Leadership-Skills
CLAUDE.md4 starsChanged 7 months agoMITView on GitHub
A Claude Code plugin marketplace for leadership-oriented skills and agents. This repo is a Claude Code marketplace (not a plugin itself). It catalogs leadership skill plugins for distribution.
In this repository4 other files it gives its agents.
- add-pluginSkill
- link-for-testingSkill
- update-pluginSkill
- validate-marketplaceSkill
The file
Files
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Purpose
A Claude Code plugin marketplace for leadership-oriented skills and agents.
Structure
This repo is a Claude Code marketplace (not a plugin itself). It catalogs leadership skill plugins for distribution.
.claude-plugin/
└── marketplace.json # Marketplace catalog for Claude (name, owner, plugins list)
.cursor-plugin/
└── marketplace.json # Marketplace catalog for Cursor (name, owner, plugins list)
.mcp.json # MCP server definitions
<plugin-name>/ # One folder per domain plugin (e.g. decision-making, communication)
├── .claude-plugin/
│ └── plugin.json # Plugin metadata (name, description, version)
├── skills/ # Skills — each subfolder has a SKILL.md
├── agents/ # Agent definitions (future)
└── commands/ # Slash commands (future)
docs/ # DocumentationKey Conventions
- Marketplace catalog:
marketplace.jsonlists plugins with theirsource(relative path, GitHub repo, npm, etc.). Add new plugins to theplugins[]array. - Plugins: Each domain plugin lives at the repo root (e.g.
decision-making/,communication/) with a.claude-plugin/plugin.jsonand subfolders for skills, agents, commands, etc. - Skills: Each skill lives in
<plugin>/skills/<skill-name>/SKILL.mdwith YAML frontmatter (name,description) and instructions in the body. - Agents: Markdown files in
<plugin>/agents/with frontmatter (name,description,model, etc.).
Testing Locally
/plugin marketplace add ./path/to/this/repoDoes 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
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.

