agent-qa-engineer

Execute specified scenario methods across declared viewports and report pass/fail with evidence.

12|1|Updated Apr 7, 2026

Search Tags:#automation #accessibility #qa #playwright #browser-testing #runtime-verification #visual-conformance

Ready to run

npx skills add https://github.com/Space-Dinosaurs/DinoStack --skill agent-qa-engineer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-qa-engineer
Source: https://github.com/Space-Dinosaurs/DinoStack/tree/main/.openclaw/skills/agent-qa-engineer
Command: npx skills add https://github.com/Space-Dinosaurs/DinoStack --skill agent-qa-engineer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Dynamic verification agent for runtime testing that ensures changes with visible UI or behavioral output work as intended in real browser environments. It is spawned after Skeptic review and can be invoked when users say commands like "run QA", "verify in the browser", "check the feature works", "test the acceptance criteria", or "does it work".

Core Features & Use Cases

Spawn after skepticism review, before merge, to validate UI/behavior in a real browser.
Supports scenario methods: browser, api, runtime-required, visual_conformance, accessibility (WCAG via axe-core), perceptual_diff (pixel regression via pixelmatch), and motion (prefers-reduced-motion via Playwright CDP).
Iterates across declared viewports and returns a structured pass/fail report with evidence. Does not fix issues. Appends learned project quirks to .agentic/qa.md for future runs.

Quick Start

Spawn the agent to verify runtime changes in a browser and generate a structured QA report.

Frequently Asked Questions about agent-qa-engineer

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

FAQPage Schema

How do I automate browser testing for runtime UI changes across multiple viewports?▼

Automate browser testing by executing scenario methods like browser, api, and visual_conformance across declared viewports using Playwright. The agent verifies runtime UI changes and returns a structured pass/fail report with evidence.

Can I automate accessibility testing with axe-core and Playwright?▼

Yes, accessibility testing is supported via the accessibility scenario method using axe-core through Playwright. It evaluates WCAG compliance during runtime verification and includes results in the structured pass/fail report.

How do I run pixel regression testing to detect visual layout shifts?▼

Pixel regression testing uses the perceptual_diff scenario method powered by pixelmatch to detect visual changes. It compares visual output across declared viewports and reports discrepancies as structured evidence.

Does this tool check prefers-reduced-motion behavior in browser environments?▼

Yes, the motion scenario method verifies prefers-reduced-motion behavior using Playwright CDP. It validates motion-related UI output across browser environments and reports results in the structured pass/fail format.

What do I need to set up before running automated QA verification in the browser?▼

Browser QA verification requires tool support for Playwright and related verification assets. You must declare target viewports and scenario methods, and the agent appends learned project quirks to a local configuration file for future runs.

Why should I use automated runtime verification instead of manual browser checks?▼

Automated runtime verification validates visible UI and behavioral output across multiple viewports and methods like api, visual_conformance, and accessibility. It provides structured pass/fail evidence, reducing human error compared to manual browser checks.