continuous-learning

Automatically evaluates Claude Code sessions on end to extract reusable patterns that can be saved as learned skills. This skill runs as a Stop hook at the end of each session: Edit config.json to customize: Add to your ~/.claude/settings.json : Homunculus v2 takes a more sophisticated approach: Key insight from homunculus: "v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time. v2 uses hooks for observation (100% reliable) and instincts as the atomic unit of learned behavior." See: docs/continuous-learning-v2-spec.md for full spec. - Setting up automatic pattern extraction from Claude Code sessions - Configuring the Stop hook for session evaluation - Reviewing or curating learned skills in ~/.claude/skills/learned/ - Adjusting extraction thresholds or pattern categories - Comparing v1 (this) vs v2 (instinct-based) approaches - Session Evaluation : Checks if session has enough messages (default: 10+) - Pattern Detection : Identifies extractable patterns from the session - Skill Extraction : Saves useful patterns to ~/.claude/skills/learned/ - Lightweight : Runs once at session end - Non-blocking : Doesn't add latency to every message - Complete context : Has access to full session transcript - The Longform Guide - Section on continuous learning - /learn command - Manual pattern extraction mid-session - Instinct-based learning - Smaller, atomic...