visual-verdict

Name: visual-verdict
Availability: InStock
Author: byonk19-svg

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

Updated Feb 21, 2026

Search Tags:#pixel-diff #ui-quality #visual-verdict #json-verdict #screenshot-comparison

Ready to run

npx skills add https://github.com/byonk19-svg/rt-scheduler --skill visual-verdict-byonk19-svg

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/byonk19-svg/rt-scheduler/tree/main/.codex/skills/visual-verdict
Command: npx skills add https://github.com/byonk19-svg/rt-scheduler --skill visual-verdict-byonk19-svg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quickly determine how closely a generated UI screenshot matches reference images by producing a structured, deterministic verdict that can drive the next iteration.

Core Features & Use Cases

Uses a strict JSON verdict with fields score, verdict, category_match, differences, suggestions, and reasoning to guide design or development edits.
Accepts inputs: reference_images[] and generated_screenshot to quantify visual fidelity across layouts, spacing, typography, and component styling.
Ideal for UI review workflows, pixel-perfect validation of dashboards, apps, or marketing pages, and for standardizing QA feedback across teams.

Quick Start

Use the generated_screenshot path and reference_images to obtain a JSON verdict that describes visual differences and suggested fixes.

Frequently Asked Questions about visual-verdict

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

FAQPage Schema

How do I compare a generated UI screenshot against a reference image for pixel-perfect accuracy?▼

Screenshot comparison for UI quality assurance accepts reference images and a generated screenshot to produce a structured JSON verdict, quantifying visual fidelity across layouts, spacing, typography, and component styling with actionable suggestions.

What is a deterministic JSON verdict for visual QA and how does it work?▼

A deterministic JSON verdict outputs structured fields including score, verdict, category_match, differences, suggestions, and reasoning to identify visual fidelity gaps between a generated UI screenshot and reference images for standardized QA feedback.

Can I use screenshot comparison to validate mobile app layouts and web dashboards?▼

Screenshot comparison applies to UI dashboards, components, and layouts across web or mobile interfaces when pixel-perfect accuracy is required, accepting reference images and a generated screenshot to quantify visual fidelity gaps.

What is the best way to automate UI review workflows with structured visual feedback?▼

The best way to automate UI review workflows is using a deterministic JSON verdict from screenshot comparison, providing score, differences, and suggestions fields that programmatically drive the next design or development iteration for pixel-perfect validation.

Do I need any dependencies or specific components to run visual verdict checks?▼

Visual verdict checks require no dependencies or specific components; you only need to provide the generated screenshot path, reference images array, and an optional category hint to obtain the structured JSON output for pixel-diff analysis.