claude-plugin-dev

Synchronize version numbers across all four required locations for a plugin. Use when releasing a new plugin version.

Guided workflow to create a complete Claude Code plugin with interactive prompts

Quick dashboard of all plugins — versions, sync status, and pending changes. Use at session start or before releases.

Pre-commit validation for plugin releases. Catches version mismatches, missing files, and common errors before the commit hook rejects.

Validate, commit, and push plugin changes to the marketplace. Runs pre-release checks, stages files, creates a release commit, and pushes to remote.

AI-assisted agent generation for Claude Code plugins. Use this agent when the user asks to "create an agent", "generate an agent", "help me build an agent", "design an agent", or needs help writing an AGENT.md file with proper structure, tools, and system prompt. <example> Context: User wants to create a new agent for their plugin user: "I need an agent that reviews database migrations for safety" assistant: "I'll use the agent-creator agent to help design this specialized agent." <commentary> User is creating a new agent. Delegate to agent-creator for interactive design workflow. </commentary> </example> <example> Context: User is building a plugin and needs agent guidance user: "How should I structure an agent for code review?" assistant: "I'll use the agent-creator agent to help you design the code review agent." <commentary> Agent design question. The agent-creator can guide through the interactive process. </commentary> </example> <example> Context: User has a vague agent idea user: "I want an agent that helps with testing" assistant: "I'll use the agent-creator agent to clarify requirements and generate the agent." <commentary> Vague request needs clarification. agent-creator will use AskUserQuestion to refine. </commentary> </example>

Validate plugin structure and conventions. Use this agent when reviewing a plugin for correctness, checking plugin structure, or before publishing a plugin. <example> Context: User just finished creating a plugin user: "I've finished my plugin, can you check it?" assistant: "I'll use the plugin-validator agent to check the structure and conventions." <commentary> Plugin validation requested after completion. Delegate to validator. </commentary> </example> <example> Context: User wants to publish their plugin user: "Is my plugin ready for the marketplace?" assistant: "I'll use the plugin-validator agent to verify it meets all requirements." <commentary> Pre-publish check requested. Run comprehensive validation. </commentary> </example> <example> Context: User is debugging plugin issues user: "My plugin skills aren't loading correctly" assistant: "I'll use the plugin-validator agent to check the structure for issues." <commentary> Loading issues often stem from structure problems. Validate first. </commentary> </example>

Quality review specialist for Claude Code skills. Use this agent proactively after creating or modifying a skill, when the user asks to "review my skill", "check skill quality", "improve skill description", or needs feedback on SKILL.md structure and content. <example> Context: User just created a new skill user: "I finished writing my skill, can you check it?" assistant: "I'll use the skill-reviewer agent to analyze the skill quality." <commentary> Skill just created, proactively review for quality issues. </commentary> </example> <example> Context: Skill isn't triggering as expected user: "My skill doesn't seem to load when I expect it to" assistant: "I'll use the skill-reviewer agent to check the description and triggers." <commentary> Triggering issue likely related to description quality. </commentary> </example> <example> Context: User wants to improve their skill user: "How can I make my skill better?" assistant: "I'll use the skill-reviewer agent to provide specific improvement suggestions." <commentary> Quality improvement request, skill-reviewer can analyze and suggest. </commentary> </example>

Guide for creating specialized subagents with AGENT.md files. Use when the user asks to "create an agent", "write AGENT.md", "subagent", "specialized agent", "agent tools", or needs guidance on agent design.

Overview of Claude Code plugin development with component routing. Use when the user asks to "create a plugin", "build a plugin", "plugin structure", "how do plugins work", or needs general plugin guidance.

Guide for creating user-invocable slash commands. Use when the user asks to "create a command", "slash command", "write a command", "$ARGUMENTS", "dynamic arguments", or "@ file references".

Guide for creating event-driven hooks that validate, log, or modify Claude's behavior. Use when the user asks to "create a hook", "add PreToolUse hook", "validate tool use", "hook events", "hooks.json", or mentions hook events (PreToolUse, PostToolUse, Stop).

Guide for bundling MCP servers with plugins. Use when the user asks to "add MCP server", "integrate MCP", "external tools", ".mcp.json", or "Model Context Protocol".

Guide for implementing user-configurable plugin settings with .local.md files. Use when the user asks about ".local.md", "plugin settings", "configuration file", "temporarily active hooks", or "user configuration".

Guide for organizing Claude Code plugin directories and creating manifests. Use when the user asks to "create plugin structure", "set up plugin directories", "plugin layout", "plugin manifest", or "plugin.json".

Guide for writing effective SKILL.md files with proper triggers and progressive disclosure. Use when the user asks to "create a skill", "write SKILL.md", "skill frontmatter", "skill description", or "trigger phrases".

2 hooks across 2 events