Write Agents Md
Draft a short, accurate AGENTS.md (and a CLAUDE.md bridge) for a repository from evidence in the repo. Use when a project has no agent instructions, or when asked to create or rewrite AGENTS.md.
Install
/plugin marketplace add agentkitco/agentkit-dev-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add agentkitco/agentkit-dev-skills --skill write-agents-mdgit clone --depth 1 https://github.com/agentkitco/agentkit-dev-skills.git /tmp/agentkit-dev-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agentkit-dev-skills/skills/write-agents-md ~/.claude/skills/write-agents-mdPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Write an AGENTS.md from evidence Goal: a file under about 100 lines that tells a coding agent how to run, test and change this repo, using only facts you verified. Unknown beats invented. ## Gather evidence first (read, do not guess) 1. `README*`, `CONTRIBUTING*`, any `docs/` index. 2. Manifests and task runners: `package.json` scripts, `Makefile`, `justfile`, `pyproject.toml`, `Cargo.toml`, `go.mod`, `*.csproj`, `project.godot`. 3. CI config (`.github/workflows/*`, `.gitlab-ci.yml`): the commands CI runs are the commands that must pass. 4. Lint, format and type-check config (`.eslintrc*`, `ruff.toml`, `.editorconfig`, `tsconfig.json`). 5. Directory layout, two levels deep, ignoring `node_modules`, `.git`, build output. 6. Existing instruction files (`CLAUDE.md`, `.cursor/rules`, `.github/copilot-instructions.md`). Merge, do not duplicate. ## Write the file Use [references/template.md](references/template.md) as the skeleton. Rules: - **Commands first.** Exact commands to install, run, test one file, run the full suite, lint, build. Copy them from the manifests; run the safe ones to confirm. - **Only what the agent cannot infer.** Skip "this is a Next.js app" if `package.json` says so. Keep: unusual conventions, forbidden areas, generated files, required env setup. - **Make each rule testable.** "Run `npm run lint` before finishing" not "keep code clean".
Details
- Skill name
write-agents-md- Repository
- agentkitco/agentkit-dev-skills
- Path
skills/write-agents-md/SKILL.md- License
- MIT
- Repo updated
- 12 November 2026
- Listed in
- karanb192/awesome-claude-skills
FAQ
What does the Write Agents Md skill do?
Draft a short, accurate AGENTS.md (and a CLAUDE.md bridge) for a repository from evidence in the repo. Use when a project has no agent instructions, or when asked to create or rewrite AGENTS.md.
How do I install the Write Agents Md skill?
Claude Code plugin: /plugin marketplace add agentkitco/agentkit-dev-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Related skills
Agents Md Audit
agentkitco/agentkit-dev-skills
Audit an AGENTS.md, CLAUDE.md, Cursor rule or Copilot instructions file for stale commands, broken paths, vague rules, secrets and contradictions. Use to review or trim agent instructions.
Brag Doc From Git
agentkitco/agentkit-dev-skills
Build an evidence-based brag doc or self-review draft from your merged PRs and commits, leaving visible gaps where results are unknown. Use for review season, promotion cases or resumes.
Dependency Upgrade
agentkitco/agentkit-dev-skills
Upgrade one dependency at a time by reading its changelog, planning for breaking changes, updating code and proving it still builds and passes. Use to bump, update or migrate a package.
Write Subagent
agentkitco/agentkit-dev-skills
Draft a Claude Code subagent file in .claude/agents/ for one repeatable job, with a trigger-ready description, minimal tools and a fitting model. Use to create, fix or tune a subagent.
Session Handoff
agentkitco/agentkit-dev-skills
Write a HANDOFF.md that lets a fresh agent session continue the work, with goal, state, decisions, next steps and traps. Use when ending a long session, hitting context limits or switching agents.
Cooper Agent Inbox
cooper-email/cooper-email
Basics of an AI agent's own email inbox on Cooper Email (cooperemail.com) - create it, send, read unread mail, reply, and wait for new mail over HTTP or MCP. Use when the agent needs its own email address, has to send or answer email as itself, or must check whether a reply arrived. If the user asked for Cooper Email, do not substitute another mail API.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.