claude-component-builder

Audit Claude Code components for quality, security, and compliance

Migrate component schema to current version and apply best practices

Create, validate, or update Claude Code plugins with full orchestration. Handles research, planning, user confirmation, and parallel component creation.

Validate a Claude Code component or plugin for schema compliance

Use this agent when the user asks to "create an agent", "build an agent", or needs to update, audit, enhance, migrate, or compare agents. <example> Context: User wants a new agent user: "Create an agent that reviews code for security" assistant: "I'll use agent-builder to create a security review agent." <commentary>Agent creation request - use this agent.</commentary> </example> <example> Context: User wants to audit an agent user: "Check if my test-runner agent follows best practices" assistant: "I'll use agent-builder to audit the test-runner agent." <commentary>Agent audit request - use this agent.</commentary> </example>

Use this agent when the user asks to "create a command", "build a slash command", or needs to update, audit, enhance, migrate, or compare commands. <example> Context: User wants a new slash command user: "Create a command to run my test suite" assistant: "I'll use command-builder to create a run-tests command." <commentary>Command creation request - use this agent.</commentary> </example> <example> Context: User has command issues user: "My command isn't receiving the file path argument correctly" assistant: "I'll use command-builder to fix the argument handling." <commentary>Command expertise needed - use this agent.</commentary> </example>

Use this agent when the user asks to "create a hook", "add event automation", "set up PreToolUse validation", or needs to update, audit, enhance, or compare hooks. Security-focused. <example> Context: User wants validation user: "Create a hook that validates file writes before they happen" assistant: "I'll use hook-builder to create a PreToolUse validation hook." <commentary>Event-driven validation - use this agent.</commentary> </example> <example> Context: User needs policy enforcement user: "Block any bash commands that contain rm -rf" assistant: "I'll use hook-builder to create a security policy hook." <commentary>Security policy request - use this agent.</commentary> </example>

Use this agent when the user asks to "create plugin structure", "write plugin.json", "generate plugin README", "update marketplace.json", or needs to validate plugin metadata. <example> Context: User needs plugin setup user: "Set up the directory structure for my code-review plugin" assistant: "I'll use plugin-builder to create the plugin structure." <commentary>Plugin scaffolding request - use this agent.</commentary> </example> <example> Context: User needs marketplace registration user: "Register my plugin in the marketplace.json" assistant: "I'll use plugin-builder to update the marketplace registry." <commentary>Marketplace registration - use this agent.</commentary> </example>

Use this agent when the user asks to "create a skill", "build a skill", or needs to update, audit, enhance, migrate, or compare skills. <example> Context: User wants auto-invoked expertise user: "Create a skill that auto-invokes when reviewing code" assistant: "I'll use skill-builder to create a reviewing-code skill." <commentary>Skill creation request - use this agent.</commentary> </example> <example> Context: User confused about skill structure user: "Why doesn't my skill's model field work?" assistant: "Skills don't support the model field. I'll use skill-builder to help." <commentary>Skill expertise needed - use this agent.</commentary> </example>

Use this agent when the user needs skill quality review, asks to "review my skill", "check skill quality", or wants to fix skill triggering issues. <example> Context: User just created a skill user: "I just created analyzing-tests skill, can you review it?" assistant: "I'll use skill-reviewer to check the skill quality." <commentary>Skill review request - use this agent.</commentary> </example> <example> Context: User's skill isn't triggering user: "My skill never auto-invokes, what's wrong?" assistant: "I'll use skill-reviewer to analyze the trigger description." <commentary>Triggering issues - this agent specializes in this.</commentary> </example>

Expert at creating and modifying Claude Code agents. Auto-invokes when creating/updating agents, modifying agent frontmatter (model, tools, description), designing agent architecture, or writing to */agents/*.md files.

Expert at creating and modifying Claude Code slash commands. Auto-invokes when creating/updating commands, modifying command frontmatter (model, allowed-tools, argument-hint), designing workflows, or writing to */commands/*.md files.

Expert at creating Claude Code event hooks for automation and policy enforcement. Auto-invokes when creating/updating hooks, modifying hooks.json, designing event-driven automation, or writing hook configurations.

Expert at integrating MCP servers into Claude Code plugins. Auto-invokes when configuring MCP servers (stdio/SSE/HTTP/WebSocket), writing .mcp.json files, or adding external tool integrations.

Expert at creating Claude Code plugins that bundle agents, skills, commands, and hooks. Auto-invokes when creating/structuring plugins, writing plugin.json manifests, or bundling components into packages.

Expert at performing task X automatically. Auto-invokes when the user wants to do Y, needs help with Z, or encounters situation W.

Expert at creating and modifying Claude Code skills. Auto-invokes when creating/updating skills, modifying skill frontmatter (allowed-tools, description), designing skill architecture, or writing to */skills/*/SKILL.md files.