agentleFS
Sign inStart free
nuthinkingnuthinking/skills/AGENTS.md

skills

AGENTS.md0 starsChanged 10 days agoMITView on GitHub

This repo publishes agent skills. Each skill is a folder under skills/ with a SKILL.md (frontmatter name + description, then instructions), an optional README.md for humans, references/ for longer docs the agent loads on demand, and scripts/ for helpers. When adding or changing a skill:

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository5 other files it gives its agents.

The file

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

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When adding or changing a skill:

    line 5
  2. Very specific:

    Keep SKILL.md lean (well under 500 lines).

    line 7
  3. Distinctive:

    Test a skill against a realistic repo before changing its instructions substantially.

    line 11
  4. Very specific:

    After changing skills/product-map/scripts/validate.py, run python3 skills/product-map/scripts/test_validate.py.

    line 12
  5. Very specific:

    After changing anything under skills/design-catalog/scripts/, run python3 skills/design-catalog/scripts/test_scripts.py, and re-run the …

    line 14
  6. Very specific:

    After changing anything under skills/ui-tweaks/scripts/, run node skills/ui-tweaks/scripts/test_scripts.mjs, and check the panel against a …

    line 15

≈ “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 notes for this repository

This repo publishes agent skills. Each skill is a folder under skills/ with a SKILL.md (frontmatter name + description, then instructions), an optional README.md for humans, references/ for longer docs the agent loads on demand, and scripts/ for helpers.

When adding or changing a skill:

  • Keep SKILL.md lean (well under 500 lines). Move long templates, schemas and examples into references/ and link to them with a sentence on when to read them.
  • Register new skills in .claude-plugin/plugin.json (skills array) and in the table in README.md.
  • Skills must work for any agent that reads SKILL.md (Claude Code, Codex, Cursor), so avoid agent-specific tool names in instructions.
  • Scripts must be dependency-free where possible (Python 3 standard library) and runnable from any working directory.
  • Test a skill against a realistic repo before changing its instructions substantially.
  • After changing skills/product-map/scripts/validate.py, run python3 skills/product-map/scripts/test_validate.py.
  • After changing skills/product-demo/scripts/validate.py, run python3 skills/product-demo/scripts/test_validate.py.
  • After changing anything under skills/design-catalog/scripts/, run python3 skills/design-catalog/scripts/test_scripts.py, and re-run the extraction against a drifted fixture app (see skills/design-catalog/README.md, Testing) before changing the instructions.
  • After changing anything under skills/ui-tweaks/scripts/, run node skills/ui-tweaks/scripts/test_scripts.mjs, and check the panel against a running app through preview.mjs (see skills/ui-tweaks/README.md, Testing) before changing the instructions.

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