continuous-learning

Extract reusable patterns from Claude Code sessions and save them as learned skills.

16|3|Updated Mar 12, 2026

Search Tags:#automation #claude-code #session-analysis #pattern-extraction #learned-skills #continuous-learning #stop-hook

Ready to run

npx skills add https://github.com/sehoon787/my-claude --skill continuous-learning-sehoon787

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: continuous-learning
Source: https://github.com/sehoon787/my-claude/tree/main/skills/ecc/continuous-learning
Command: npx skills add https://github.com/sehoon787/my-claude --skill continuous-learning-sehoon787

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Claude Code sessions generate valuable insights, but patterns are scattered across transcripts and runbooks. This skill automatically extracts reusable patterns and saves them as learned skills for future reuse.

Core Features & Use Cases

Automatic session pattern detection at the end of Claude Code sessions.
Persistence of extracted patterns to ~/.claude/skills/learned/ for quick reuse.
Supports review and curation of learned skills to improve tooling.

Quick Start

Enable the Stop hook so Claude Code sessions are evaluated and reusable patterns are saved to ~/.claude/skills/learned/.

Frequently Asked Questions about continuous-learning

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

FAQPage Schema

How do I automatically extract reusable patterns from Claude Code sessions?▼

You can automatically extract reusable patterns from Claude Code sessions by enabling a Stop-hook evaluation that analyzes session transcripts and saves identified patterns directly to your learned skills directory.

What is a Stop-hook in Claude Code for continuous learning?▼

A Stop-hook in Claude Code is an evaluation trigger that runs at the end of a session to detect reusable patterns in transcripts, enabling continuous learning by persisting them as learned skills for future use.

Can I configure minimum session length for pattern extraction in Claude Code?▼

Yes, pattern extraction supports a configurable minimum session length, ensuring that only Claude Code sessions meeting your specified duration threshold are evaluated for reusable patterns.

Where are extracted Claude Code patterns saved for future reuse?▼

Extracted Claude Code patterns are saved as learned skills in the ~/.claude/skills/learned/ directory, allowing you to review, curate, and reuse them to improve future tooling.

Do I need access to session transcripts to extract learned skills from Claude Code?▼

Yes, you need access to session transcripts and the ~/.claude/skills/learned/ directory, as the pattern extraction mechanism evaluates these transcripts to identify and persist reusable skills.

What are the limitations of automatic session pattern detection in Claude Code?▼

Automatic session pattern detection relies on session transcripts and a minimum session length threshold, meaning shorter sessions may be skipped and manual curation is recommended to ensure extracted patterns are truly reusable.