Use when the human partner asks a question, reports a problem, requests a change, or follows up in an agent tool such as Cursor, Claude Code, Codex, Kimi, OpenCode, or Pi, including 提问, 咨询, bug reports, feature requests, and UI or docs discussions
Use when the human partner explicitly asks to be grilled, deeply interviewed, or questioned one decision at a time about an unclear programming feature, refactor, architecture choice, or complex implementation before action begins
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions. Source-change pressure to skip, defer, or bypass a failing test requires test-driven-development before…
You MUST use this before creative or behavior-changing work — creating features, building components, adding functionality, modifying behavior, or ambiguous product intent. Explores user intent, requirements and design before implementation.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation