Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use after completing an implementation task or major feature, and before claiming ready/merge, to verify the work meets requirements via a focused reviewer subagent.
Use after an implementation plan exists and it contains independent tasks that can be delegated to fresh subagents in the current session.
Use after planning/brainstorming when implementation begins for any feature or bugfix, before writing production code; requires tests first and red-green verification.
Use after an approved design/spec or clear requirements exist and before implementing a multi-step task; creates a task-by-task implementation plan before code changes.
Use after making code changes, before committing, or when the user asks to "simplify", "clean up", or "review" recent edits — runs three parallel review agents (reuse, quality, efficiency) over the diff and fixes the findings.
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or evaluating a plan/design. Relentlessly explores user intent, requirements, trade-offs, and decision branches before implementation.
Use when the user asks to "commit", "create a commit", "git commit", "stage and commit", or invokes /skill:commit. Creates git commits following the gitmoji convention.