skills.rest
chrisxue90
chrisxue90COMMUNITY
Explore all skills by this author →
GitHub

visual-verdict

Compare UI screenshots against reference images and return a strict JSON verdict.

2|2|Updated Apr 3, 2026
Search Tags:#ui#qa#screenshot#reference-images#json-output#image-diff#visual-verdict
One-click install
npx skills add https://github.com/chrisxue90/oh-my-qwencode --skill visual-verdict-chrisxue90
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/chrisxue90/oh-my-qwencode/tree/main/skills/visual-verdict
Command: npx skills add https://github.com/chrisxue90/oh-my-qwencode --skill visual-verdict-chrisxue90

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill evaluates UI visual fidelity by comparing a generated screenshot against reference images and returns a strict JSON verdict that can drive the next edit iteration.

Core Features & Use Cases

  • Determines deterministic verdicts by highlighting exact visual differences between a current screenshot and reference images.
  • Returns a structured JSON payload with score, verdict, category_match, differences, suggestions, and reasoning for downstream automation.
  • Supports an optional category_hint to guide evaluation across multiple UI categories (e.g., dashboards, feeds, or landing pages).

Quick Start

Provide the reference images and the generated screenshot, then request a visual verdict to obtain a structured JSON result.

Frequently Asked Questions about visual-verdict

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

FAQPage Schema
How do I automate visual QA for UI screenshots against reference images?▼

Visual QA for UI screenshots is automated by comparing a generated image to one or more reference images, returning a strict JSON verdict. This provides deterministic pass/fail guidance to drive the next edit iteration.

What JSON output do I get from comparing a UI screenshot to a reference?▼

Comparing a UI screenshot to a reference returns a structured JSON payload containing score, verdict, category_match, differences, suggestions, and reasoning fields for downstream automation.

Can I use a category hint to evaluate different UI layouts like dashboards or feeds?▼

You can use an optional category_hint to guide evaluation across multiple UI categories such as dashboards, feeds, or landing pages. This focuses the visual fidelity comparison on the specific layout type.

What do I need to provide to get a pixel-perfect UI verdict?▼

To get a pixel-perfect UI verdict you need to provide at least one reference image and a current generated screenshot. The skill then highlights exact visual differences and returns a structured JSON result.

When should I use an image diff tool for UI visual fidelity testing?▼

An image diff tool for UI visual fidelity testing should be used when you have a current screenshot and at least one reference, and you need deterministic pass/fail guidance. It is ideal for automating visual QA tasks.

Related Skills

Explore More Design & Creative Skills→
SeoJaeWanSeoJaeWan
1

visual-compare

Compare reference and current UI renderings with pixel-level diff reports.

Community
Intermediate
skeduloDevelopersskeduloDevelopers
2

automations-developer

Build and debug Skedulo Pulse automations with REST JSON and Step Functions workflows.

Official
Advanced
hffmnnjhffmnnj
39

visual-regression

Compare screenshots pixel-by-pixel to detect unintended UI changes.

Community
Intermediate
YeaChan05YeaChan05

visual-verdict

Compare UI screenshots against reference images and return a JSON verdict.

Community
Intermediate