plugin-structure

Structure Claude Code plugin directories and manifests for reliable component discovery.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/NGTPTE/TuriX-MarketPlace --skill plugin-structure-ngtpte
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plugin-structure
Source: https://github.com/NGTPTE/TuriX-MarketPlace/tree/main/plugins/plugin-dev/skills/plugin-structure
Command: npx skills add https://github.com/NGTPTE/TuriX-MarketPlace --skill plugin-structure-ngtpte

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It helps you structure Claude Code plugins so commands, agents, skills, hooks, and manifests are organized for automatic discovery and reliable loading.

Core Features & Use Cases

  • Manifest and directory layout guidance for .claude-plugin/plugin.json and root-level component folders.
  • Patterns for organizing commands, agents, skills, hooks, MCP servers, and shared scripts.
  • Path portability and naming conventions to avoid loading errors in real plugin development and maintenance.
  • Use case: preparing a new plugin, refactoring a growing plugin, or troubleshooting discovery and path issues.

Quick Start

Ask the AI to review your plugin directory and tell you how to organize commands, agents, skills, hooks, and the manifest for Claude Code compatibility.

Frequently Asked Questions about plugin-structure

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I structure a Claude Code plugin for auto-discovery?

To structure a Claude Code plugin for auto-discovery, use root-level component folders and configure the .claude-plugin/plugin.json manifest. This layout ensures commands, agents, skills, hooks, and MCP servers load reliably without manual intervention.

What is the correct directory layout for Claude Code plugin components?

The correct directory layout for Claude Code plugin components requires organizing commands, agents, skills, hooks, and MCP servers at the root level. Portable Claude plugin root paths and kebab-case naming prevent validation and loading errors.

Why are my Claude Code plugin commands or hooks not loading?

Claude Code plugin commands or hooks fail to load when the plugin structure violates path resolution rules. Ensure your manifest configuration points to root-level component folders and uses kebab-case naming to avoid discovery errors.

Does Claude Code plugin manifest configuration support MCP servers and hooks?

Yes, Claude Code plugin manifest configuration supports auto-loading scenarios for MCP servers and hooks. Defining these components in the .claude-plugin/plugin.json manifest with root-level organization ensures they are discovered and validated correctly.

What's the best way to refactor a growing Claude Code plugin to avoid path errors?

The best way to refactor a growing Claude Code plugin and avoid path errors is to enforce portable Claude plugin root paths and move components into root-level directories. This structure guarantees reliable path resolution and auto-discovery.

When do I need kebab-case naming for Claude Code plugin directories?

You need kebab-case naming for Claude Code plugin directories whenever you are preparing a new plugin or troubleshooting discovery issues. Enforcing kebab-case naming and root-level component organization prevents loading and validation errors.