skills.rest
Rheinmir
RheinmirCOMMUNITY
Explore all skills by this author →
GitHub

visual-verdict

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

Updated Mar 17, 2026
Search Tags:#ui-testing#quality-assurance#pixel-diff#screenshot-diff#design-quality#visual-verdict
One-click install
npx skills add https://github.com/Rheinmir/skills-kit --skill visual-verdict-rheinmir
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/Rheinmir/skills-kit/tree/main/skills/visual-verdict
Command: npx skills add https://github.com/Rheinmir/skills-kit --skill visual-verdict-rheinmir

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Compare generated UI screenshots against reference images to produce a deterministic JSON verdict that guides subsequent edits.

Core Features & Use Cases

  • Deterministic pass/fail verdicts for UI screenshots against references
  • Pixel-diff based localization of visual mismatches with actionable suggestions
  • Use Case: integrate into design QA pipelines to drive next iteration priorities

Quick Start

Run the visual-verdict check against the latest screenshot and reference images to obtain the verdict JSON.

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 regression testing for UI screenshots?▼

Automate visual regression testing by matching generated UI screenshots against reference images to produce a deterministic JSON verdict. This output includes pass/fail guidance, pixel-diff localization, and actionable suggestions to drive design iterations.

What is pixel-diff based visual QA and how does it work?▼

Pixel-diff based visual QA compares a new UI screenshot against a reference image to identify visual mismatches. It generates a structured JSON object containing a score, verdict, category match, differences, suggestions, and reasoning for iterative design.

How do I get a pass/fail verdict for front-end validation against design references?▼

Obtain a pass/fail verdict for front-end validation by running a screenshot comparison against your reference images. The process returns a strict JSON schema with deterministic verdicts and localized pixel differences to guide corrections.

Can I compare multiple UI references at once for design quality assurance?▼

Yes, you can perform visual QA across multiple references simultaneously. The process evaluates each generated UI screenshot against the provided reference images and returns structured pass/fail guidance and suggestions for each comparison.

Does visual-verdict require external dependencies to run screenshot diff checks?▼

No external dependencies are required to run visual-verdict. The skill operates independently to match UI screenshots against reference images and output the deterministic JSON verdict without needing additional component installations.

What is the best way to structure visual QA feedback for iterative design?▼

The best way to structure visual QA feedback is using a deterministic JSON schema containing score, verdict, category match, differences, suggestions, and reasoning. This format standardizes pass/fail guidance for design iterations.

Related Skills

Explore More Design & Creative Skills→
gtpgg1013gtpgg1013

visual-verdict

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

Community
Intermediate
OliverOuyangOliverOuyang
1

visual-verdict

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

Community
Intermediate
wmasfoewmasfoe

visual-verdict

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

Community
Advanced
hffmnnjhffmnnj
39

visual-regression

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

Community
Intermediate