agentleFS
gabimonchagabimoncha/skills/AGENTS.md

skills

AGENTS.md12 starsChanged 20 days agoMITView on GitHub

This is a single-context repo. GLOSSARY.md holds the domain language. Use its terms in code, docs, and replies. A new authored skill moves through two stages, in this order: The marker hides the skill from Skills CLI discovery. To test the skill while it is internal, install it by name: The Marketplace Manifest lists only Public Skills. An Internal Skill never appears in it. .agents/skills/ holds the Repository Skills that maintain this repo, and .claude/skills/ links to them. They belong…

The file

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

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

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

    Internal Skill: Create the skill at skills/<collection>/<skill-name>/SKILL.md.

    line 9
  2. Distinctive:

    Promotion: When the owner considers the skill ready, make both changes in the same commit:

    line 22
  3. Very specific:

    Remove the internal marker from the frontmatter.

    line 23
  4. Very specific:

    Add ./skills/<collection>/<skill-name> to the group of its Collection in .claude-plugin/marketplace.json.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Agents

This is a single-context repo. GLOSSARY.md holds the domain language. Use its terms in code, docs, and replies.

Skill lifecycle

A new authored skill moves through two stages, in this order:

  1. Internal Skill. Create the skill at skills/<collection>/<skill-name>/SKILL.md. Give it name and description frontmatter, and add this marker to the frontmatter:

    metadata:
      internal: true

    The marker hides the skill from Skills CLI discovery. To test the skill while it is internal, install it by name:

    npx skills@latest add gabimoncha/skills --skill <skill-name>
  2. Promotion. When the owner considers the skill ready, make both changes in the same commit:
    • Remove the internal marker from the frontmatter.
    • Add ./skills/<collection>/<skill-name> to the group of its Collection in .claude-plugin/marketplace.json.

The Marketplace Manifest lists only Public Skills. An Internal Skill never appears in it.

Repository Skills

.agents/skills/ holds the Repository Skills that maintain this repo, and .claude/skills/ links to them. They belong to no Collection, so they stay out of the Marketplace Manifest.

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.