agentleFS
Sign inStart free
memi-designmemi-design/design-skills/AGENTS.md

design-skills

AGENTS.md7 starsChanged 4 months agoMITView on GitHub

The file

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

9 rules. About 0 are common, 1 is distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Treat skills/<slug>/SKILL.md as the canonical workflow surface.

    line 3
  2. Very specific:

    Treat registry/skills.json and registry/collections/*.json as the canonical behavioral metadata and collection surfaces.

    line 4
  3. Very specific:

    Treat provenance.json as the canonical legal and source record.

    line 5
  4. Very specific:

    Keep skill frontmatter to name and description only.

    line 6
  5. Very specific:

    Keep entrypoints under 500 lines and use one-level references/ for detail.

    line 7
  6. Distinctive:

    Never import paid, gated, or unlicensed prose without written permission.

    line 9
  7. Very specific:

    Never use always activation.

    line 11
  8. Very specific:

    Run npm run sync after source, registry, or documentation changes and npm run check before handoff.

    line 12
  9. Very specific:

    Do not edit generated catalog.json or note.json files by hand when scripts/sync-catalog.mjs can express the change.

    line 13

≈ “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

  • Treat skills/<slug>/SKILL.md as the canonical workflow surface.
  • Treat registry/skills.json and registry/collections/*.json as the canonical behavioral metadata and collection surfaces.
  • Treat provenance.json as the canonical legal and source record.
  • Keep skill frontmatter to name and description only.
  • Keep entrypoints under 500 lines and use one-level references/ for detail.
  • Preserve every source's license, author, repository, and immutable commit in provenance.json.
  • Never import paid, gated, or unlicensed prose without written permission.
  • Give every public canonical skill one bounded primary intent, an explicit portability class, declared capabilities, and at least one collection.
  • Never use always activation. Internal, deprecated, or quarantined skills must not enter public default collections.
  • Run npm run sync after source, registry, or documentation changes and npm run check before handoff.
  • Do not edit generated catalog.json or note.json files by hand when scripts/sync-catalog.mjs can express the change.

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.

Check your setup, free