Featured

command-name

Name: command-name
Author: anthropics

This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.

TL;DR

Standardized plugin structure for Claude Code with auto-discovered components and manifest-driven configuration.

What Is It

Conventional directory layout with auto-discovery
Manifest-driven configuration in .claude-plugin/plugin.json
Component-based organization (commands, agents, skills, hooks)
Portable path references using ${CLAUDE_PLUGIN_ROOT}

Key Features

Manifest in .claude-plugin/plugin.json at root level
Components auto-discovered in commands/ agents/ skills/ hooks/
Use kebab-case for all directory and file names
Custom component paths supplement default locations
Supports multiple component types with specific file formats
Hooks register automatically on plugin enablement
MCP servers defined in .mcp.json
Commands, agents, and skills load based on context

How to Use

1.Create plugin directory with standard structure
2.Place plugin.json in .claude-plugin/ with required fields
3.Add components (commands, agents, skills, hooks) in appropriate directories
4.Use kebab-case for all file and directory names
5.Configure custom paths in plugin.json if needed
6.Ensure all components are in root-level directories

Guardrails & Gotchas

Manifest MUST be in .claude-plugin/ directory
Component directories MUST be at plugin root level, not nested in .claude-plugin/
No absolute paths in component paths
Custom paths supplement defaults—they don't replace them
Use semantic versioning for version field
Must use kebab-case with no spaces or special characters