continuous-learning

Extract reusable patterns from Claude Code sessions into learned skills.

Updated Jul 28, 2024
One-click install
npx skills add https://github.com/fredericvahrenhorst/share-app --skill continuous-learning-fredericvahrenhorst
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: continuous-learning
Source: https://github.com/fredericvahrenhorst/share-app/tree/main/.cursor/skills/continuous-learning
Command: npx skills add https://github.com/fredericvahrenhorst/share-app --skill continuous-learning-fredericvahrenhorst

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automatically identifies and saves reusable patterns from Claude Code sessions to accelerate future work.

Core Features & Use Cases

  • Stop-hook evaluation at session end to ensure complete context without impacting live workflows.
  • Pattern detection that surfaces actionable insights like common mistakes, debugging approaches, and project conventions.
  • Saves extracted learned-skills to ~/.claude/skills/learned/ for quick reuse.

Quick Start

Run the evaluate-session.sh script at the end of a Claude Code session to extract reusable patterns and save them as learned skills.

Frequently Asked Questions about continuous-learning

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

FAQPage Schema
How do I extract reusable patterns from Claude Code sessions?

You can extract reusable patterns from Claude Code sessions by running the evaluate-session.sh script at the end of a session, which identifies actionable insights like debugging approaches and saves them as learned skills.

What is continuous learning in Claude Code workflow optimization?

Continuous learning in Claude Code is an automated pattern extraction process that captures common mistakes and project conventions from your sessions, saving them to the ~/.claude/skills/learned/ directory for reuse in future projects.

Can I configure pattern detection thresholds and output paths in Claude Code?

Yes, you can configure pattern extraction settings by editing the config.json file, allowing you to adjust detection thresholds, storage paths, and pattern types to match your specific workflow optimization needs.

Does extracting learned skills impact live Claude Code workflows?

No, pattern extraction uses a stop-hook evaluation at session end to ensure complete context is captured without impacting your live workflows or causing interruptions during active development.

What is the best way to save debugging approaches from Claude Code sessions?

The best way to save debugging approaches is to use automated session evaluation, which surfaces these patterns and stores them locally in the ~/.claude/skills/learned/ directory for immediate future reference.