continuous-learning-v2

Analyze Claude Code sessions to generate atomic instincts with confidence scores.

Updated Jan 30, 2026
One-click install
npx skills add https://github.com/GoBeromsu/My-Awesome-RA --skill continuous-learning-v2-goberomsu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: continuous-learning-v2
Source: https://github.com/GoBeromsu/My-Awesome-RA/tree/main/.claude/skills/continuous-learning-v2
Command: npx skills add https://github.com/GoBeromsu/My-Awesome-RA --skill continuous-learning-v2-goberomsu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Observations from Claude Code sessions are captured, transformed into atomic instincts with confidence scores, and evolved into reusable skills, commands, and agents to improve automation and learning over time.

Core Features & Use Cases

  • Atomic instincts with confidence scoring that capture repeated patterns in tool usage and prompts.
  • Evolution pipeline that clusters instincts into skills, commands, and agents for reusability.
  • Local-first learning with hooks-based observation and export capabilities for sharing and reuse.

Quick Start

Enable observation hooks, initialize the homunculus directories, and begin using the instinct lifecycle to observe, evolve, and export.

Frequently Asked Questions about continuous-learning-v2

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track Claude Code sessions to build reusable skills?

You can track Claude Code sessions by enabling observation hooks that capture tool usage events, which the system then analyzes to generate atomic instincts and evolve them into reusable skills, commands, and agents.

What are atomic instincts in continuous learning automation?

Atomic instincts are captured patterns from repeated tool usage and prompts, assigned confidence scores to evaluate their reliability before evolving into higher-level reusable artifacts like commands and agents.

How do I turn repeated tool usage patterns into reusable commands?

The system clusters atomic instincts through an evolution pipeline that groups repeated tool usage patterns into reusable commands, agents, and skills, assigning confidence scores based on session activity.

Do I need any external dependencies to analyze session activity with hooks?

No external dependencies are required. The system operates local-first, using hooks-based observation to capture session data and tool usage events directly within your environment to identify patterns.

Can I export evolved skills and instincts for reuse across different projects?

Yes, the system includes export capabilities that allow you to share and reuse evolved artifacts, skills, and commands generated from clustered instincts across different environments.

What is the best way to initialize homunculus directories for instinct evolution?

Initialize homunculus directories during the quick start phase after enabling observation hooks, which sets up the local-first environment needed to observe, evolve, and export session patterns.