rct-methodologylisted

# RCT Methodology Skill Transform specifications into executable, AI-agent-ready implementation checklists using the RCT (Representation Contract Tests) methodology. ## When to Use This Skill - Creating implementation checklists from specifications or design documents - Planning phased implementations for complex systems - When user mentions "RCT", "representation contracts", "Gate 0", or "agent-ready checklist" - When converting a specification into tasks an AI agent can execute autonomously ## Core Principle **Representations first. Behavior second. Internals last.** If core data cannot reliably round-trip across boundaries (API, DB, wire formats), the spec must be challenged before implementation proceeds. RCT prevents the two dominant risks in AI-assisted development: 1. **Representation mismatch** - wire/storage/tool formats don't behave as assumed 2. **Integration hell** - independently "perfect" components don't fit together ## The Four RCT Gates (Methodology Gates) ### Gate 0 - RCT MUST be green Representation contracts must pass before any behavior implementation: - Serialization/encoding for enums/IDs/links - NULL vs NONE semantics - Migration/versioning behavior - Persistence round-trip (write → read → equals) - External contract shapes **If Gate 0 fails:** Stop and revise. Do not proceed. ### Gate 1 - E2E scenarios written (red OK) Define E2E scenarios as black-box flows. Tests may be red but must: - Start reliably - Fail for expected reasons (not conne