What problem does it solve? Raw intent inputs like brain dumps, meeting transcripts, PRDs, and customer emails are unstructured and inconsistent, making them unreliable inputs for downstream planning and implementation work. This Skill condenses any such input into a canonical SPEC.md contract with a stable five-field kernel (Why, Capabilities, Constraints, Non-goals, Success signal) that downstream skills and agents can consume without ambiguity. ## Core Features & Use Cases - Spec distillation: Transforms any intent input into SPEC.md plus content-typed companion files (glossaries, diagrams, entity catalogs), preserving every load-bearing claim. - Append-only memory log: Records every decision, capability, and assumption in .memlog.md and re-derives SPEC.md from it, so updates never cause merge drift and capability IDs stay stable. - Validation and story breakdown: Self-validates each spec against eight Spec Law rules and can break a spec into a stories.yaml file of independently shippable slices. - Use Case: Paste a messy Slack thread about a new feature and receive a spec folder containing SPEC.md, a glossary companion, and a validated capability list ready for PRD, UX, or architecture skills. ## Quick Start Ask the assistant to distill the attached product brief into a spec using the bmad-spec skill.
