skills.rest
Goblin1024
Goblin1024COMMUNITY
Explore all skills by this author →
GitHub

visual-verdict

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

6|1|Updated Apr 16, 2026
Search Tags:#ui-testing#design QA#pixel-diff#screenshot-analysis#visual-verdict#json-verdict
One-click install
npx skills add https://github.com/Goblin1024/oh-my-kimi --skill visual-verdict-goblin1024
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/Goblin1024/oh-my-kimi/tree/main/skills/visual-verdict
Command: npx skills add https://github.com/Goblin1024/oh-my-kimi --skill visual-verdict-goblin1024

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Compare the latest generated UI screenshot against reference images and produce a precise JSON verdict. This approach is applicable to design QA workflows that require pixel-accurate validation and may involve multiple reference images to characterize differences.

Core Features & Use Cases

  • Pixel-accurate UI comparison between generated screenshots and reference images.
  • Output a structured JSON payload with score, verdict, category_match, differences, suggestions, and reasoning.
  • Integrate into design QA pipelines to automate iteration gating and regression detection.

Quick Start

Run visual-verdict on the latest UI screenshot and reference images to obtain a JSON verdict.

Frequently Asked Questions about visual-verdict

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

FAQPage Schema
How do I automate UI regression detection using screenshot comparison?▼

To automate UI regression detection, the visual-verdict Skill compares your latest UI screenshots against reference images and outputs a structured JSON object containing a score, verdict, and list of differences. This enables automated gating in your design QA pipelines.

What is a JSON verdict in design QA workflows?▼

A JSON verdict in design QA workflows is a structured output payload containing score, verdict, category_match, differences, suggestions, and reasoning. It enables automated iteration gating and regression detection by providing deterministic UI visual verdicts.

How do I perform pixel-accurate UI validation against multiple reference images?▼

To perform pixel-accurate UI validation, you provide the latest generated UI screenshot alongside multiple reference images. The tool characterizes the differences and produces a precise JSON verdict with suggestions and reasoning.

Can I use screenshot analysis to gate UI iteration pipelines?▼

Yes, you can gate UI iteration pipelines by running screenshot analysis on the latest generated UI and reference images. The tool outputs a deterministic JSON verdict with a score and category match, enabling automated pipeline gating.

Does visual-verdict work with multiple reference images to characterize UI differences?▼

Yes, visual-verdict works with multiple reference images to characterize differences. It compares the latest generated UI screenshot against these references and outputs a structured JSON object containing differences, suggestions, and reasoning.

Related Skills

Explore More Design & Creative Skills→
EvolutionAPIEvolutionAPI
520

dev-visual-verdict

Compare before and after screenshots to detect visual regressions in UI components.

Official
Intermediate
KYRIE66nbKYRIE66nb

visual-verdict

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

Community
Advanced
OliverOuyangOliverOuyang
1

visual-verdict

Compare UI screenshots to reference images and output a JSON pass/fail verdict.

Community
Intermediate
robit-manrobit-man

regression-visual

Compare screenshots and analyze pixel differences across browsers and viewports.

Community
Advanced