agentleFS
Sign inStart free
grcmanagrcmana/grcskills/CLAUDE.md

grcskills

CLAUDE.md2 starsChanged 14 days agoMITView on GitHub

This repo is a library of portable GRC agent skills distributed with npx skills add grcmana/grcskills and listed on grcskills.io. You're editing the library, not running a GRC programme.

The file

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

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

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never add copyrighted standard text (ISO, AICPA).

    line 8
  2. Very specific:

    Run python3 scripts/sync_references.py --check before committing.

    line 10
  3. Distinctive:

    When a skill's behaviour changes, update its README in the same PR so the page stays accurate.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Maintainer notes for agents working on this repo

This repo is a library of portable GRC agent skills distributed with npx skills add grcmana/grcskills and listed on grcskills.io. You're editing the library, not running a GRC programme.

  • Shared knowledge lives in knowledge/. Never edit skills/*/references/ copies directly. Edit knowledge/, then run python3 scripts/sync_references.py.
  • Each skill must stay self-contained and follow knowledge/methodology/grc-workspace.md.
  • SKILL.md frontmatter: name equals the folder name, and description is 1024 characters or fewer and describes what the skill does and when to use it.
  • Never add copyrighted standard text (ISO, AICPA). Use IDs and own-words summaries.
  • Bump metadata.version in a skill when you change its behaviour. Update the as_of date in a framework pack when you change its facts.
  • Run python3 scripts/sync_references.py --check before committing.
  • The grcskills.io website lives in a separate private repo. This repo's only interface to it is catalog.json, built by scripts/build_catalog.py and attached to tagged releases. Keep metadata.summary and metadata.frameworks accurate.
  • Website content also lives here: skills/<name>/README.md (skill pages, template in templates/skill-README.md), collections/<slug>.md (categories) and contributors/<handle>/README.md (opt-in profiles, with an optional avatar.png/.jpg; checks in scripts/contributor_checks.py). build_catalog.py validates them and packs them into catalog.json (schema 2, see docs/catalog-schema-2.md). A change to the catalogue shape needs the website owner's agreement.
  • When a skill's behaviour changes, update its README in the same PR so the page stays accurate.

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