What problem does it solve? Turning vague ideas, brain dumps, PRDs, transcripts, or mixed multi-source material into a single canonical specification is error-prone: decisions get lost, capability IDs drift, and downstream teams work from divergent documents. This Skill produces a preservation-validated SPEC.md kernel plus companion files that every downstream workflow consumes as the machine contract. ## Core Features & Use Cases - Spec distillation: Converts any intent input into the five-field kernel (Why, Capabilities, Constraints, Non-goals, Success signal) with stable CAP-N identifiers. - Append-only memory log: Records every decision, constraint, and assumption in .memlog.md and re-derives SPEC.md from it, so updates never cause merge drift. - Two-pass self-validation: Enforces eight Spec Law rules covering coherence and preservation of every load-bearing source claim. - Story breakdown: Optionally generates stories.yaml with checkpoints and dispatch notes for independently shippable slices. - Use Case: Paste a customer email thread and a meeting transcript, and receive a spec folder containing SPEC.md, a glossary companion, and a memlog with open questions flagged for human decision. ## Quick Start Ask the assistant to distill the attached product brief into a spec and validate it against the spec rules.
