What problem does it solve? Project knowledge gets scattered across README files, legacy TODO/HISTORY documents, GitHub Issues, PRs, and commits, leaving agents and developers without a reliable source of durable truth. This Skill organizes that sprawl into maintained canonical files (README, AGENTS, DECISIONS, RUNBOOK) while migrating legacy operational tracking into GitHub Issues. ## Core Features & Use Cases - Knowledge distillation: Reads local documentation and GitHub sources (Issues, PRs, commits) and routes only durable knowledge into README.md, AGENTS.md, DECISIONS.md, and RUNBOOK.md. - Legacy migration: Migrates TODO.md, HISTORY.md, and OPEN_QUESTIONS.md into GitHub Issues through a deterministic, dry-run-by-default script with semantic classification and cutover validation. - Traceability catalog: Maintains .agent/catalog/SOURCE_INDEX.md and PROCESSING_RUNS.md so every processed source and run is auditable. - Use Case: A repository still tracks work in TODO.md and HISTORY.md. Run the migration workflow to classify each legacy entry, create or link GitHub Issues, distill knowledge-only content into canonical docs, and validate the cutover before deleting the legacy files. ## Quick Start Ask the agent to inventory this project's documentation and GitHub sources, then update README, AGENTS, DECISIONS, and RUNBOOK with the durable knowledge it finds.