qa

Tests web applications for bugs and iteratively fixes them with atomic commits.

Updated Aug 9, 2026
One-click install
npx skills add https://github.com/raghavbadhwar/rstack --skill qa-raghavbadhwar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qa
Source: https://github.com/raghavbadhwar/rstack/tree/main/qa
Command: npx skills add https://github.com/raghavbadhwar/rstack --skill qa-raghavbadhwar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Manually testing a web application for bugs is slow and inconsistent, and found issues often go unfixed or unverified. This Skill systematically QA tests a web app, classifies every issue by severity and category, then fixes bugs in source code with atomic commits and re-verifies each fix. ## Core Features & Use Cases - Tiered QA Testing: Choose Quick (critical/high only), Standard (+ medium), or Exhaustive (+ cosmetic) coverage depending on how thorough the pass should be. - Find-and-Fix Loop: Detects issues across visual, functional, UX, content, performance, console, and accessibility categories, then fixes them in code, commits each fix atomically, and re-verifies. - Evidence-Producing Reports: Generates before/after health scores, annotated screenshots, regression tests, and a ship-readiness summary using a structured report template. - Use Case: Before shipping a feature branch, ask the agent to QA the running site; it crawls pages, clicks every interactive element, checks the console for errors, fixes what it finds, and reports the health score improvement. ## Quick Start Ask the agent to QA test the running web application and fix any bugs it finds, then review the generated report and health score.

Frequently Asked Questions about qa

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

FAQPage Schema
How do I automatically test a web app for bugs?

Invoke the qa skill against the running site. It visits pages, clicks interactive elements, submits forms, checks console errors, and classifies every issue by severity and category before fixing them in code.

What types of bugs does automated web QA testing find?

It covers seven categories: visual/layout breaks, functional failures like dead buttons and broken forms, UX problems, content errors, performance issues, console and network errors, and accessibility violations like missing alt text.

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

Quick covers only critical and high severity issues, Standard adds medium severity, and Exhaustive adds low-severity cosmetic issues. Choose the tier based on how thorough the testing pass needs to be.

Can I get a QA report without fixing the bugs found?

Yes, use the /qa-only variant for report-only mode. It produces the same health scores, issue taxonomy, and screenshots without modifying source code or committing fixes.

How are bug fixes verified after automated QA?

Each fix is committed atomically and then re-verified against the original reproduction steps. The report records fix status as verified, best-effort, reverted, or deferred, with before/after screenshot evidence.