What problem does it solve? Codebases drift into inconsistent terminology and undocumented decisions, leaving future readers guessing why things were built a certain way. This Skill actively sharpens a project's domain model during design discussions by resolving ambiguous terms, keeping a canonical glossary, and recording hard-to-reverse decisions. ## Core Features & Use Cases - Glossary Management: Builds and updates CONTEXT.md with opinionated term definitions, canonical names, and Avoid lists for rejected synonyms, supporting both single-context and multi-context repos via CONTEXT-MAP.md. - Terminology Challenges: Detects when code and conversation use two names for one concept, cites both locations, and resolves them into a single canonical term. - Selective ADR Recording: Offers Architecture Decision Records only when a decision is hard to reverse, surprising without context, and the result of a real trade-off, using a minimal numbered format in docs/adr/. - Use Case: While discussing a new reporting endpoint, the Skill notices the code calls a concept "Sleeve" in one module and "bucket" in another, surfaces the collision with file references, and updates CONTEXT.md with the resolved term inline. ## Quick Start Ask the assistant to use the domain-modeling skill to review the terminology in your codebase discussion and update CONTEXT.md with any resolved terms.
