continuous-learning

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

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/Femad-6/my-skills --skill continuous-learning-femad-6
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: continuous-learning
Source: https://github.com/Femad-6/my-skills/tree/main/.github/skills/continuous-learning
Command: npx skills add https://github.com/Femad-6/my-skills --skill continuous-learning-femad-6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Valuable problem-solving patterns discovered during Claude Code sessions are lost when the session ends, forcing users to rediscover the same fixes and workarounds repeatedly. ## Core Features & Use Cases - Automatic Session Evaluation: Runs as a Stop hook at the end of each session to detect extractable patterns once a minimum message threshold is met. - Configurable Pattern Detection: Detects error resolutions, user corrections, workarounds, debugging techniques, and project-specific conventions while ignoring typos and one-time fixes via config.json. - Learned Skill Storage: Saves extracted patterns as reusable skills in ~/.claude/skills/learned/ for future sessions. - Use Case: After a long debugging session where you resolved a tricky framework quirk, the Stop hook flags the session so the resolution pattern is captured and reused automatically next time. ## Quick Start Add the evaluate-session.sh script as a Stop hook in ~/.claude/settings.json and let it evaluate each session for extractable patterns.

Frequently Asked Questions about continuous-learning

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

FAQPage Schema
How do I automatically save patterns from Claude Code sessions?

Register evaluate-session.sh as a Stop hook in ~/.claude/settings.json. At the end of each session, the script checks the transcript message count and signals that the session should be evaluated for extractable patterns saved to ~/.claude/skills/learned/.

What patterns does continuous learning extract from sessions?

It detects error resolutions, user corrections, workarounds, debugging techniques, and project-specific conventions. It ignores simple typos, one-time fixes, and external API issues, all configurable in config.json.

Why use a Stop hook instead of UserPromptSubmit for session evaluation?

The Stop hook runs once at session end, making it lightweight and non-blocking, while UserPromptSubmit runs on every message and adds latency. The Stop hook also has access to the complete session transcript for better analysis.

Why is the session evaluation script not running?

Sessions shorter than the configured minimum (default 10 user messages) are skipped silently. Also verify the hook is registered in ~/.claude/settings.json and that the transcript path is passed correctly via hook stdin.

Does the session evaluator require jq to be installed?

jq is optional. Without it, the script falls back to default values for minimum session length and the learned skills path, printing a warning to stderr.