What problem does it solve? Writing functional specifications manually often produces vague feature lists, untestable requirements, and missing acceptance criteria. This Skill produces structured, evidence-tagged functional specs with enforced completeness rules before architecture or development begins. ## Core Features & Use Cases - Deterministic Spec Compilation: Validates and renders structured JSON specs into Markdown via scripts/compile-functional-spec.py, rejecting specs with fewer than 8 use cases or missing acceptance criteria. - Evidence-Tagged Analysis: Every finding is tagged [CODE], [CONFIG], [DOC], [INFERENCE], or [ASSUMPTION], with a warning banner when assumptions exceed 30%. - Platform Feasibility Lens: Maps requirements to Firebase (Firestore), Vercel, and Hostinger platforms, including Firestore collection metadata with owner, PII, indexes, and retention. - Use Case: Given stakeholder interviews and policy documents for a field-service MVP, produce a spec with MVP modules, 8+ actor-goal use cases, typed business rules traceable to use cases, and Given/When/Then acceptance criteria. ## Quick Start Ask the AI to create a functional specification for your MVP from your project documents, including at least eight use cases, business rules, acceptance criteria, and Firestore data model notes.