What problem does it solve? Valuable lessons learned during debugging, feature implementation, and design discussions are often lost between sessions, forcing developers and AI agents to rediscover the same patterns and repeat the same mistakes. ## Core Features & Use Cases - Executable Contract Capture: Records concrete signatures, request/response fields, environment keys, and validation/error matrices rather than vague 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. - Spec vs Guide Separation: Enforces a clear distinction between code-specs (how to implement) in layer directories and thinking checklists in guides/. - Use Case: After fixing a subtle API error-handling bug, use this Skill to document the validation matrix, wrong-vs-correct examples, and required tests in the relevant .trellis/spec/ file so future sessions avoid the same issue. ## Quick Start Ask the AI to update the code-spec with what was just learned from the completed task or bug fix.
