What problem does it solve? Managing long-running AI coding sessions often leads to lost context, unorganized history, and no way to branch or recover work. This Skill provides operational guidance for NanoClaw v2, a session-aware REPL that persists conversations as markdown files and keeps sessions task-focused. ## Core Features & Use Cases - Persistent Sessions: Markdown-backed session storage with branching via /branch and cross-session search via /search. - Session Lifecycle Management: Switch models with /model, compact history with /compact, and export to md/json/txt with /export. - Extension Guidance: Rules for extending scripts/claw.js while preserving zero external runtime dependencies and markdown-as-database compatibility. - Use Case: Before attempting a high-risk refactor, branch your current session, complete the work, compact the history at the milestone, and export the session for archival. ## Quick Start Ask the AI to start a NanoClaw session, switch to your preferred model with /model, and branch the session before making risky changes.