learner

Extract codebase-specific debugging insights into reusable skills with YAML frontmatter.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/dropsyoon/oh-my-claudecode --skill learner-dropsyoon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learner
Source: https://github.com/dropsyoon/oh-my-claudecode/tree/main/skills/learner
Command: npx skills add https://github.com/dropsyoon/oh-my-claudecode --skill learner-dropsyoon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you capture a tricky, codebase-specific lesson from a conversation—so future Claude sessions can apply the same learned principle and workflow instead of repeating the same investigation.

Core Features & Use Cases

  • Skill extraction with guardrails: Only records insights that are non-googleable, specific to the project, and precise enough to be actionable.
  • Separate learnings into Expertise vs Workflow: Stores domain principles (updatable) apart from stable procedures (kept steady).
  • Built-in validation: Rejects vague, boilerplate, or overly generic “best practices” to prevent low-quality skills from being saved.
  • Project-level learned skill saving: Creates a version-controlled learned skill in the repository under .omc/skills for consistent reuse.

Quick Start

Ask the AI to extract a new learned skill from your latest debugging session, and include the exact error message, relevant file paths with line numbers, the final fix, and the trigger phrases you expect to see next time.

Frequently Asked Questions about learner

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

FAQPage Schema
How do I save debugging insights from a Claude Code session into reusable heuristics?

This skill extracts non-obvious, codebase-specific debugging insights from your current conversation into a reusable, structured format. It captures the validated Problem, Solution, and Triggers, ensuring future Claude sessions can apply the same learned principle without repeating the investigation.

How do I document a project-specific gotcha so future AI coding sessions remember it?

The skill separates learnings into Expertise for updatable domain principles and Workflow for stable procedures. It also applies built-in validation to reject vague, boilerplate, or overly generic best practices, preventing low-quality or non-actionable skills from being saved to your project.

What is the best way to turn a complex bug fix into a structured, version-controlled skill?

The best way to turn a complex bug fix into a structured skill is to capture the exact error, relevant file paths, and the final fix during your conversation. The system produces a learned skill with YAML frontmatter containing the name and description required for discovery, saving it under .omc/skills.

Why are generic coding best practices rejected when extracting a learned skill?

Generic coding best practices are rejected because the extraction process includes built-in guardrails that only record non-googleable, project-specific insights. This validation ensures your saved heuristics remain precise enough to be actionable rather than cluttered with boilerplate advice.