Use whenever building or revising the system contract (architecture decisions, OpenAPI spec, data model) from an approved PRD — the 契约 station of DDT's 5-station spine.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when you have a spec or requirements for a multi-step task, before touching code
Use when executing implementation plans with independent tasks in the current session
Use at the start of every DDT session and before any DDT pipeline action — the DDT constitution governing Iron Laws, skill priority, the 5-station spine, intent classification,…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and…
Use to write a per-slice implementation spec before invoking ddt-writing-plans — the spec step of DDT's 实现 station.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any…
Use when the frontend slice does NOT route through ddt-design-source (external loop disabled) — produce production-grade frontend code directly bound to the OpenAPI contract, with…
Use at the 交付 (delivery) station of DDT's 5-station spine, after 验证 station passes — produces README, deployment guide, demo script, and (via Plan 5 metrics layer) the AI…
Use during a frontend slice's spec step when the convergence target is judged perceptually by a human (UI aesthetics/UX) — routes the perceptual problem to an external AI design…
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
Use when implementing any feature or bugfix, before writing implementation code