flag-feedback

Generates requirements documentation (user stories, acceptance criteria, out-of-scope) for a feature in an AI-native MVP project. Invoke before any implementation of a new feature begins — a feature without requirements documentation should not be built. If the developer mentions wanting to add or implement something new, trigger this skill before any code is written.

Scans all authoritative documents (constitution, context, glossary, requirements) and all derivative documents (architecture decisions, architecture overview, MVP architecture spec, vision, implementation heuristics) to add missing citations, replace stale duplicate facts with pointers, and correct contradictions. Use this skill whenever a document has been written or revised in the current phase, whenever you suspect a constraint in one document is not reflected in another, or whenever an agent reading multiple documents has flagged a conflict. Safe to re-run — applying it a second time produces the same result as the first.

Enriches each user story's acceptance criteria with a "Relevant constraints" line pointing to the specific architecture decisions, implementation heuristics, design principles, and UI kit that apply to that story. Use this skill after any phase that introduces new constraints — after architecture decisions are written (Phase 3), after the UI kit is approved (Phase 4), and after implementation heuristics and design principles are established (Phase 5). Also invoke whenever a Phase 6 agent reads the acceptance criteria and lacks a clear picture of which constraints govern a particular story. Safe to re-run at any phase — each invocation only adds constraints not already listed; nothing is ever removed from an existing entry.