What problem does it solve? Teams lose track of domain terminology and the reasoning behind architectural choices, leading to inconsistent language in code and repeated debates about settled decisions. This Skill actively builds a ubiquitous language glossary (CONTEXT.md) and records architectural decision records (ADRs) as they crystallize during design discussions. ## Core Features & Use Cases - Ubiquitous Language Management: Challenges conflicting or fuzzy terms, proposes canonical vocabulary, and updates CONTEXT.md inline with opinionated definitions and avoided synonyms. - Architectural Decision Records: Offers ADRs only when decisions are hard to reverse, surprising without context, and the result of real trade-offs, using a minimal numbered format in docs/adr/. - Multi-Context Support: Handles single-context repos with one CONTEXT.md or multi-context repos via a CONTEXT-MAP.md describing bounded contexts and their relationships. - Use Case: While designing an ordering system, the user says "account" ambiguously; the Skill asks whether they mean Customer or User, records the resolved term in CONTEXT.md, and drafts an ADR when the team picks event-sourced orders over a CRUD model. ## Quick Start Ask the AI to help define the domain terminology for your project and record the key architectural decisions as ADRs.