continuous-learning

Extract reusable patterns from Claude Code sessions via stop-hook evaluation.

Updated Mar 1, 2026
One-click install
npx skills add https://github.com/derekhu0002/ai4pb-orchestrator --skill continuous-learning-derekhu0002
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: continuous-learning
Source: https://github.com/derekhu0002/ai4pb-orchestrator/tree/main/skills/continuous-learning
Command: npx skills add https://github.com/derekhu0002/ai4pb-orchestrator --skill continuous-learning-derekhu0002

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automatically extract reusable patterns from Claude Code sessions at the end of each session.

Core Features & Use Cases

  • Stop-hook based evaluation triggers pattern detection and persistence of learned skills to the local path ~/.claude/skills/learned/.
  • Configurable thresholds and pattern categories via a lightweight config.json to tailor extraction.
  • Use Case: Imagine a developer reviews Claude Code transcripts and builds a personal library of repeatable solutions.

Quick Start

Enable the Stop hook in Claude Code and ensure learned skills 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 patterns from Claude Code sessions?

You can automatically extract patterns from Claude Code sessions by enabling a stop-hook evaluation that triggers pattern detection at the end of each session, saving the learned skills locally for future reuse.

Where are extracted skills saved when using stop-hooks in Claude Code?

Extracted skills are saved as persistent files to the local path ~/.claude/skills/learned/ when the stop-hook evaluation triggers at the end of a Claude Code session.

Can I configure extraction thresholds for Claude Code session patterns?

Yes, you can configure extraction thresholds and pattern categories by modifying a lightweight config.json file to tailor pattern detection to your specific workflow requirements.

What is the minimum session length needed to save learned skills locally?

You can customize the minimum session length required to trigger pattern extraction by adjusting the min_session_length parameter within the config.json file.

Does this pattern detection tool work without external dependencies?

Yes, the continuous-learning pattern detection tool operates without external dependencies, relying entirely on local storage and native stop-hook evaluations to process and save skills.