learner

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

Updated May 18, 2026
One-click install
npx skills add https://github.com/solitude6060/Yao-skills --skill learner-solitude6060
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learner
Source: https://github.com/solitude6060/Yao-skills/tree/main/skills/learner
Command: npx skills add https://github.com/solitude6060/Yao-skills --skill learner-solitude6060

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you capture a learned solution from a debugging session into a reusable, high-quality skill that others can apply later without relearning the same investigation.

Core Features & Use Cases

  • Skill extraction with quality gates: Ensures the captured insight is non-Googleable, codebase-specific, and hard-won before it’s saved.
  • Structured expertise vs workflow classification: Separates durable principles from stable step-by-step procedures so future improvements don’t destabilize operations.
  • Validated, trigger-driven skill files: Requires YAML frontmatter and rejection rules for vague or overly generic outputs to improve discovery and matching.

Quick Start

Use the learner skill after you solve a tricky, codebase-specific bug by providing the exact error, the files/lines involved, and the precise fix so it can extract a reusable principle or workflow.

Frequently Asked Questions about learner

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

FAQPage Schema
How do I capture debugging insights into reusable knowledge for my team?

Capturing debugging insights involves extracting the exact error, affected file paths, and precise fix from a conversation into a structured skill file. This ensures future teams can recall the same hard-won principle without relearning the investigation.

What inputs are needed to extract a debugging session into a workflow skill?

Extracting a debugging session requires evidence-rich inputs: the specific error, file paths and line numbers, triggers, and the exact fix. Providing these details ensures the output captures a durable, codebase-specific principle rather than a generic solution.

How do I structure extracted troubleshooting outcomes for trigger-based retrieval?

Troubleshooting outcomes are structured using YAML frontmatter formatting to enable trigger-based retrieval. This format enforces classification into expertise versus workflow and applies rejection rules to prevent vague, un-Googleable outputs from cluttering the knowledge base.

When should I classify an incident triage outcome as expertise versus workflow?

Classify an incident triage outcome as expertise when it represents a durable principle, and as workflow when it outlines stable step-by-step procedures. This separation ensures future improvements to procedures do not destabilize core operational principles.

Does the skill extraction process reject generic or easily Googleable fixes?

Yes, the skill extraction process applies quality gates that reject generic or easily Googleable fixes. It specifically requires the insight to be non-Googleable, codebase-specific, and hard-won before saving it as a validated, trigger-driven skill file.

Why use YAML frontmatter for incident triage knowledge capture?

YAML frontmatter is used for incident triage knowledge capture to improve discovery and matching. It enforces validated, trigger-driven metadata that categorizes the fix, ensuring fast recall of specific principles or procedures during future incidents.