qa

Systematically test web applications and produce structured QA reports with screenshots and health scores.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/fullya99/simple-blog-page --skill qa-fullya99
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qa
Source: https://github.com/fullya99/simple-blog-page/tree/main/.claude/skills/gstack/qa
Command: npx skills add https://github.com/fullya99/simple-blog-page --skill qa-fullya99

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Manual QA testing of web applications is slow, inconsistent, and often undocumented. This Skill automates systematic exploration of a web app like a real user, capturing reproducible evidence for every bug found. ## Core Features & Use Cases - Three Testing Modes: Full systematic exploration, a 30-second quick smoke test, and regression comparison against a saved baseline. - Evidence-Based Issue Reports: Every issue includes annotated screenshots, repro steps, severity, and category, written incrementally to a structured Markdown report. - Health Score & Baselines: Computes a weighted 0-100 health score across console, links, visual, functional, UX, performance, content, and accessibility categories, saving a baseline.json for regression diffs. - Use Case: Point it at your staging URL before a release to get a full QA report with the top 3 things to fix, console error summary, and screenshot evidence for each bug. ## Quick Start QA test my web app at http://localhost:3000 in full mode and generate a report with screenshots.

Frequently Asked Questions about qa

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

FAQPage Schema
How do I QA test a web application automatically?▼

Provide the target URL and choose a mode: full for systematic exploration, --quick for a 30-second smoke test, or --regression with a baseline file. The skill visits pages, interacts with elements, checks the console, and writes a structured report with screenshot evidence.

What does the QA report include?▼

The report contains a weighted health score out of 100, the top 3 issues to fix, a console error summary, severity counts, and detailed issues with repro steps and annotated screenshots. A baseline.json is saved for future regression comparisons.

Can it test sites that require login or authentication?▼

Yes. It supports credential-based login by filling the login form, importing cookies from a JSON file, and handling 2FA by asking the user for the code. Passwords are always redacted as [REDACTED] in the report.

Does it work with Next.js, Rails, or single-page applications?▼

Yes. It detects the framework automatically and applies specific guidance, such as checking hydration errors in Next.js, CSRF tokens in Rails, and using interactive snapshots for client-side navigation in SPAs.

How is the health score calculated?▼

Each category (console, links, visual, functional, UX, performance, content, accessibility) is scored 0-100 with deductions per issue severity, then combined using fixed weights. Functional issues carry the highest weight at 20 percent.

What are the limitations of automated QA testing?▼

It cannot bypass CAPTCHAs without user help and does not read source code, testing only as an end user. Deep coverage depends on reachable pages, so hidden or role-restricted flows may need explicit credentials or scope instructions.