skills.rest
marcmunoz-uno
marcmunoz-unoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

visual-verdict

Compare generated UI screenshots against reference images and output structured JSON verdicts.

3|Updated Apr 2, 2026
Search Tags:#screenshot comparison#reference images#ui regression#pixel diff#visual qa#iteration loop#json verdict
One-click install
npx skills add https://github.com/marcmunoz-uno/jailbreak --skill visual-verdict-marcmunoz-uno
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/marcmunoz-uno/jailbreak/tree/main/skills/visual-verdict
Command: npx skills add https://github.com/marcmunoz-uno/jailbreak --skill visual-verdict-marcmunoz-uno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes guesswork from screenshot-based UI iteration by producing a strict, machine-readable verdict against reference images.

Core Features & Use Cases

  • Screenshot-to-reference comparison: Evaluates a generated screenshot against one or more reference images for layout, spacing, typography, and styling consistency.
  • Deterministic QA loop support: Returns structured JSON verdict data that can drive the next edit iteration until a target threshold is reached.
  • Category/style alignment check: Flags whether the generated output matches the intended UI category or style using an optional category hint.

Quick Start

Use the visual-verdict skill with reference_images and the generated_screenshot to obtain a JSON-only verdict for whether the UI needs revision.

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 checks using screenshot comparison?▼

Automate UI regression checks by comparing a generated screenshot against reference images to produce a structured JSON verdict containing pass/fail scores, differences, and suggestions for the next edit iteration.

What is visual QA pass/fail JSON and when do I need it for iteration loops?▼

Visual QA pass/fail JSON is a machine-readable verdict evaluating layout, spacing, and typography against reference images, needed when running deterministic editing loops until a visual conformance threshold is reached.

How do I get a pixel diff score for style and category conformance?▼

Obtain a pixel diff score by evaluating a generated screenshot with an optional category hint against reference images, returning a strict JSON contract with category_match flags and concise reasoning.

Can I use screenshot validation to drive automated UI editing workflows?▼

Screenshot validation drives automated UI editing workflows by returning structured JSON data containing scores and suggestions that trigger subsequent code edits until the target visual threshold is met.

Does visual QA work with multiple reference images for layout comparison?▼

Visual QA evaluates a generated screenshot against one or more reference images, checking layout, spacing, typography, and styling consistency to return a strict JSON verdict for iterative design.

Related Skills

Explore More Design & Creative Skills→
hffmnnjhffmnnj
39

visual-regression

Compare screenshots pixel-by-pixel to detect unintended UI changes.

Community
Intermediate
Goblin1024Goblin1024
6

visual-verdict

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

Community
Intermediate
aquariuscookaquariuscook

visual-testing-advanced

Compare screenshots across viewports and browsers to detect visual regressions.

Community
Advanced
YeaChan05YeaChan05

visual-verdict

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

Community
Intermediate