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. This Skill scans an existing codebase and produces a complete, structured documentation set ready for brownfield PRD workflows. ## Core Features & Use Cases - Multi-Level Project Scanning: Choose quick (pattern-only), deep (critical directories), or exhaustive (all source files) scan levels, with automatic project type detection across 12 types (web, mobile, backend, CLI, library, game, and more). - Full Documentation Generation: Produces index.md, project-overview, architecture, source-tree-analysis, component-inventory, development-guide, api-contracts, data-models, and integration-architecture files, including per-part docs for monorepos and multi-part projects. - Deep-Dive Mode: Exhaustively reads every file in a chosen feature, folder, or API group to produce dependency graphs, data flow analysis, and implementation guidance. - Resumable State Tracking: Maintains a project-scan-report.json state file so interrupted scans can resume within 24 hours. - Use Case: Point the Skill at a legacy full-stack repository and receive a linked documentation set that an AI agent can use to plan new features without re-reading the entire codebase. ## Quick Start Ask the AI to document the project by saying "document project" and then choose a scan level when prompted.
