create-agents-md — Claude Code skill: what it does, how to install
Generates repo-committed AGENTS.md files for inline rules. Useful for keeping code style, build commands, and safety boundaries close to the code.
npx skills add siviter-xyz/dot-agent --skill create-agents-md -a claude-codeWhat create-agents-md does
This skill guides agents in writing clean AGENTS.md files committed directly to source control. Files follow plain Markdown without metadata frontmatter. They capture tech stack rules, formatting conventions, and exact CLI commands.
Instructions work at the repository root or inside nested folders. That fits monorepo packages or test trees where local rules diverge. Agent tooling combines root guidelines with the nearest subdirectory file.
For knowledge shared across different repositories or heavy reference manuals, AGENTS.md is the wrong tool. In those cases, the guide prescribes standalone skills with dedicated scripts.
What it helps with
- define project-level coding conventions in the repository root
- scope custom testing instructions to a specific test directory
- set package-level workflows within a monorepo setup
- point agents to canonical code patterns and exact terminal commands
Example prompts for the agent
- Create an AGENTS.md file in the root with our TypeScript and service layer conventions
- Write an AGENTS.md inside the tests folder with local runner commands
- Draft folder-scoped instructions for this monorepo package using the AGENTS.md guide
How to install create-agents-md
1Skills CLI (Vercel)
npx skills add siviter-xyz/dot-agent --skill create-agents-md -a claude-code2Manually: put the files in place
~/.claude/skills/create-agents-md/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/create-agents-md/
1Skills CLI (Vercel)
npx skills add siviter-xyz/dot-agent --skill create-agents-md -a codex2Manually: put the files in place
.agents/skills/create-agents-md/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add siviter-xyz/dot-agent --skill create-agents-md -a cursor2Manually: put the files in place
.cursor/skills/create-agents-md/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install siviter-xyz/dot-agent create-agents-md2Manually: put the files in place
.github/skills/create-agents-md/SKILL.md1Skills CLI (Vercel)
npx skills add siviter-xyz/dot-agent --skill create-agents-md -a gemini-cli2Platform CLI
gemini skills install https://github.com/siviter-xyz/dot-agent --path skills/create-agents-mdManually: put the files in place
.devin/skills/create-agents-md/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add siviter-xyz/dot-agent --skill create-agents-md -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about create-agents-md
How to install create-agents-md in Claude Code?
Run npx skills add siviter-xyz/dot-agent --skill create-agents-md -a claude-code in your terminal. You can also save the file directly to ~/.claude/skills/create-agents-md/SKILL.md.
What does the create-agents-md skill do?
It provides instructions for creating clean, metadata-free AGENTS.md files. These files store local conventions, architectural boundaries, and CLI invocations for coding agents.
When should you use skills instead of AGENTS.md?
AGENTS.md belongs inside a repository for small, local guidelines. If knowledge must span multiple repos or requires heavy scripts and documentation, the guide advises creating dedicated skills instead.
Source text
SKILL.md · MIT
--- name: create-agents-md description: Create AGENTS.md files for project-specific inline rules. Use when adding small, project-specific instructions that should be committed in repos. --- # Create AGENTS.md Guide for creating AGENTS.md files for project-specific inline rules. ## When to Use AGENTS.md - **Small, project-specific instructions** that should be committed in the repo - **Folder-scoped rules** for specific directories - **Package-specific instructions** in monorepos - **Test-specific guidance** in test directories ## When NOT to Use AGENTS.md - Reusable knowledge across projects → Use skills - Large documentation → Use skills with references - Complex workflows → Use skills with scripts ## AGENTS.md Structure AGENTS.md is a simple markdown file without metadata: ```markdown # Project Instructions ## Code Style - Use TypeScript for all new files - Prefer functional components in React - Use snake_case for database columns ## Architecture - Follow the repository pattern - Keep business logic in service layers ``` ## Location - **Project root**: `AGENTS.md` – Primary, inline instructions and references for the whole project (commands, tech stack, testing, code style, architecture, safety boundaries). - **Subdirectories**: `subdirectory/AGENTS.md` – Folder- or package-scoped instructions when local behavior meaningfully diverges from the root (e.g., a specific package, service, or test tree). - **Nested support**: Agents typically combine instructions from the closest `AGENTS.md` with parent ones; keep root general and use nested `AGENTS.md` only where you truly need more specific rules. ## Best Practices - Keep AGENTS.md files small and focused - Use for project-specific conventions - Prefer **short, concrete references** over long prose: - Link to project docs, specs, and runbooks - Point to example files or directories (e.g., `see src/api/users.ts for canonical pattern`) - Include the most important commands with exact CLI invocations - Reference existing code examples when possible - Update as project evolves ## References For detailed best practices, see `references/best-practices.md`.
© siviter-xyz · MIT · siviter-xyz/dot-agent