, opinionated dashboard via the custom agent — closer to a code review than a metrics dump. - For CI gating, recommend
agentrc readiness --fail-level <n>(1–5). - The skill never modifies repository files other than creating
reports/index.html.