skills.rest
JochenYang
JochenYangCOMMUNITY
Explore all skills by this author →
GitHub

continuous-learning-v2

Capture Claude Code session observations into confidence-scored instincts for evolution.

21|3|Updated Jan 22, 2026
Search Tags:#automation#hooks#learning#confidence#claude-code#pattern-detection#instincts
One-click install
npx skills add https://github.com/JochenYang/Jochen-ai-rules --skill continuous-learning-v2-jochenyang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: continuous-learning-v2
Source: https://github.com/JochenYang/Jochen-ai-rules/tree/main/.claude/skills/continuous-learning-v2
Command: npx skills add https://github.com/JochenYang/Jochen-ai-rules --skill continuous-learning-v2-jochenyang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill turns Claude Code sessions into reusable knowledge by observing prompts and tool use, creating atomic instincts with confidence scoring, and evolving them into skills, commands, and agents.

Core Features & Use Cases

  • Observation hooks capture session activity to build a living knowledge base of repeatable patterns.
  • Instincts are atomic, confidence-scored behaviors that can be evolved into commands, skills, or agents.
  • Export/import instincts enable collaboration and reuse across projects.

Quick Start

  1. Enable observation hooks in your Claude Code settings to start capturing session data.
  2. Run the continuous-learning-v2 observer to begin building instincts automatically.
  3. Use the instinct CLI to status, export, import, or evolve instincts as they accumulate.

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 session patterns for continuous learning?▼

You can track session patterns by enabling observation hooks in Claude Code settings, capturing prompts and tool usage to formalize repeatable patterns into confidence-scored atomic instincts for continuous learning.

What are atomic instincts with confidence scoring in Claude Code workflows?▼

Atomic instincts are confidence-scored behaviors derived from session observations, designed to identify repeatable patterns across Claude Code workflows and evolve them into actionable skills, commands, or agents.

How do I export and import learning instincts across different projects?▼

You export and import instincts using the instinct CLI, enabling collaboration and reuse of confidence-scored behaviors across different projects by transferring the self-managed instinct store data.

Do I need external dependencies to run the continuous learning observer?▼

No external dependencies are required; the observer relies on a lightweight, self-managed observatory and instinct store using built-in Python tooling and the standard library only.

How do I evolve session observations into reusable Claude Code commands?▼

You evolve session observations into reusable commands by running the observer to build atomic instincts, then using the instinct CLI to evolve accumulated confidence-scored patterns into actionable Claude Code commands.

Related Skills

Explore More Software Engineering Skills→
krishnakanthb13krishnakanthb13
89

continuous-learning-v2

Transforms session observations into confidence-weighted instincts and evolves them into skills, commands, and agents.

Community
Advanced
linnefromicelinnefromice

continuous-learning-v2

Convert Claude Code sessions into confidence-weighted instincts and evolvable skills.

Community
Advanced
andrew-starosciakandrew-starosciak
2

continuous-learning-v2

Observe Claude sessions to create confidence-scored instincts and evolve them into skills.

Community
Advanced
parcadeiparcadei
3.9k

braintrust-analyze

Analyze Braintrust tracing data from Claude Code sessions for patterns and insights.

Community
Advanced