What problem does it solve? Domain terminology drifts and key architectural decisions go unrecorded during software design, leaving future readers guessing why the code looks the way it does. This Skill actively sharpens a project's domain model by challenging fuzzy terms, stress-testing concepts with concrete scenarios, and writing down glossary entries and decisions the moment they crystallize. ## Core Features & Use Cases - Ubiquitous language management: Maintains a CONTEXT.md glossary with opinionated canonical terms and explicit _Avoid_ lists, supporting single-context repos and multi-context setups via CONTEXT-MAP.md. - Architectural decision records: Creates sequentially numbered ADRs in docs/adr/ only when a decision is hard to reverse, surprising without context, and the result of a real trade-off. - Live model challenging: Flags conflicts between user language and the existing glossary, cross-references claims against actual code, and updates files inline rather than batching. - Use Case: While designing an ordering system, a user says "account" ambiguously; the Skill asks whether they mean Customer or User, records the resolved term in CONTEXT.md, and offers an ADR when the team picks event-sourced writes over a CRUD model. ## Quick Start Help me pin down the domain terminology for my ordering system and record any significant architectural decisions we make along the way.