What problem does it solve? Domain terminology drifts and architectural decisions get forgotten as a project grows, leaving future readers guessing why the code looks the way it does. This Skill actively sharpens a project's domain model by challenging vague terms, stress-testing concepts with concrete scenarios, and recording glossary entries and architectural decisions the moment they crystallize. ## Core Features & Use Cases - Ubiquitous Language Management: Maintains an opinionated CONTEXT.md glossary that picks canonical terms and lists words to avoid, with support for multi-context repos via CONTEXT-MAP.md. - Architectural Decision Records: Creates lightweight, sequentially numbered ADRs in docs/adr/, but only when a decision is hard to reverse, surprising without context, and the result of a real trade-off. - Active Model Sharpening: Challenges conflicting terminology, proposes precise terms for fuzzy language, invents edge-case scenarios, and cross-references user statements against the actual code. - Use Case: While designing an ordering system, a user says "cancel the account." The Skill flags that the glossary defines Customer and User separately, asks which is meant, updates CONTEXT.md with the resolved term, and offers an ADR when the team decides partial cancellation is supported. ## Quick Start Ask the assistant to help define the domain terminology for your project and record any significant architectural decisions as ADRs.