agentleFS
Wsh7AshWsh7Ash/skillmcp/skills/publishing-a-pack-locally/SKILL.md

publishing-a-pack-locally

Skill0 starsChanged 15 days agoMITView on GitHub

Lay out a pack so any skill-aware runtime recognises it without a bespoke loader. Use when a new skill pack is ready to be used by an agent runtime on the same machine

The file

We split this skill into the rules it gives an agent

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

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create the pack root with pack.json at the top level

    line 20
  2. Very specific:

    Write each skill to skills/<slug>/SKILL.md

    line 21
  3. Distinctive:

    Verify the server lists the pack and returns one skill by slug

    line 25
  4. Distinctive:

    every manifest path resolves on disk

    line 30

≈ “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

Publishing a Pack Locally

Lay out a pack so any skill-aware runtime recognises it without a bespoke loader

Use when: a new skill pack is ready to be used by an agent runtime on the same machine

Avoid when: the skills are consumed by a hosted service with its own ingestion format

Procedure

  1. Create the pack root with pack.json at the top level
  2. Write each skill to skills/<slug>/SKILL.md
  3. Include a skill_count and a SHA-256 per file in the manifest
  4. Generate a catalog so a human can browse without opening every file
  5. Point the runtime at the parent directory so discovery finds the pack
  6. Verify the server lists the pack and returns one skill by slug

Signals

  • the manifest's skill_count matches the number of skill files
  • every manifest path resolves on disk
  • the catalog lists all slugs
  • a runtime pointed at the parent directory finds the pack

Patterns

1. Pack layout

pack.json, skills/<slug>/SKILL.md, results/catalog.md

2. Manifest entry

{"slug":..., "path":"skills/x/SKILL.md", "sha256":...}

3. Runtime pointer

serve --packs-root <parent directory>

Pitfalls

  • Putting pack.json below the skill directory so discovery misses it
  • Committing skills without the manifest, leaving consumers unable to verify
  • Pointing the runtime at the pack itself when it expects a parent directory

Done when

  • a runtime discovers the pack from its parent directory
  • the manifest validates against the files on disk

References

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.