qa

Convert bug conversations into GitHub issues with reproduction steps.

1|Updated May 5, 2026

Search Tags:#qa #github issues #codebase exploration #bug reporting #reproduction steps #domain language #issue scoping

Ready to run

npx skills add https://github.com/yashs33244/my-mac-claude --skill qa-yashs33244

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qa
Source: https://github.com/yashs33244/my-mac-claude/tree/main/skills/mattpocock/deprecated/qa
Command: npx skills add https://github.com/yashs33244/my-mac-claude --skill qa-yashs33244

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns conversational bug reports into clear, reproducible, user-focused GitHub issues, while quickly learning the relevant domain language from your codebase.

Core Features & Use Cases

Light clarification: Asks up to 2-3 focused questions to capture the expected vs actual behavior and key reproduction details.
Background codebase exploration: Runs an “Explore” subagent to learn the feature’s intent and the ubiquitous domain language, without trying to implement a fix during QA.
Durable issue creation: Creates one or multiple GitHub issues with mandatory reproduction steps, written from the user’s perspective and using domain terminology.

Quick Start

Tell the agent about a bug you’re seeing and include what you expected, what actually happened, and how you tried to reproduce it.

Frequently Asked Questions about qa

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

FAQPage Schema

How do I convert bug reports into GitHub issues with reproduction steps?▼

You can convert conversational bug reports into durable GitHub issues by providing the expected behavior, actual behavior, and reproduction details. The agent asks up to three clarifying questions, explores the codebase for domain language, and creates issues with mandatory reproduction steps written from the user's perspective.

How does codebase exploration help scope multi-symptom QA reports?▼

Codebase exploration helps scope multi-symptom QA reports by running a background subagent to learn the feature's intent and ubiquitous domain language. This ensures the resulting GitHub issues use accurate terminology without requiring the reporter to manually map symptoms to code paths.

Can I create multiple independently fixable GitHub issues from a single bug report?▼

Yes, you can create multiple independently fixable GitHub issues from a single bug report. When a multi-symptom QA report requires scoping, the agent separates the defects into distinct issues, each with clear expectations and mandatory reproduction steps created via the gh issue create command.

Does the generated GitHub issue include file paths or code references?▼

No, the generated GitHub issues strictly avoid code and file-path references. The agent writes issues from the user's perspective using domain terminology learned during background codebase exploration, ensuring the report remains durable and focused on expected versus actual behavior.

What do I need to provide to file a durable GitHub issue from a bug report?▼

You need to provide a description of the bug, what you expected to happen, what actually happened, and how you tried to reproduce it. The agent handles the rest, asking light clarification questions and creating the issue using the gh issue create command.

Why use an agent to scope bug reports instead of writing GitHub issues manually?▼

Using an agent to scope bug reports ensures issues include mandatory reproduction steps and domain terminology extracted from codebase exploration. This approach prevents inconsistent behaviors from being poorly documented and returns formatted GitHub issue URLs directly to the user.