udecode/dotai

Use when creating or updating pull requests with comprehensive descriptions and meaningful commits - streamlines PR workflow with branch management and commit best practices

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions

Look up documentation and source code for libraries and packages. Use when the user asks a question about a library, needs to understand a library's API, or when you need information about a library that you don't know about. Triggers on questions like "How do I use X library?", "What's the API for Y?", "Show me how Z library handles this", or when encountering unfamiliar library usage.

Use when creating or updating draft pull requests without code review - streamlines draft PR workflow with meaningful descriptions and commit messages, focusing on work-in-progress documentation

Continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /learn command to review session learnings, (2) "save this as a skill" or "extract a skill from this", (3) "what did we learn?", (4) After any task involving non-obvious debugging, workarounds, or trial-and-error discovery. Creates new Claude Code skills when valuable, reusable knowledge is identified.

Use when reviewing pull requests with comprehensive code analysis, incremental or full review options, and constructive feedback - provides thorough code reviews with severity ratings

Use when implementing complex logic that needs test coverage - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first; NOT for UI components, simple CRUD, or straightforward code

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior