agentleFS
monikazapisekmonikazapisek/design-engineering-playbook/skills/AGENTS.md

design-engineering-playbook / skills

AGENTS.md1 starsChanged 5 months agoMITView on GitHub

The file

We split this AGENTS.md into the rules it gives an agent

10 rules. About 1 is common, 7 are distinctive, and 2 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Follow skills-guideline.md when creating or editing skills.

    line 3
  2. Distinctive:

    Every skill must have one clear job.

    line 4
  3. Distinctive:

    Create one folder per skill.

    line 5
  4. Very specific:

    Every skill folder must contain SKILL.md.

    line 6
  5. Distinctive:

    Do not create empty optional folders unless the user asks for a full scaffold.

    line 9
  6. Distinctive:

    Do not copy private workspace content directly.

    line 10
  7. Distinctive:

    Keep all content public-safe, generic, and reusable.

    line 11
  8. Common:

    Avoid client-specific, personal, or secret data.

    line 12
  9. Distinctive:

    Ask before deleting, renaming, or broadening the scope of a skill.

    line 13
  10. Distinctive:

    Do not edit root README.md without explicit user approval.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Agent Instructions for skills/

  • Follow skills-guideline.md when creating or editing skills.
  • Every skill must have one clear job.
  • Create one folder per skill.
  • Every skill folder must contain SKILL.md.
  • Optional subfolders: references/, examples/, scripts/.
  • Do not add per-skill README.md by default. Exception: add one when the skill is in a public GitHub repo and you want humans to discover the skill by browsing the folder directly (without going through the agent runtime). The README is the GitHub-facing landing page; the SKILL.md is the agent-facing working document. Don't duplicate — the README summarizes, the SKILL.md is the full procedure.
  • Do not create empty optional folders unless the user asks for a full scaffold.
  • Do not copy private workspace content directly.
  • Keep all content public-safe, generic, and reusable.
  • Avoid client-specific, personal, or secret data.
  • Ask before deleting, renaming, or broadening the scope of a skill.
  • Do not edit root README.md without explicit user approval.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.