agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/agent-skills-packaging/SKILL.md

agent-skills-packaging

Skill2 starsChanged 33 days agoMITView on GitHub

Packages and reviews agent Skills (SKILL.md + capability.yaml) using Stars-derived packaging patterns

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Use this Skill when / Inputs / Procedure / Output / Prohibited actions.

    line 30
  2. Very specific:

    Ensure capability.yaml matches the slug, sets lifecycle_stage: AVAILABLE_SKILL (or proposal stage), and lists real capabilities_provided …

    line 31
  3. Very specific:

    Verify M23 gates: security-review + dependency-supply-chain evidence paths exist.

    line 34
  4. Very specific:

    Run ./scripts/compile-capability-registry.sh and ./scripts/doctor.sh.

    line 37
  5. Distinctive:

    Do not clone or execute external starred repositories

    line 47
  6. Very specific:

    Do not set approved_for_execution: true on TI candidates

    line 48
  7. Distinctive:

    Do not install Skills without a Captain-reviewed PR

    line 49

≈ “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

Agent Skills Packaging

Use this Skill when

Authoring, reviewing, or promoting a NorthStar / Cursor Skill sidecar (SKILL.md + capability.yaml), especially drafts from the Skills Learning Loop.

Origin

  • Starred discovery: anthropics/skills
  • Candidate: github-stars-anthropics-skills
  • Lifecycle: AVAILABLE_SKILL (Captain-promoted Wave 1 / OVA-71)
  • Metadata/procedure only — do not clone or execute the starred repo

Inputs

  • Draft Skill directory or Learning Loop skill-draft path
  • TI scorecard evidence (security-review + dependency-supply-chain)
  • Target slug and install path under .cursor/skills/<slug>/

Procedure

  1. Confirm the draft has YAML frontmatter (name, description) and sections: Use this Skill when / Inputs / Procedure / Output / Prohibited actions.
  2. Ensure capability.yaml matches the slug, sets lifecycle_stage: AVAILABLE_SKILL (or proposal stage), and lists real capabilities_provided (not token-noise from repo names).
  3. Verify M23 gates: security-review + dependency-supply-chain evidence paths exist; approved_for_execution stays false on TI candidates.
  4. Register the slug in orchestrator/registry/compiler.py SKILL_SLUGS.
  5. Run ./scripts/compile-capability-registry.sh and ./scripts/doctor.sh.
  6. Ship only via Captain-reviewed PR; never auto-install from Learning Loop.

Output

  • Review notes or PR that installs .cursor/skills/<slug>/
  • Updated capability registry compile (no warnings for the new slug)

Prohibited actions

  • Do not clone or execute external starred repositories
  • Do not set approved_for_execution: true on TI candidates
  • Do not install Skills without a Captain-reviewed PR

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