SDD step 1. Analyse a feature request and produce a detailed feature.md spec. Use when the user describes a new feature they want to build. Asks for missing details before writing the spec.
SDD step 0. Analyse the project codebase and create docs/project.md with tech stack, architecture, and conventions. Run once before starting SDD in a new project. If docs/project.md already exists, asks whether to regenerate it.
SDD step 3. Read feature.md and produce a detailed implementation plan.md tailored to the project's tech stack and architecture. Use after /sdd-feature has produced feature.md.
SDD step 2 (optional, repeatable). Read an existing feature.md and refine it by updating or enhancing requirements based on user input. Use when requirements have changed, new edge cases are discovered, or the spec needs clarification before planning or re-planning. Run before /sdd-plan if plan.md already exists.
SDD fast path. Runs the full pipeline — analyse → plan → implement → review → archive — with a single confirmation gate before implementation begins. Stops automatically if Critical or Major issues are found in review. Use when you want to ship a well-understood feature with minimal interruptions.
SDD step 7. Archive feature.md and plan.md into docs/specs-archive/<yyyymmddHHMM>-<feature-name>/ directory, then update docs/project.md with the new feature, and any architecture decisions made. Use after /sdd-review is complete and the feature is ready to merge.
SDD step 5. Reviews the implemented feature code against language and framework best practices, checks for code duplication, security vulnerabilities, performance issues, test coverage, and alignment with feature.md acceptance criteria. Use after /sdd-implement or on any existing feature implementation.
SDD step 4. Read plan.md and implement the feature step by step, then verify all acceptance criteria are met. Use after /sdd-plan has produced plan.md.