What problem does it solve? Teams lose alignment when domain terms are vague, overloaded, or contradict the code, and when architectural decisions are made without recorded rationale. This Skill actively sharpens a project's domain model by challenging fuzzy terminology, stress-testing concepts with concrete scenarios, and capturing glossary terms and important decisions the moment they crystallize. ## Core Features & Use Cases - Ubiquitous Language Management: Maintains a CONTEXT.md glossary with opinionated term definitions and explicit _Avoid_ lists, updated inline as terms are resolved. - Terminology Challenge & Scenario Probing: Flags conflicts between user language and the glossary, sharpens vague terms, and invents edge-case scenarios to force precision about concept boundaries. - Living Decision Records: Adds or updates entries in a single living important-decisions document only when a choice is hard to reverse, surprising without context, and involves a real trade-off. - Use Case: While designing an order system, a user says "cancel the account" — the Skill asks whether they mean the Customer or the User, records the resolved term in CONTEXT.md, and offers a decision entry when the team commits to a hard-to-reverse cancellation policy. ## Quick Start Ask the agent to help define the domain terminology for a new feature and record any important architectural decisions in the repository's living decisions document.
