This skill should be used when the user asks to "review this code", "check my implementation", "review before merge", "get feedback on changes", or after completing major features. Also use proactively before merging to catch issues early. Dispatches code-reviewer subagent.
This skill should be used BEFORE saying "done", "fixed", "complete", "it works", "tests pass", "ready for review", or creating commits/PRs. Run verification commands and confirm output BEFORE making success claims. Evidence before assertions, always. If you haven't run tests/build/lint, you cannot claim completion.
Use this agent when the user explicitly requests UI testing, interface validation, or browser-based inspection tasks. This agent is specifically designed to operate the Playwright MCP Server in isolation to prevent context pollution in the main agent. Examples: Context: User wants to verify that a new feature renders…
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Interact with Google Workspace (Gmail, Drive, Calendar, Docs, Sheets, Tasks) via the gws CLI. Use when the user asks to read emails, check calendar, manage drive files, send emails, create events, read spreadsheets, or any Google Workspace operation.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
This skill should be used when the user asks to "create an issue", "write a spec", "document this task", "make a task spec", "create issue spec", or needs a markdown document describing a task with implementation plan. Saves to issues/YYYYMMDD-description.md.
This skill should be used when the user asks to "update documentation", "sync docs with code", "audit docs", "archive old plans", "check if docs are outdated", "verify documentation accuracy", or wants to ensure documentation matches the current codebase state.
This skill should be used when the user asks to "write a plan", "create an implementation plan", "plan this feature", "break this down", "document the approach", or has a spec/requirements for a multi-step task. Use BEFORE touching code - creates comprehensive bite-sized implementation plans saved to docs/plans/.
Search and find previous code agent sessions (Claude-Code or Codex-CLI) for specific work, decisions, or code patterns. Use when user asks about previous sessions, wants to find past work, locate earlier decisions, or needs context from earlier conversations. Returns concise summaries without polluting main context.
This skill should be used when the user asks "where was I?", "what was I working on?", "continue from last session", "resume previous work", "pick up where I left off", "recover context", "restore context", or references a session lineage shown at conversation start. Also use when starting a new conversation that has…
This skill should be used when the user asks to "find previous session", "search sessions", "what did I work on before", "find that code from last time", "search conversation history", or needs to find work, decisions, or code patterns from past sessions. For agents WITHOUT subagent support - if you have Task tool…
Process video files with FFmpeg and analyze them with Gemini AI. Use when extracting clips, taking screenshots at timestamps, splitting long videos, analyzing video content with AI, transcribing/translating speech in video, building timestamped shot inventories, verifying cut points, assembling montages/grid walls…