agentleFS
Sign inStart free
OKHP3OKHP3/skillz/.agents/skills/catalog-integrity/SKILL.md

catalog-integrity

Skill3 starsChanged 2 months agoMITView on GitHub

Rebuild and validate Skillz Forge catalog truth, evidence contracts, and provenance without credentials.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run after changing a skill contract, family metadata, evidence artifacts, catalog derivation, or generated catalog assets.

    line 10
  2. Distinctive:

    Never paste credentials into the command.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
SKILL.md

Catalog integrity

Use when

Run after changing a skill contract, family metadata, evidence artifacts, catalog derivation, or generated catalog assets.

Callable command

node .agents/skills/catalog-integrity/run.mjs

The command runs the existing artifacts/forge/scripts/build-catalog.js and test-catalog.mjs from their migrated workspace locations. It builds the catalog and project summary in a temporary validation directory, and checks an unchanged copy of the source manifest before generation can conceal inventory drift. A local check does not rewrite tracked release metadata. If it reports stale inventory, run node artifacts/forge/scripts/build-catalog.js and include the refreshed manifest in the source change. The validator allows a shallow checkout for local inspection. CI retains strict history checks and uses the same --check-manifest guard. Publishing still regenerates release metadata.

Inputs and outputs

  • Input: the current checkout's root distribution families and generated artifacts/forge/public/data/ assets.
  • Output: concise pass/fail lines and a non-zero exit on invalid counts, metadata, evidence vocabulary, payload split, or provenance.

Never paste credentials into the command. A local shallow-history warning is not a release pass; a CI shallow-history failure blocks publishing.

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