What problem does it solve? Brownfield projects often lack up-to-date documentation, making it hard for developers and AI agents to understand the existing system before planning new features or writing a PRD. This Skill scans an existing codebase and produces a complete, structured documentation set ready for AI-assisted development. ## Core Features & Use Cases - Multi-Level Project Scanning: Choose quick (pattern-based), deep (critical directories), or exhaustive (all source files) scan levels, with automatic project type detection across 12 project types. - Full Documentation Generation: Produces index.md, project overview, architecture docs, source tree analysis, API contracts, data models, development and deployment guides, plus integration architecture for multi-part projects. - Deep-Dive Mode: Exhaustively documents a specific folder, feature, or API group with file inventories, dependency graphs, data flow analysis, and modification guidance. - Resumable State Tracking: Maintains a project-scan-report.json state file so interrupted scans can resume within 24 hours. - Use Case: Point the workflow at a legacy client/server repository, run a deep scan, and receive architecture-client.md, architecture-server.md, api-contracts, and an index.md that a brownfield PRD workflow can consume directly. ## Quick Start Ask the AI to document this project and choose a scan level when prompted.
