Agent skill

continuous-learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Stars 1
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/oldwinter/skills/tree/main/lenny-skills/continuous-learning

SKILL.md

Continuous Learning Skill

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

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 ~/.claude/skills/learned/

Configuration

Edit config.json to customize:

json
{
  "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:

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

Related

  • The Longform Guide - Section on continuous learning
  • /learn command - Manual pattern extraction mid-session

Comparison Notes (Research: Jan 2025)

vs Homunculus (github.com/humanplane/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

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

Expand your agent's capabilities with these related and highly-rated skills.

oldwinter/skills

fundraising

Plan and run an early-stage fundraising process and produce a Fundraising Pack (raise decision memo, round design brief, pitch narrative + deck outline, investor pipeline + tracker, outreach/follow-up scripts, diligence checklist). Use for fundraising, raising capital, venture capital, pitch deck, investor outreach, pre-seed, seed. Category: Career.

1 0
Explore
oldwinter/skills

ai-evaluation-evals

Create AI evaluation plans with benchmarks, rubrics, and error analysis workflows.

1 0
Explore
oldwinter/skills

giving-presentations

Plan and deliver persuasive, confident presentations and produce a Presentation Pack (brief, narrative, slide outline, Q&A bank, pre-brief plan, rehearsal plan, delivery checklist). Use for presentation, deck, keynote, all-hands, exec review, demo talk track. Category: Communication.

1 0
Explore
oldwinter/skills

personal-productivity

Build a Personal Productivity System Pack (weekly timebox plan, capture+to-do system, daily/weekly review rituals, and a 7-day rollout). Use for timeboxing, calendar blocking, and staying on top of high-volume leadership work. Category: Career.

1 0
Explore
oldwinter/skills

ai-product-strategy

Create an AI Product Strategy Pack (thesis, prioritized use cases, system plan, eval + learning plan, agentic safety plan, roadmap). Use for AI product strategy, LLM/agent strategy, AI roadmap, AI-first product direction.

1 0
Explore
oldwinter/skills

career-transitions

Plan and execute a career transition and produce a Career Transition Pack (progress metric + push/pull map, target archetypes, option scorecard, opportunity pipeline + outreach scripts, skills plan, 4–12 week experiment plan). Use for career change, career pivot, career transition, switching roles. Category: Career.

1 0
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results