skills.rest
ozby
ozbyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

visual-verdict

Compare generated UI screenshots to reference images and output a strict JSON verdict.

1|Updated Mar 17, 2025
Search Tags:#ui#quality-assurance#visual-regression#reference-images#pixel-diff#visual-verdict#json-verdict
One-click install
npx skills add https://github.com/ozby/node-pubsub --skill visual-verdict-ozby
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/ozby/node-pubsub/tree/main/.codex/skills/visual-verdict
Command: npx skills add https://github.com/ozby/node-pubsub --skill visual-verdict-ozby

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Compares generated UI screenshots against reference images to provide a deterministic, machine-readable verdict that guides subsequent UI iterations.

Core Features & Use Cases

  • Produces a JSON verdict containing score, verdict, category_match, differences, suggestions, and reasoning.
  • Accepts reference_images and generated_screenshot inputs with optional category_hint for domain scoping.
  • Supports iterative improvement loops with threshold-based feedback and state persistence for analytics.

Quick Start

Run a visual-verdict pass by comparing a generated screenshot to reference images and returning the required verdict fields.

Frequently Asked Questions about visual-verdict

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

FAQPage Schema
How do I get a JSON verdict for visual regression testing of a UI screenshot?▼

To get a JSON verdict for visual regression, compare a generated UI screenshot against reference images to receive a strict object containing score, verdict, category_match, differences, suggestions, and reasoning fields.

What is visual regression comparison and how does pixel diff scoring work?▼

Visual regression comparison evaluates a generated UI screenshot against reference images, producing a pixel diff score and a strict JSON verdict to guide subsequent UI iterations with deterministic, machine-readable feedback.

Can I scope visual regression checks to specific UI domains like layouts or typography?▼

Yes, you can scope visual regression checks to specific UI domains by providing an optional category_hint, allowing the comparison to focus strictly on components, layouts, or typography as needed.

How do I automate iterative UI improvement loops using threshold-based visual feedback?▼

You can automate iterative UI improvement by feeding the JSON verdict back into your pipeline, using the threshold-based score and suggestions fields to drive subsequent UI generation passes.

Does visual regression testing require external dependencies to compare reference images?▼

No external dependencies are required to compare reference images and generated screenshots; the visual verdict process operates independently to output the strict JSON verdict object.

What is the best way to evaluate UI quality assurance across multiple reference images?▼

The best way to evaluate UI quality assurance is to input multiple reference images alongside a generated screenshot, yielding a single JSON verdict with pixel diff scores and actionable suggestions.

Related Skills

Explore More Design & Creative Skills→
huyhung9630huyhung9630
1

omc-visual-verdict

Compare UI screenshots against reference images and generate a JSON visual QA verdict.

Community
Intermediate
INNERJOINTINNERJOINT

visual-verdict

Compare generated UI screenshots against reference images and emit a strict JSON pass/fail verdict.

Community
Intermediate
gtpgg1013gtpgg1013

visual-verdict

Compare generated UI screenshots with reference images to produce a deterministic JSON verdict.

Community
Intermediate
YeaChan05YeaChan05

visual-verdict

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

Community
Intermediate