Generates tailored AI agent instruction files like .github/copilot-instructions.md and scoped .instructions.md files for monorepos.
- GitHub stars
- 41,038
- Files
- 1
- Last commit
- Nov 11, 2026
- License
- MIT
- Allowed tools
- —
What does the acreadiness-generate-instructions skill do?
acreadiness-generate-instructions generates tailored AI agent instruction files like .github/copilot-instructions.md and scoped .instructions.md files for monorepos.
Summary generated from the skill's SKILL.md.
About the acreadiness-generate-instructions skill
Creating custom instruction files for AI coding assistants is what this skill enables for developers working in VS Code or with multi-agent environments. It automates the generation of configuration files like .github/copilot-instructions.md and AGENTS.md based on the actual code, languages, and frameworks detected in a repository. This process helps close gaps in AI tooling by providing agents with specific context about project conventions.
Users can choose between a flat strategy that produces a single instruction file or a nested strategy that creates a central hub alongside specialized topic files. For developers managing monorepos, the skill can generate area-scoped instructions using the paths defined in an agentrc.config.json file. These scoped files include applyTo globs to ensure that specific rules only load when an agent is working within relevant directories, such as a frontend or api folder.
What an agent can do with it
- 1Generate Copilot instructionsCreate a default instruction file for VS Code Copilot to guide its behavior across the entire workspace.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the acreadiness-generate-instructions skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the acreadiness-generate-instructions skill in Claude Code
~/.claude/skills/acreadiness-generate-instructions/SKILL.md
$ npx degit github/awesome-copilot/skills/acreadiness-generate-instructions ~/.claude/skills/acreadiness-generate-instructionsInstall the acreadiness-generate-instructions skill in Claude Code (project)
.claude/skills/acreadiness-generate-instructions/SKILL.md
$ npx degit github/awesome-copilot/skills/acreadiness-generate-instructions .claude/skills/acreadiness-generate-instructionsInstall the acreadiness-generate-instructions skill in Codex
~/.agents/skills/acreadiness-generate-instructions/SKILL.md
$ npx degit github/awesome-copilot/skills/acreadiness-generate-instructions ~/.agents/skills/acreadiness-generate-instructionsInstall the acreadiness-generate-instructions skill in Gemini CLI
~/.gemini/skills/acreadiness-generate-instructions/SKILL.md
$ npx degit github/awesome-copilot/skills/acreadiness-generate-instructions ~/.gemini/skills/acreadiness-generate-instructionsInstall the acreadiness-generate-instructions skill in Claude.ai
npx degit github/awesome-copilot/skills/acreadiness-generate-instructions acreadiness-generate-instructions && zip -r acreadiness-generate-instructions.zip acreadiness-generate-instructions # claude.ai → Customize → Skills → + → Create skill → Upload a skill → acreadiness-generate-instructions.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachablegithub/awesome-copilot/skills/acreadiness-generate-instructions is public and reachablegithub.com/github/awesome-copilot/tree/HEAD/skills/acreadine ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-11github.com/github/awesome-copilot/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/github/awesome-copilot/blob/HEAD/skills/acreadine ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/github/awesome-copilot/blob/HEAD/skills/acreadine ↗Pass
- SKILL.md follows the Agent Skills formatthe description does not say when to use the skillgithub.com/github/awesome-copilot/blob/HEAD/skills/acreadine ↗Finding
SKILL.md
View on GitHub/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.
Files in this skill
1acreadiness-generate-instructions skill questions
How do I install the acreadiness-generate-instructions skill in Claude Code?
Run npx degit github/awesome-copilot/skills/acreadiness-generate-instructions ~/.claude/skills/acreadiness-generate-instructions. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the acreadiness-generate-instructions skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
What is the difference between the flat and nested strategies?
The flat strategy creates a single instruction file for the whole workspace, while the nested strategy creates a main hub file plus specific topic files with globs to load rules only when relevant.