agentleFS
ankitgoyalioankitgoyalio/skills/AGENTS.md

skills

AGENTS.md1 starsChanged 56 days agoMITView on GitHub

Skills are organized into category folders under skills/: Every skill in these folders is part of the published collection and must appear exactly once in both catalogs: The category folders, skills.sh.json groupings, and .claude-plugin/marketplace.json plugins mirror one another. Keep their names, descriptions, membership, and ordering aligned. A new category requires a group in both catalogs; remove both catalog groups when a category loses its final skill. Whenever adding, renaming, moving, or deleting a skill, update both catalogs in the same…

The file

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every skill in these folders is part of the published collection and must appear exactly once in both catalogs:

    line 14
  2. Very specific:

    Before finishing a skill change, validate both JSON files and confirm that each catalog covers the complete set of SKILL.md directories …

    line 23

≈ “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

Skill repository

Skills are organized into category folders under skills/:

  • apple/: Apple platform design and development
  • code/: software development workflows
  • communication/: professional and workplace communication
  • food/: cooking and recipe planning
  • health/: personal health interviews and preventive care planning
  • knowledge/: reflection and personal knowledge management
  • naming/: naming projects and products
  • shopping/: researching and comparing purchases

Every skill in these folders is part of the published collection and must appear exactly once in both catalogs:

  • skills.sh.json controls the groups displayed on skills.sh. Its entries use the name from each skill's SKILL.md frontmatter.
  • .claude-plugin/marketplace.json controls the groups displayed by the skills CLI. Its entries use repository-relative skill directory paths in the form ./skills/<category>/<skill-name>.

The category folders, skills.sh.json groupings, and .claude-plugin/marketplace.json plugins mirror one another. Keep their names, descriptions, membership, and ordering aligned. A new category requires a group in both catalogs; remove both catalog groups when a category loses its final skill.

Whenever adding, renaming, moving, or deleting a skill, update both catalogs in the same change. After editing a skill, verify that its frontmatter name, directory path, and category membership still agree with both catalogs. Content-only changes need no catalog diff when those identifiers remain unchanged.

Before finishing a skill change, validate both JSON files and confirm that each catalog covers the complete set of SKILL.md directories without duplicates or stale entries. After a catalog, skill-name, or skill-path change, run npx skills@latest add . --list and verify that every skill appears under the expected category.

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.