codebase▌

Systematically analyze an unfamiliar codebase and produce a structured onboarding guide. Designed for developers joining a new project or setting up Claude Code in an existing repo for the first time.

Generates GitHub Copilot migration instructions by analyzing code differences between project versions. \n \n Compares two project states (branches, commits, or tags) to extract transformation patterns, API changes, and architectural shifts \n Creates a .github/copilot-migration-instructions.md file with mandatory rules, validated transformations, API correspondences, and obsolete patterns to avoid \n Supports multiple migration types: framework version upgrades, architecture refactoring, techno

Analyze codebases for architectural friction and propose module-deepening refactors as testability improvements. \n \n Explores codebases organically to surface shallow modules, tightly-coupled components, and untested seams rather than following rigid heuristics \n Applies John Ousterhout's \"deep module\" principle: small interfaces hiding large implementations for better testability and AI navigability \n Generates multiple radically different interface designs (minimalist, flexible, caller-o

Search and navigate large codebases with semantic search, grep patterns, and file discovery. \n \n Supports three search modes: semantic search for conceptual queries, grep for exact text and regex patterns, and glob for file discovery by type or naming convention \n Includes workflow guidance for common scenarios like tracing function calls, understanding feature implementations, locating bugs, and performing impact analysis \n Provides language-specific patterns for Python, JavaScript, TypeScr