qa

Automates end-to-end QA testing of web applications simulating user interactions across multiple modes.

Updated Feb 8, 2026
One-click install
npx skills add https://github.com/ckallum/calsuite --skill qa-ckallum
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qa
Source: https://github.com/ckallum/calsuite/tree/main/skills/qa
Command: npx skills add https://github.com/ckallum/calsuite --skill qa-ckallum

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

QA teams and developers spend hours manually testing web apps; this skill provides a repeatable, user-like QA workflow to catch issues early and document evidence automatically.

Core Features & Use Cases

  • Systematic browser-based testing using real user interactions to uncover issues that automated checks miss
  • Supports multiple modes (diff-aware, full, quick, regression) to balance depth and speed
  • Generates structured QA reports with health scores, screenshots, and reproducible steps for each issue
  • Per-page exploration with automated snapshot, validation, and issue documentation to guide fixes

Quick Start

Open the target URL with agent-browser and start a diff-aware QA run.

Frequently Asked Questions about qa

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

FAQPage Schema
How do I automate end-to-end QA testing for web applications?

Automate end-to-end QA testing by simulating real user interactions in a browser to uncover issues automated checks miss, capturing screenshots and reproducible steps for each documented issue.

What is diff-aware testing and when should I use it for web app smoke tests?

Diff-aware testing targets recent code changes to systematically validate updates without running a full suite, making it ideal for quick smoke tests focused on affected page areas.

How do I generate structured QA reports with reproducible steps and screenshots?

Generate structured QA reports by running user-like browser interactions that automatically snapshot pages, assign health scores, and document validation issues with steps to reproduce.

Can I run regression testing modes against a baseline web application snapshot?

Run regression testing modes to compare current browser interactions against a baseline snapshot, identifying visual and functional deviations while documenting reproducible steps.

Does agent-browser support automated web testing without writing complex scripts?

Agent-browser supports automated web testing by directly simulating real user interactions, allowing you to start diff-aware or full exploration runs without manual scripting.