agentleFS
UnfoldCRO-OrganizationUnfoldCRO-Organization/cro-agent-skills/AGENTS.md

cro-agent-skills

AGENTS.md0 starsChanged 22 days agoMITView on GitHub

Guide for any coding agent (Claude Code, Codex, Cursor, or other) working with this repo. A library of Claude Code skills under skills/. Each skill is a folder with a SKILL.md (YAML frontmatter name + description, then Markdown instructions) and optional references/, scripts/, and templates/. There is no build step and no hosted service.

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Keep it generic and clean: No secrets, no personal or client data, no internal-only paths.

    line 16

≈ “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.md

Guide for any coding agent (Claude Code, Codex, Cursor, or other) working with this repo.

What this repo is

A library of Claude Code skills under skills/. Each skill is a folder with a SKILL.md (YAML frontmatter name + description, then Markdown instructions) and optional references/, scripts/, and templates/. There is no build step and no hosted service.

How to use the skills

  • Claude Code / Claude apps — native. Copy a skill folder into ~/.claude/skills/ and it is auto-discovered and model-invoked when a request matches its description. No slash command needed.
  • Any other agent (Codex, Cursor, …) — skills do not auto-fire, so use them as content: open the relevant skills/<name>/SKILL.md, follow its instructions, pull in its references/ when the body points to them, and run its scripts/ as documented. You can also paste a SKILL.md straight into a model.

Working in this repo

  • Keep it generic and clean. No secrets, no personal or client data, no internal-only paths. A leak gate (scripts/scrub_gate.py gate <dir>) runs before anything is published and fails on brand/email/path/private references.
  • Validate skill metadata with python3 scripts/validate-skills.py (valid frontmatter, name matches folder, non-empty body).
  • Regenerate the README tables with python3 scripts/build-readme.py after adding or editing a skill.
  • Third-party sources are listed in third-party-sources.json (not vendored); scripts/update-third-party.sh --check reports upstream drift.
  • Changes land via pull request to main.

Pointers

  • README.md — install, the full skill index, portability, and the good-repos library.
  • GOOD-REPOS.md — tracked skill/tool repos with verdicts and a monthly review.
  • SECURITY.md — how to report a security or leaked-data issue.

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.