skills.rest
DanielKerridge
DanielKerridgeCOMMUNITY
Explore all skills by this author →
GitHub

visual-qa

Walk through web apps, record captioned actions, and send evidence to Gemini for visual QA review.

56|16|Updated Feb 12, 2026
Search Tags:#automation#qa#captions#gemini#visual-testing#web-app
One-click install
npx skills add https://github.com/DanielKerridge/claude-code-power-platform-skills --skill visual-qa-danielkerridge
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visual-qa
Source: https://github.com/DanielKerridge/claude-code-power-platform-skills/tree/main/visual-qa
Command: npx skills add https://github.com/DanielKerridge/claude-code-power-platform-skills --skill visual-qa-danielkerridge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI-powered visual QA testing that walks through an app in the browser, records every action with annotated captions (what was done, what should happen), captures screenshots/GIFs, and sends the evidence to Gemini for automated review. Catches UX misalignments, broken flows, missing states, and edge cases that traditional tests miss. Can use Agent Teams for parallel test coverage.

Core Features & Use Cases

  • Plan test runs with distributed agent teams to cover happy paths and edge cases
  • Walk the app to record actions, generate captions, and collect visual evidence (screenshots/GIFs)
  • Submit evidence to Gemini for automated review and generate a findings report
  • Optional Gemini review and team coordination to speed QA cycles

Quick Start

Record a visual QA test by navigating your web app in a browser with Claude in Chrome, log each action with a caption, and submit the evidence to Gemini for review.

Frequently Asked Questions about visual-qa

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

FAQPage Schema
How do I automate visual QA testing for a web app?▼

Automate visual QA testing by walking through your web app in a browser with Claude in Chrome, logging each action with structured captions, and submitting visual evidence like screenshots to Gemini for automated review.

What is AI-assisted visual testing and how does it catch UX issues?▼

AI-assisted visual testing records browser actions with annotated captions and screenshots, then sends the evidence to Gemini for review to catch UX misalignments, broken flows, missing states, and edge cases that traditional tests miss.

Do I need a Gemini API key to run AI visual testing?▼

Yes, you need Gemini API access to submit visual evidence for automated review, Claude in Chrome for browser interaction, and a caption script to guide test planning, execution, and evidence export.

Can I use agent teams for parallel UI test coverage?▼

Yes, you can use distributed agent teams to plan test runs and execute parallel visual QA, covering both happy paths and edge cases across your web app to speed up QA cycles.

What's the best way to validate layout and UX consistency across web apps?▼

Validate layout and UX consistency by navigating your web app to record actions and capture visual evidence, then submit the annotated screenshots and GIFs to Gemini for automated review and a findings report.

Related Skills

Explore More Software Engineering Skills→
ingpocingpoc
9

testing

Orchestrates unit, API, browser, and database tests with structured JSON evidence output.

Community
Advanced
AndreKuraitAndreKurait

remediating-with-aws-security-agent

Automates AWS Security Agent findings triage and remediation planning into gitignored exports.

Community
Advanced
arthrodarthrod

dogfood

Explore web applications and generate bug reports with screenshots and videos.

Community
Advanced
darshan-rambhiadarshan-rambhia

testing

Standardize unit and end-to-end tests using Vitest and Playwright.

Community
Advanced