agentleFS
Sign inStart free
gastonlarap-a11ygastonlarap-a11y/claude-code-setup/.claude/skills/new-plugin/SKILL.md

new-plugin

Skill1 starsChanged 3 months agoMITView on GitHub

Scaffold a new plugin for the dev-plugins marketplace — skeleton, marketplace entry, dual version, install list, validate and republish. Use when adding a plugin to this repo.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. os-factory/har★ 130same name
    2. langburd/agent-skills★ 4same name
    3. chewygumxx/claude-library★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Add the entry to .claude-plugin/marketplace.json (name, source: ./plugins/<name>, description, version, defaultEnabled, category).

    line 13
  2. Very specific:

    Test hot without installing: claude --plugin-dir ./plugins/<name> and /reload-plugins while iterating.

    line 24
  3. Very specific:

    Run the verify skill and report real results.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

New plugin

  1. Scaffold plugins/<name>/ — claude plugin init <name> gives the official skeleton, or mirror an exemplar: every plugin here ships .claude-plugin/plugin.json + skills/ (see plugins/go/ for the shape). Manifest fields as in plugins/go/.claude-plugin/plugin.json, including "defaultEnabled": false for stack/domain plugins (projects re-enable their own).
  2. Add the entry to .claude-plugin/marketplace.json (name, source: ./plugins/<name>, description, version, defaultEnabled, category). Version MUST match the plugin's own plugin.json — dual-bump rule, enforced by scripts/check-versions.sh. Renaming or retiring a plugin later: use the marketplace renames map ("old-name": "new-name" or null to retire; requires CLI ≥ 2.1.193) so installed copies migrate safely.
  3. Wire distribution: add the plugin to plugins.txt under its section (the installers install from it) and an explicit entry in global/settings.json enabledPlugins (scripts/check-versions.sh / CI keep these in sync).
  4. Content rules: all config content in English; skill descriptions lead with the words a request would contain; heavy reference material goes in references/ (loads on demand).
  5. Test hot without installing: claude --plugin-dir ./plugins/<name> and /reload-plugins while iterating.
  6. Validate & publish: claude plugin validate ./plugins/<name> --strict && claude plugin marketplace update dev-plugins && claude plugin update <name>@dev-plugins
  7. Run the verify skill and report real results. New plugins rely on the dual-bump rule — a CHANGELOG.md entry is only needed if the marketplace as a whole changes behavior.

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