continuous-learning

Name: continuous-learning
Availability: InStock
Author: yulong

Extract reusable patterns from Claude Code sessions into learned skills.

Updated Aug 27, 2026

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

Ready to run

npx skills add https://github.com/yulong-me/Xrunner --skill continuous-learning-yulong-me

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: continuous-learning
Source: https://github.com/yulong-me/Xrunner/tree/main/.agent/skills/continuous-learning
Command: npx skills add https://github.com/yulong-me/Xrunner --skill continuous-learning-yulong-me

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automatically evaluates Claude Code sessions on end to extract reusable patterns and save them as learned skills for future use.

Core Features & Use Cases

Session Evaluation: Checks if session has enough messages (default: 10+)
Pattern Detection: Identifies extractable patterns from the session
Skill Extraction: Saves useful patterns to ~/.claude/skills/learned/
Config and integration: Works with a configurable config.json to tailor thresholds, paths, and patterns to detect

Quick Start

Configure Claude to run the Stop hook after each session to automatically extract patterns and save them 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 configuring a Stop hook. This hook evaluates the session upon ending, detects useful patterns, and saves them directly as learned skills to your local directory.

How many messages does a Claude Code session need before pattern extraction triggers?▼

A Claude Code session needs a minimum of 10 messages by default to trigger pattern extraction. This threshold is configurable via a config.json file, allowing you to tailor when the session evaluation and skill harvesting process activates.

Can I configure the output path for learned skills extracted from Claude Code sessions?▼

Yes, you can configure the output path for learned skills using a config.json file. By default, the extracted patterns are saved to the ~/.claude/skills/learned/ directory, but thresholds, paths, and patterns to detect are all adjustable.

What is the mechanism for continuous learning in Claude Code workflows?▼

Continuous learning in Claude Code workflows is achieved through a session hook mechanism. After a session ends, it checks for minimum messages, identifies extractable patterns, and writes them as learned skills for future use.

Does the pattern extraction process require any external dependencies?▼

No external dependencies are required for the pattern extraction process. The skill operates independently within the Claude Code environment using a Stop hook and a configurable config.json file to manage thresholds and paths.

Why aren't Claude Code session patterns being saved to the learned skills directory?▼

Session patterns may not be saved if the session lacks the minimum required messages, which defaults to 10. Check your config.json settings to ensure thresholds and the target output path are correctly configured for the Stop hook.