agentleFS
Sign inStart free
RohiRIKRohiRIK/skills/skills/CreatePlugin/SKILL.md

CreatePlugin

Skill1 starsChanged 30 days agoMITView on GitHub

Package a project as an AI-agent plugin with Hermes, Claude, OpenClaw, Pi, OpenCode, and MCP adapters. USE WHEN porting workflows across agent hosts. NOT FOR standalone CLIs (use CreateCLI).

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

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

    Put substantive instructions once in plugin/skills/.

    line 23
  2. Very specific:

    Use native host packages or skills where documented.

    line 25
  3. Distinctive:

    Treat static validation, successful loading, and interactive/runtime evidence as different claims.

    line 26

≈ “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

CreatePlugin

Package a project as one maintainable plugin with one canonical workflow source and thin host-specific adapters. Read official host documentation before writing manifests; do not guess unsupported fields.

Workflow Routing

WorkflowTriggerFile
CreatePlugin"convert this project into a portable AI-agent plugin", "port this workflow to agent hosts"Workflows/CreatePlugin.md

Quick Reference

  • Put substantive instructions once in plugin/skills/; host files only route to them.
  • Inspect project context, existing integrations, Git status, and official host docs before editing.
  • Use native host packages or skills where documented; use MCP as the common fallback.
  • Treat static validation, successful loading, and interactive/runtime evidence as different claims.

Gotchas

  • Hermes, Claude, Pi, and OpenCode package formats are not interchangeable; shared name/version/path fields must agree.
  • An OpenClaw installer must be idempotent and refuse to replace unrelated files.
  • Global or user-level configuration, publishing, deployment, and production actions require explicit approval.

Examples

Example 1: "Port this project to Claude, Pi, and OpenCode" → CreatePlugin → inspect project and host docs → create one shared package plus three thin adapters → run static, host, and MCP verification.

Example 2: "Add a Hermes manifest" → read the existing plugin and Hermes docs first → update only the Hermes adapter → validate without changing global configuration.

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