qa

Automate tiered QA testing and bug-fix workflows for web applications.

2|Updated May 8, 2026
One-click install
npx skills add https://github.com/xotong/claude-marketplace --skill qa-xotong
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qa
Source: https://github.com/xotong/claude-marketplace/tree/main/plugins/gstack/skills/qa
Command: npx skills add https://github.com/xotong/claude-marketplace --skill qa-xotong

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack) Voice triggers (speech-to-text aliases) are available to trigger QA workflows.

Core Features & Use Cases

  • Tiered QA modes: Quick, Standard, Exhaustive to balance speed and coverage.
  • Plan-mode execution: run tests, collect evidence, and iterate fixes with atomic commits and re-verification.
  • Health scoring and ship-readiness: generate before/after health reports and a readiness summary.
  • Evidence generation: attach results, logs, and evidence of fixes for audits.
  • Voice and integration: supports command aliases and integration into Claude Code workflows.

Quick Start

Run the QA skill to start a tiered test pass, fix issues iteratively, and generate a ship-readiness summary.

Frequently Asked Questions about qa

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

FAQPage Schema
How do I automate QA testing and bug-fixing for my web application?

Automated QA testing runs tiered test passes, iteratively fixes bugs in source code, commits each fix atomically, and re-verifies to ensure stability. It generates before/after health scores, fix evidence, and a ship-readiness summary for your web application.

What is the difference between Quick, Standard, and Exhaustive testing tiers?

Quick testing covers critical and high-priority issues only, Standard adds medium-priority issues, and Exhaustive includes cosmetic issues. These tiered testing modes balance speed and coverage, allowing you to choose the appropriate depth for verifying your web application.

Can I run a report-only QA test without automatically fixing the bugs?

Yes, you can run a report-only QA test without fixing bugs by using the /qa-only mode. This generates health scores and testing evidence without iterating through source code fixes or atomic commits, providing a standalone assessment of your web application.

How do I generate health scores and ship-readiness summaries for my web app?

Health scores and ship-readiness summaries are generated by running tiered QA testing modes on your web application. The process evaluates critical to cosmetic issues, iteratively fixes them with atomic commits, and outputs before/after health reports and readiness summaries.

Do I need environment tooling integration to run automated verification workflows?

Yes, environment tooling integration is required because tests run via gstack and command modes. This integration supports plan-mode safety, executes test passes, and enables the iterative bug-fix workflow with atomic commits and re-verification.