This skill should be used when the user asks to run multiple agents in parallel, dispatch subagents concurrently, parallelize work across agents, or orchestrate parallel task execution. Triggers include phrases like "run these in parallel", "dispatch agents simultaneously", "parallelize this work", "concurrent…
This skill should be used when the user asks to "execute the plan", "run the plan", "implement the plan", "follow the plan", "start implementing", or when there's a written plan file in docs/plans/ to execute. Provides batch execution with checkpoints for review between batches.
This skill should be used when the user asks to "run tasks in parallel", "use subagents", "implement in parallel", "dispatch agents for each task", or when executing implementation plans where tasks are independent. Dispatches fresh subagent per task with two-stage review (spec compliance then code quality).
This skill should be used when the user asks "which model should I use", "compare model prices", "cheapest LLM", "fastest model", "AI Gateway setup", "unified endpoint", "multi-provider AI", "model fallback", "OpenAI compatible endpoint", or questions about GPT-5.4, GPT-5, GPT-5-mini, GPT-5-nano, Claude 4.5, Claude…
Use when generating content with Google Gemini at scale - provides parallel batch processing, retry logic, output validation, and file caching patterns for Vertex AI.
This skill should be used when WebFetch fails (403, blocked, timeout), when the user asks to "scrape this URL", "fetch this page", "search the web for", "find articles about", or when you need to extract content from a URL that blocks standard fetching. Provides Firecrawl for scraping and Exa for semantic search as…
This skill should be used when users ask about deploying to Cloudflare Workers, setting up D1 databases, configuring KV or R2 storage, or troubleshooting Wrangler deployments. Triggers include phrases like "deploy to Cloudflare", "set up D1 database", "configure KV storage", "wrangler dev not working", "Workers…
This skill should be used when the user reports a bug, test failure, error, crash, unexpected behavior, or says "it's not working", "this broke", "why is this failing", "debug this", "find the root cause", "investigate this error". Use BEFORE proposing fixes - root cause investigation must complete first.
This skill should be used when the user asks to "write tests first", "use TDD", "test-driven", "red-green-refactor", "write failing test", or when implementing features where test quality matters. Use BEFORE writing implementation code - tests must exist and fail before any production code is written.
This skill should be used when the user says "I'm done", "implementation complete", "ready to merge", "how should I integrate this", "create a PR", "finish this branch", or when all tests pass and work is ready for integration. Presents structured options for merge, PR, or cleanup.
This skill should be used when the user asks to "commit", "make a commit", "commit these changes", "write a commit message", "review staged changes", "what should I commit", "help me commit", or after completing implementation work that should be committed. Generates safe, chunked commits with sensitive file…
This skill should be used when the user shares code review feedback, review comments, PR feedback, "reviewer said X", "got feedback on my code", or when receiving suggestions that seem unclear or technically questionable. Requires technical rigor and verification - not blind implementation.
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.
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/.
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…