skills.rest
wmasfoe
wmasfoeCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

visual-verdict

Compare a generated UI screenshot against reference images and output a structured JSON verdict.

Updated Apr 23, 2026
Search Tags:#reference-images#json-output#pixel-diff#ui-quality#qa-automation#visual-verdict#screenshot-comparison
One-click install
npx skills add https://github.com/wmasfoe/notch-pet --skill visual-verdict-wmasfoe
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/wmasfoe/notch-pet/tree/main/.codex/skills/visual-verdict
Command: npx skills add https://github.com/wmasfoe/notch-pet --skill visual-verdict-wmasfoe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Compares a generated UI screenshot against reference images and returns a strict JSON verdict to drive the next design iteration.

Core Features & Use Cases

  • Visual-didelity assessment against reference images to identify layout, typography, and component mismatches
  • Deterministic JSON verdict including score, verdict, category_match, differences, and suggestions for rapid iteration
  • Supports design reviews, UI QA sprints, and cross-device validation workflows

Quick Start

Provide a deterministic verdict by comparing the latest UI render against reference images.

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?▼

Automated visual QA compares a generated UI screenshot against reference images to identify layout and typography mismatches, returning a structured JSON verdict with a pass/fail score to drive design iteration.

What is pixel-diff driven UI comparison and how does it work?▼

Pixel-diff driven UI comparison evaluates visual fidelity by analyzing a generated screenshot against reference images, outputting a deterministic JSON verdict containing category match scores, detected differences, and actionable suggestions.

Can I get a structured JSON output for screenshot comparison results?▼

Yes, screenshot comparison returns a deterministic JSON verdict containing score, verdict, category_match, differences, suggestions, and reasoning to provide strict pass/fail guidance for automated design reviews.

How do I use visual verdicts for cross-device validation and UI QA sprints?▼

Visual verdicts support cross-device validation and UI QA sprints by providing deterministic pass/fail guidance from screenshot comparisons, enabling rapid iteration during design reviews.

Does automated visual mismatch detection require any specific dependencies?▼

No specific dependencies are required to run automated visual mismatch detection, as the Skill directly accepts reference images and generated screenshots to produce its structured JSON output.

What limitations are there when using JSON verdicts for design iteration?▼

The JSON verdict provides deterministic pass/fail guidance based on visual fidelity, meaning it is strictly limited to comparing provided screenshots against reference images rather than dynamically interacting with the live UI code.

Related Skills

Explore More Design & Creative Skills→
yy1588133yy1588133
2

vverify

Compare screenshots to reference images and generate JSON scorecards.

Community
Advanced
Goblin1024Goblin1024
6

visual-verdict

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

Community
Intermediate
OliverOuyangOliverOuyang
1

visual-verdict

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

Community
Intermediate
flyingtimesflyingtimes

podcast-writer

Transform user-provided text into structured podcast narration scripts.

Community
Intermediate