acreadiness-generate-instructions
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.
- License 许可
- MIT
- 最近更新
- 2026-08-19
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- description
- Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.
03 SKILL.md 正文
/acreadiness-generate-instructions — write AI agent instructions
Use this skill whenever the user wants to create, regenerate, or refresh their custom instructions for AI coding agents (Copilot, Claude, etc.). This is the Generate step in AgentRC's Measure → Generate → Maintain loop and the single highest-leverage action for the AI Tooling pillar.
Output options
VS Code recognises several instruction file types — AgentRC generates the most common ones:
| File | Scope | When to use |
|---|---|---|
.github/copilot-instructions.md |
Always-on, whole workspace | Default — VS Code Copilot's native instruction file |
AGENTS.md |
Always-on, whole workspace | Multi-agent repos (Copilot + Claude + others) |
.github/instructions/*.instructions.md |
Scoped by applyTo glob |
Per-area / per-language rules in monorepos |
CLAUDE.md |
Claude-specific | Add via --claude-md (nested only) |
Strategies
flat(default) — single.github/copilot-instructions.mdat the chosen path. Simple, easy to review.nested— hub at.github/copilot-instructions.md+ per-topic detail files at.github/instructions/<topic>.instructions.md, each with anapplyToglob so VS Code only loads the topic when it's relevant. Better for large or multi-stack repos.
Why
.github/instructions/and not.agents/? AgentRC's default nested layout writes to.agents/, which is the right home for agent-agnostic repos (Copilot + Claude + Cursor readingAGENTS.md). For VS Code Copilot specifically, the native location is.github/instructions/withapplyTofrontmatter — that's what Copilot auto-discovers. This skill rewrites AgentRC's nested output to the VS Code-native location whenever the main output is.github/copilot-instructions.md. If you instead chose--output AGENTS.md, nested keeps AgentRC's default.agents/layout.
For monorepos, generate area-scoped instructions with --areas, --area <name>, or --areas-only. Areas are defined in agentrc.config.json. Per-area output is written as VS Code .instructions.md files with an applyTo glob (see below).
Topic vs area .instructions.md files
Both end up in .github/instructions/ but they answer different questions:
| Kind | Filename example | applyTo example |
Where it comes from |
|---|---|---|---|
| Topic (nested) | testing.instructions.md |
**/*.{test,spec}.{ts,tsx,js} |
AgentRC --strategy nested topic split |
| Area (monorepo) | frontend.instructions.md |
apps/frontend/** |
agentrc.config.json areas + --areas |
You can have both at once: a nested set of topic files plus per-area files for a monorepo.
Per-area files with applyTo
When the user opts into areas, emit one VS Code-native .instructions.md file per area at .github/instructions/<area>.instructions.md. Each file MUST start with frontmatter declaring the glob the rules apply to:
---
applyTo: "apps/frontend/**"
---
# Frontend area instructions
…AgentRC-generated content for this area…
Workflow:
- Read
agentrc.config.jsonto discover declared areas and theirpaths/ globs. Ifpathsis missing, ask the user for the glob (e.g.src/api/**). - Run
agentrc instructions --areas(or--area <name>) to produce the per-area body content. - Wrap each area's content in
.github/instructions/<area>.instructions.mdwith theapplyTofrontmatter taken from the area'spaths. If the user passed--apply-to <glob>on a single-area call, use that glob verbatim. - Leave the main file alone — the root
.github/copilot-instructions.mdstays as the always-on instructions;.instructions.mdfiles only kick in for matching paths.
Naming: lowercase, kebab-case area name. Examples: .github/instructions/frontend.instructions.md, .github/instructions/api.instructions.md, .github/instructions/infra.instructions.md.
Steps
- Pick the target file. Default to
.github/copilot-instructions.md. Switch toAGENTS.mdonly if the user mentions multi-agent / Claude / Cursor support. - Always ask which strategy to use —
flatornested— unless the user already specified one in their message or via--strategy. Present the trade-off briefly:- Flat (default) — one
.github/copilot-instructions.md. Simple, easy to review in a single PR. Best for small/medium repos with one stack. - Nested — hub
.github/copilot-instructions.md+ per-topic.github/instructions/<topic>.instructions.mdfiles (each with anapplyToglob so VS Code only loads them when relevant). Best for large or multi-stack repos. Add--claude-mdto also emitCLAUDE.md. Recommendnestedproactively when the repo has > 5 top-level directories, multiple stacks, or already uses a monorepo tool (turbo/nx/pnpm workspaces).
- Flat (default) — one
- Detect monorepo areas by reading
agentrc.config.json. If areas exist, ask the user whether they want per-area.instructions.mdfiles withapplyToin addition to the root file. Default to "yes" whenagentrc.config.jsondeclares areas. - Run dry-run first so the user can preview:
npx -y github:microsoft/agentrc instructions --output <file> --strategy <flat|nested> [--areas|--area <name>] [--claude-md] --dry-run - Show a short summary of what would change — files that would be created or overwritten, area count + their
applyToglobs, model used (defaultclaude-sonnet-4.6). - On confirmation, run the same command without
--dry-run(and optionally--forceif files already exist). - Post-process layout for Copilot output:
- If
--outputends incopilot-instructions.mdand strategy isnested: move/rewrite AgentRC's.agents/<topic>.mdfiles to.github/instructions/<topic>.instructions.md. Add frontmatter to each file with an appropriateapplyToglob (see "Topic applyTo defaults" below). Delete the now-empty.agents/directory. - If
--areaswas used: also write.github/instructions/<area>.instructions.mdfor every area, using each area'spathsfromagentrc.config.jsonas theapplyToglob (override with--apply-tofor single-area calls). - If
--output AGENTS.mdwas chosen: keep AgentRC's native.agents/layout for nested — agent-agnostic readers expect it there. Create the.github/instructions/directory if missing.
- If
Topic applyTo defaults
When promoting AgentRC's nested topic files to .instructions.md, use these defaults unless the user specifies otherwise:
| Topic | Default applyTo |
|---|---|
testing |
**/*.{test,spec}.{ts,tsx,js,jsx,mjs,cjs} |
style / code-quality / formatting |
**/*.{ts,tsx,js,jsx,mjs,cjs,py,go,rs,java,kt,cs} |
build / ci |
**/{package.json,turbo.json,nx.json,.github/workflows/**} |
docs |
**/*.md |
security |
** |
| anything else / hub-level | ** |
- Verify by reading the generated file(s) back and showing the user a 1-paragraph synopsis: stack detected, conventions captured, length, list of
.instructions.mdfiles with their globs. - Suggest next steps:
- Re-run the
assessskill to confirm the AI Tooling pillar score improved. - If the user already has both
copilot-instructions.mdandAGENTS.md, recommend consolidating to a single source of truth (AgentRC flags this at maturity Level 2+).
- Re-run the
Notes
- AgentRC reads your actual code — no templates. Output reflects detected languages, frameworks, and conventions.
--claude-md(nested strategy only) also emitsCLAUDE.md.- VS Code applies
.instructions.mdfiles automatically when the active file matchesapplyTo. The root.github/copilot-instructions.mdalways loads. - Never run this skill non-interactively in CI; instructions are part of the repo and should land via PR.
04 同仓库更多 Skills
youtube-transcript
Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports output with or without timestamps.
youtube-thumbnail-design
YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image
youtube-short-maker
Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: "youtube short", "make a youtube short", "shorts video", "short-form video". NOT for long-form or landscape video.
xcode-project-setup
Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or "build it in" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.
x-twitter-scraper
Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.