learn

Extract user preferences and lessons from conversations into CLAUDE.md and SKILL.md files.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/icyrainz/.dotfiles --skill learn-icyrainz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/icyrainz/.dotfiles/tree/main/claude/skills/learn
Command: npx skills add https://github.com/icyrainz/.dotfiles --skill learn-icyrainz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes the current conversation to extract user preferences, patterns, and actionable lessons, enabling improvements to CLAUDE.md and custom SKILL.md files and persisting insights for future sessions.

Core Features & Use Cases

  • Extract user preferences and session lessons from chat history to inform future interactions.
  • Update CLAUDE.md and the user's custom SKILL.md with learned conventions and improvements.
  • Persist insights in a memory layer for seamless application across sessions while respecting privacy.

Quick Start

Ask me to /learn or say remember my preferences and I will extract insights from this session and update CLAUDE.md and your SKILL.md accordingly.

Frequently Asked Questions about learn

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

FAQPage Schema
How do I save user preferences from a conversation to improve future interactions?

To save user preferences from a conversation, you can prompt the system to analyze chat history and extract actionable lessons, which updates your configuration files to improve future interactions automatically.

What is the best way to extract conversation patterns and apply them to future sessions?

The best way to extract conversation patterns is by running a conversation analysis that identifies user preferences, updates your CLAUDE.md configuration, and persists these insights in a privacy-conscious memory layer for future sessions.

Can I update CLAUDE.md automatically based on chat history analysis?

Yes, you can update CLAUDE.md automatically by analyzing your current chat history to extract learned conventions, actionable lessons, and user preferences, then writing those insights directly into the file.

Does the memory layer store sensitive data when extracting preferences from chat?

No, the memory layer applies insights in a privacy-conscious manner, explicitly avoiding sensitive data exposure while persisting only extracted user preferences and learned conventions from the conversation.

When should I not use automated conversation analysis for personalization?

You should avoid automated conversation analysis for personalization when your chat contains sensitive data, as the extraction process is designed to avoid sensitive data exposure and only applies changes when explicitly prompted.