What problem does it solve? Brownfield projects often lack documentation that AI agents and developers need to understand existing architecture, APIs, and data models before planning new features. This Skill scans an existing codebase and produces a complete, structured documentation set ready for brownfield PRD workflows. ## Core Features & Use Cases - Multi-Level Scanning: Choose quick (pattern-based), deep (critical directories), or exhaustive (all source files) scan levels, with batching and write-as-you-go output to manage context. - Project Classification: Detects monolith, monorepo, and multi-part structures, classifies each part against 12 project types, and generates per-part architecture, API contract, and data model documents. - Deep-Dive Mode: Performs exhaustive file-by-file analysis of a selected folder, feature, or API group, producing dependency graphs, data flow traces, and modification guidance. - Resumable State: Tracks progress in a state file so interrupted scans can resume within 24 hours. - Use Case: Point the workflow at a legacy full-stack repository to generate an index.md, architecture docs, source tree analysis, and development guides that an AI agent can use to plan new features. ## Quick Start Ask the AI to document this project and follow the prompts to choose a scan level and confirm the detected project structure.
