What problem does it solve? Onboarding onto an unfamiliar codebase requires hours of manual exploration, and README files often describe intended rather than actual architecture. This Skill automates repository discovery and produces grounded documentation where every claim is traceable to source files or terminal output. ## Core Features & Use Cases - Automated Repository Scanning: Runs a Python scan script detecting manifests for 25+ languages, CI/CD pipelines, containers, security configs, code metrics, and high-churn files. - Seven Structured Documents: Produces STACK.md, STRUCTURE.md, ARCHITECTURE.md, CONVENTIONS.md, INTEGRATIONS.md, TESTING.md, and CONCERNS.md in docs/codebase/ using fill-in templates. - Evidence-First Validation: Enforces a four-phase workflow with a validation loop, marking unknowns as [TODO] and intent-dependent decisions as [ASK USER]. - Use Case: A developer joining a new team runs the skill on the project repository and receives a complete, verifiable onboarding document set covering architecture, conventions, and known technical debt. ## Quick Start Ask the AI to map this codebase and generate onboarding documentation, optionally specifying a focus area such as architecture only.
