learn

Discover memory files and route conversation learnings to documentation.

5|11|Updated Jan 18, 2026
One-click install
npx skills add https://github.com/Awakehsh/awesome-agent-tools --skill learn-awakehsh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/Awakehsh/awesome-agent-tools/tree/main/skills/learn
Command: npx skills add https://github.com/Awakehsh/awesome-agent-tools --skill learn-awakehsh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

The Learn skill automatically identifies valuable insights from technical conversations and routes them into the correct documentation files across Claude Code, Codex, Cursor, Gemini, and generic rule sets, reducing manual knowledge curation.

Core Features & Use Cases

  • Automatic memory file discovery scans project and home directories for CLAUDE.md, AGENTS.md, and domain rules.
  • Intelligent routing analyzes learning context and places updates in the appropriate primary or specialized docs.
  • LLM-friendly drafting generates compact, verifiable updates ready for review.
  • Cross-platform sync propagates changes to all relevant platforms and updates navigation.

Quick Start

  • Invoke /learn to start a learning session in the current workspace.
  • When a learning is triggered, respond with clarifications or approvals to modify memory files.
  • Use /learn --review to audit active learnings and suggested archival.

Frequently Asked Questions about learn

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

FAQPage Schema
How do I extract actionable learnings from LLM conversations into memory files?

To extract actionable learnings from LLM conversations, the Learn skill analyzes dialogue flow to determine relevance and routes compact updates to appropriate memory files like CLAUDE.md or AGENTS.md. It requires explicit user approval before applying changes.

Can I sync project knowledge across Claude Code, Codex, Cursor, and Gemini?

You can sync project knowledge across Claude Code, Codex, Cursor, and Gemini. The skill features cross-platform sync that propagates documentation changes to all relevant platforms and updates navigation automatically.

How does automatic memory file discovery work for AI coding assistants?

Automatic memory file discovery works by scanning your current project and home directories for CLAUDE.md, AGENTS.md, and domain rules. It identifies valuable insights from technical conversations and extracts them without manual curation.

Do I need to manually approve updates to CLAUDE.md files?

You need to manually approve updates to CLAUDE.md files. The skill generates LLM-friendly drafts of compact, verifiable updates and requires explicit user approval before applying any changes to your memory files.

What is the best way to organize AI assistant rules by scope and platform?

The best way to organize AI assistant rules is through intelligent routing that analyzes learning context and classifies updates by scope and platform. This places updates in appropriate primary or specialized docs automatically.

How do I review and audit active learnings before they are archived?

To review and audit active learnings, use the `/learn --review` command. This allows you to audit active learnings and suggested archival, ensuring your memory files remain accurate and relevant.