plugin-dev

Guided end-to-end plugin creation workflow with component design, implementation, and validation

Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins.

Use this agent when the user asks to "validate my plugin", "check plugin structure", "verify plugin is correct", "validate plugin.json", "check plugin files", or mentions plugin validation. Also trigger proactively after user creates or modifies plugin components.

Use this agent when the user has created or modified a skill and needs quality review, asks to "review my skill", "check skill quality", "improve skill description", or wants to ensure skill follows best practices. Trigger proactively after skill creation.

Use when the user asks to "create a slash command", "add a command", "create a hook", "add a PreToolUse/PostToolUse hook", "create an agent", "write a subagent", "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", or needs guidance on any plugin component: commands, hooks, agents, MCP servers, or output styles.

Use when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "configure plugin settings", "add LSP server", "configure language server", or needs guidance on plugin architecture, directory layout, manifest configuration, auto-discovery, or portable path references.

Use when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", "run skill evals", "benchmark skill performance", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.