What problem does it solve? Domain terminology drifts and architectural decisions get forgotten, leaving future readers guessing why the code looks the way it does. This Skill keeps a project's ubiquitous language and decision history accurate by challenging fuzzy terms, cross-checking claims against code, and recording CONTEXT.md entries and ADRs the moment they crystallize. ## Core Features & Use Cases - Glossary sharpening: Detects vague or conflicting terminology during discussion, proposes canonical terms, and updates CONTEXT.md inline using a strict opinionated format. - ADR authoring with discipline: Offers an Architecture Decision Record only when a decision is hard to reverse, surprising without context, and the result of a real trade-off, using a minimal one-paragraph template. - Multi-context support: Handles both single-context repos (one root CONTEXT.md) and multi-context repos via a CONTEXT-MAP.md that maps bounded contexts and their relationships. - Use Case: While designing a billing feature, a user says "account" ambiguously; the Skill asks whether they mean Customer or User, resolves the term, writes it into CONTEXT.md, and later records an ADR explaining why Billing communicates with Ordering via domain events instead of synchronous HTTP. ## Quick Start Ask the assistant to use the domain-modeling skill to review the terminology in your design discussion and record the agreed terms and decisions in CONTEXT.md and docs/adr/.
