Explore all skills by this author →

Verified:GitHub

visual-verdict

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

Updated Mar 31, 2026

Search Tags:#ui #screenshots #qa #design-review #json-output #image-diff #visual-verdict

Ready to run

npx skills add https://github.com/ClementATH/oh-my-claudecode --skill visual-verdict

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/ClementATH/oh-my-claudecode/tree/main/skills/visual-verdict
Command: npx skills add https://github.com/ClementATH/oh-my-claudecode --skill visual-verdict

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the evaluation of UI screenshots by comparing a generated image against reference images and returning a strict JSON verdict that guides design and development iterations.

Core Features & Use Cases

Deterministic JSON verdicts with fields: score, verdict, category_match, differences, suggestions, and reasoning.
Supports multiple reference images to validate UI consistency across variants.
Ideal for design reviews, regression checks, and automated UI QA pipelines.

Quick Start

Run the visual-verdict check by providing your generated_screenshot path and one or more reference_images to receive a structured JSON verdict for integration into your workflow.

Frequently Asked Questions about visual-verdict

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

FAQPage Schema

Can I check UI consistency across multiple reference images?▼

Check UI consistency across multiple reference images by comparing a generated screenshot against them to receive a structured JSON verdict. This validates typography, layouts, and color consistency across design system variants, returning category_match and actionable guidance.

How do I get structured JSON output for UI QA?▼

Get structured JSON output for UI QA by providing a generated screenshot path and one or more reference images. The process returns a deterministic JSON verdict containing score, verdict, category_match, differences, suggestions, and reasoning for immediate workflow integration.

What UI elements does the visual verdict evaluate?▼

The visual verdict evaluates UI components, layouts, typography, and color consistency by comparing a generated screenshot against reference images. It returns a deterministic JSON verdict with score, differences, and suggestions to guide design and development iterations.

Do I need external dependencies to run automated UI regression checks?▼

No external dependencies are required to run automated UI regression checks with visual-verdict. It operates without external side effects, enforces a strict JSON schema, and safely integrates into CI/CD pipelines to evaluate generated screenshots against reference images.

How do I get structured JSON output for UI QA?▼

Related Skills

Explore More Design & Creative Skills→

yy1588133

vverify

Compare screenshots to reference images and generate JSON scorecards.

Community

Advanced

Rheinmir

visual-verdict

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

cicd-integration

Generate CI/CD pipeline configurations for design system quality checks.

Community

Advanced

lpjhelder

visual-verdict

Evaluate UI screenshots against reference images and produce a structured JSON verdict with score, pass/fail status, category match, differences, suggestions, and reasoning.

Community

Intermediate