What problem does it solve? Valuable lessons from debugging sessions, feature implementations, and design discussions are often lost between sessions, forcing developers and AI assistants to rediscover the same contracts, conventions, and gotchas repeatedly. ## Core Features & Use Cases - Executable Contract Capture: Records concrete signatures, request/response fields, environment keys, and validation/error matrices rather than abstract principles. - Structured Update Workflow: Guides classification of learnings into design decisions, conventions, patterns, anti-patterns, common mistakes, and gotchas with ready-to-use Markdown templates. - Code-Spec vs Guide Separation: Enforces a clear distinction between implementation specs (how to write code) and thinking guides (what to consider), keeping .trellis/spec/ organized. - Use Case: After fixing a subtle API validation bug, use this Skill to document the exact error matrix, good/base/bad cases, and required tests in the relevant backend spec so future sessions never repeat the mistake. ## Quick Start Ask the AI to update the project specs with what was just learned from the completed task or bug fix.
