agentleFS
ubie-ossubie-oss/claude-code-plugin/.claude/skills/implement-plugin/SKILL.md

implement-plugin

Skill1 starsChanged 9 months agoApache-2.0View on GitHub

Package and distribute Claude Code plugins with schema-safe manifests, canonical layout, component wiring, and release-ready validation.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Update .claude-plugin/plugin.json and component path mappings.

    line 13
  2. Very specific:

    Verify runtime load with --plugin-dir and optional install flow.

    line 15
  3. Distinctive:

    Run CI-parity smoke tests before distribution.

    line 16
  4. Very specific:

    Test strategy across local/CI: references/testing-strategies.md

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Implement Plugin

Implement plugin-level packaging, manifest wiring, structure checks, runtime load checks, and distribution guidance.

Workflow

  1. Define plugin metadata and distribution scope.
  2. Update .claude-plugin/plugin.json and component path mappings.
  3. Validate manifest and directory structure.
  4. Verify runtime load with --plugin-dir and optional install flow.
  5. Run CI-parity smoke tests before distribution.

Progressive Disclosure

  • Manifest schema and field rules: references/manifest-schema.md
  • Directory conventions and anti-patterns: references/directory-structure.md
  • Test strategy across local/CI: references/testing-strategies.md
  • Distribution checklist and channels: references/plugin-distribution.md
  • Scope and install context guidance: references/plugin-scopes.md
  • Manifest validator: scripts/validate-manifest.sh
  • Layout validator: scripts/check-structure.sh
  • Runtime load check: scripts/test-plugin-load.sh
  • Minimal manifest template: assets/templates/minimal-plugin.json
  • Complete manifest template: assets/templates/complete-plugin.json
  • Manifest with components template: assets/templates/plugin-with-components.json

Component Skills

  • Hooks: ../implement-hooks/SKILL.md
  • Agent Skills: ../implement-agent-skills/SKILL.md
  • Sub-Agents: ../implement-sub-agents/SKILL.md
  • Agent Teams: ../implement-agent-teams/SKILL.md
  • Umbrella selection guide: ../implement-claude-extensions/SKILL.md

Sources

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.