continuous-learning-v2

Transform Claude Code sessions into atomic instincts with confidence scores.

2|2|Updated Mar 12, 2026

Search Tags:#hooks #skills #learning #agents #evolve #instincts #project-scoped

Ready to run

npx skills add https://github.com/zhmxiaowo/opencode-simple --skill continuous-learning-v2-zhmxiaowo

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: continuous-learning-v2
Source: https://github.com/zhmxiaowo/opencode-simple/tree/main/.opencode/skills/continuous-learning-v2
Command: npx skills add https://github.com/zhmxiaowo/opencode-simple --skill continuous-learning-v2-zhmxiaowo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

The Continuous Learning v2 system transforms Claude Code sessions into atomic instincts with confidence scoring, enabling them to evolve into reusable skills, commands, and agents while supporting project-scoped isolation to prevent cross-project contamination.

Core Features & Use Cases

Observes session activity via hooks to capture patterns and corrections.
Creates atomic instincts with confidence scores and preserves them for evolution into skills, commands, and agents.
Supports project-scoped instincts by default and global instincts when appropriate to enable cross-project learning without leakage.

Quick Start

Enable the observer and start capturing sessions to begin evolving instincts into skills.

Frequently Asked Questions about continuous-learning-v2

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

FAQPage Schema

How do I capture Claude Code sessions and turn them into reusable skills?▼

To capture Claude Code sessions and turn them into reusable skills, you enable observer hooks that log session activity into atomic instincts with confidence scores. These instincts evolve into structured skills, commands, and agents through an automated workflow.

What are atomic instincts in continuous learning and how do confidence scores work?▼

Atomic instincts in continuous learning are granular behavioral patterns captured from session hooks. Each instinct receives a confidence score that determines its reliability, guiding its evolution into mature skills, commands, and agents.

How do I start evolving Claude Code session patterns into agents and commands?▼

You start evolving session patterns by enabling the observer hooks to capture activity. The system generates atomic instincts with confidence scores that progressively evolve into commands and agents using a frontmatter-driven skill manifest.

Does continuous learning prevent cross-project contamination when capturing instincts?▼

Project-scoped learning keeps captured instincts isolated per project by default, preventing cross-project contamination. Global instincts can still be enabled when appropriate to allow controlled cross-project learning and pattern sharing.

Can I use a frontmatter-driven skill manifest to manage evolving instincts?▼

Yes, a frontmatter-driven skill manifest manages evolving instincts by structuring their metadata throughout the end-to-end workflow. This supports the transition from raw session observations into fully developed skills and agents.