continuous-learning

name	continuous-learning
description	Automatically extract reusable patterns from Gemini Code sessions and save them as learned skills for future use.
origin	EGC

Continuous Learning Skill

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

When to Activate

• Setting up automatic pattern extraction from Gemini Code sessions
• Configuring the Stop hook for session evaluation
• Reviewing or curating learned skills in ~/.gemini/skills/learned/
• Adjusting extraction thresholds or pattern categories
• Comparing v1 (this) vs v2 (instinct-based) approaches

Status

This v1 skill is still supported, but continuous-learning-v2 is the preferred path for new installs. Keep v1 when you explicitly want the simpler Stop-hook extraction flow or need compatibility with older learned-skill workflows.

How It Works

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

1. Session Evaluation: Checks if session has enough messages (default: 10+)
2. Pattern Detection: Identifies extractable patterns from the session
3. Skill Extraction: Saves useful patterns to ~/.gemini/skills/learned/

Configuration

Edit config.json to customize:

{
  "min_session_length": 10,
  "extraction_threshold": "medium",
  "auto_approve": false,
  "learned_skills_path": "~/.gemini/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 ~/.gemini/settings.json:

{
  "hooks": {
    "Stop": [{
      "matcher": "*",
      "hooks": [{
        "type": "command",
        "command": "~/.gemini/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

Related

• Felipe Marzochi - Section on continuous learning
• /learn command - Manual pattern extraction mid-session

---

Comparison Notes (Research: Jan 2025)

vs instinct-based observation (continuous-learning-v2)

The instinct-based design in continuous-learning-v2 takes a more granular approach:

Feature	This skill	Instinct-based 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

Why the v2 design observes through hooks: skill-triggered observation is probabilistic, firing on only part of the relevant events, while hook-driven observation fires on every tool call. Atomic instincts with confidence scores then become the unit of learned behavior instead of whole skills.

Potential v2 Enhancements

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

See: docs/continuous-learning-v2-spec.md for full spec.