learn

Extract reusable corrections and patterns from sessions into MEMORY.md or skill files.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/naj2r/claude-econ-paper-template --skill learn-naj2r
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/naj2r/claude-econ-paper-template/tree/main/.claude/skills/learn
Command: npx skills add https://github.com/naj2r/claude-econ-paper-template --skill learn-naj2r

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill extracts reusable knowledge from an interactive session and persists corrections, patterns, and user preferences so valuable insights are not lost between sessions.

Core Features & Use Cases

  • Correction capture: Detects explicit corrections (for example [LEARN:category] tags) and records concise wrong → right notes in project memory.
  • Pattern and preference extraction: Identifies recurring coding patterns, data quirks, and communication preferences to store in MEMORY.md or targeted convention files.
  • Skill discovery and creation: Flags repeatable workflows and suggests creating new skills or updating existing rule files to automate future work.

Quick Start

Ask the learn skill to extract and save persistent learnings from the current session about the project's data quirks.

Frequently Asked Questions about learn

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

FAQPage Schema
How do I save conversation learnings to persistent memory for future sessions?

Saving conversation learnings to persistent memory involves extracting reusable corrections, coding patterns, and user preferences from a session transcript, then writing them into MEMORY.md or project rule files for future automation.

Can I automatically extract coding patterns and data quirks from a session transcript?

Automatically extracting coding patterns and data quirks from a session transcript requires analyzing the conversation for recurring behaviors and explicit corrections, then persisting these insights into targeted convention files.

What is the best way to capture user preferences and corrections from an interactive session?

Capturing user preferences and corrections from an interactive session involves detecting explicit tags during session analysis, recording concise wrong-to-right notes in project memory to prevent recurring mistakes.

Do I need file read and write permissions to extract knowledge into project rule files?

Extracting knowledge into project rule files requires file read, write, and edit permissions, along with access to tools like Grep and Glob, to analyze the session transcript and successfully persist learnings.

How does knowledge extraction handle speculative or transient session state?

Knowledge extraction handles speculative or transient session state by applying built-in safeguards that filter out temporary variables and unverified assumptions, ensuring only reusable corrections and patterns are persisted.