learner

Extract repository-specific debugging expertise into a reusable learned skill.

Updated May 20, 2026
One-click install
npx skills add https://github.com/xdkp/oh-my-claudecode --skill learner-xdkp
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learner
Source: https://github.com/xdkp/oh-my-claudecode/tree/main/skills/learner
Command: npx skills add https://github.com/xdkp/oh-my-claudecode --skill learner-xdkp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps convert a tricky, codebase-specific breakthrough from a conversation into a reusable learned skill so future work starts with the right mental model instead of repeating the same debugging effort.

Core Features & Use Cases

  • Extracts a learned skill from conversation context after a genuine, hard-won discovery tied to this repository (including concrete file paths and symptoms).
  • Separates improvement knowledge from stable procedure by defining an Expertise section for evolving patterns while keeping Workflow stable.
  • Enforces a quality gate to avoid generic or easily googled advice, reducing noise and improving future usefulness.

Quick Start

Ask it to extract a new learned skill from your latest debugging conversation, making sure to include the exact symptom, file locations, and the precise fix you applied.

Frequently Asked Questions about learner

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

FAQPage Schema
How do I extract a reusable skill from a debugging conversation?

To extract a reusable skill from a debugging conversation, provide the exact symptoms, file locations, and applied fixes. The skill synthesizes this repository-specific expertise into a structured format with a YAML-frontmatter entry separating stable workflows from updateable expertise.

What is the best way to capture non-obvious workarounds discovered during troubleshooting?

Capturing non-obvious workarounds requires grounding the knowledge in context specificity and non-googleability. This approach enforces a quality gate to filter out generic advice, ensuring only genuine codebase-specific breakthroughs are saved as learned skills.

Can I separate stable workflow procedures from evolving expertise patterns?

Yes, you can separate stable workflow procedures from evolving expertise patterns. The extraction process defines a distinct Expertise section for updateable patterns while keeping the core Workflow stable, preventing procedural noise from mixing with improvement knowledge.

Does skill extraction require specific context to generate useful repository heuristics?

Skill extraction requires concrete context to generate useful repository heuristics. You must include exact file paths, observed symptoms, and the precise fix applied during your real troubleshooting session to pass the quality gate and synthesize valid expertise.

When should I not use knowledge capture for self-improving skills?

You should not use knowledge capture for self-improving skills when the fix is easily googled or represents a generic programming concept. The enforced quality gate rejects generic advice, limiting extraction to recurring gotchas and non-obvious workarounds tied to your specific codebase.