Continuous Learning Skill Skill

Continuous Learning Skill

Automatically evaluates Claude Code sessions on end to extract reusable patterns that can be saved as learned skills.

Maestro Integration

Lifecycle: cross-cutting Activates when: maestro:new-track detects relevant tech in tech-stack.md, or maestro:implement encounters matching task types.

Phase Guidance

In maestro:cross-cutting: Extract patterns after significant implementation or debugging sessions. Save as reusable skills for future reference.

Related Skills

maestro:continuous-learning-v2
maestro:strategic-compact
maestro:eval-harness

How It Works

This skill runs as a Stop hook at the end of each session:

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/

Configuration

Edit config.json to customize:

{
  "min_session_length": 10,
  "extraction_threshold": "medium",
  "auto_approve": false,
  "learned_skills_path": "~/.claude/skills/learned/",
  "patterns_to_detect": [
    "error_resolution",
    "user_corrections",
    "workarounds",
    "debugging_techniques",
    "project_specific"
  ],
  "ignore_patterns": [
    "simple_typos",
    "one_time_fixes",
    "external_api_issues"
  ]
}

Pattern Types

| Pattern | Description | |---------|-------------| | error_resolution | How specific errors were resolved | | user_corrections | Patterns from user corrections | | workarounds | Solutions to framework/library quirks | | debugging_techniques | Effective debugging approaches | | project_specific | Project-specific conventions |

Hook Setup

Add to your ~/.claude/settings.json:

{
  "hooks": {
    "Stop": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.claude/skills/continuous-learning/evaluate-session.sh"
      }]
    }]
  }
}

Why Stop Hook?

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

Comparison Notes (Research: Jan 2025)

vs Homunculus

Homunculus v2 takes a more sophisticated approach:

| Feature | Our Approach | Homunculus v2 | |---------|--------------|---------------| | Observation | Stop hook (end of session) | PreToolUse/PostToolUse hooks (100% reliable) | | Analysis | Main context | Background agent (Haiku) | | Granularity | Full skills | Atomic "instincts" | | Confidence | None | 0.3-0.9 weighted | | Evolution | Direct to skill | Instincts → cluster → skill/command/agent | | Sharing | None | Export/import instincts |

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."

Potential v2 Enhancements

Instinct-based learning - Smaller, atomic behaviors with confidence scoring
Background observer - Haiku agent analyzing in parallel
Confidence decay - Instincts lose confidence if contradicted
Domain tagging - code-style, testing, git, debugging, etc.
Evolution path - Cluster related instincts into skills/commands

See: /Users/affoon/Documents/tasks/12-continuous-learning-v2.md for full spec.

Relationship to Maestro Workflow

/maestro:new-track -- Detects this skill during Step 9.5 (skill matching)
/maestro:implement -- Loads this skill's guidance during task execution
/maestro:review -- Uses checklists as review criteria

Agent Skills: Continuous Learning Skill

Install this agent skill to your local

Skill Files