visual-verdict

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

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/Pryma-Tech/iris --skill visual-verdict-pryma-tech
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: visual-verdict
Source: https://github.com/Pryma-Tech/iris/tree/main/cli/skills/visual-verdict
Command: npx skills add https://github.com/Pryma-Tech/iris --skill visual-verdict-pryma-tech

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Compare generated UI screenshots against reference images to produce a strict JSON verdict.

Core Features & Use Cases

  • Automated visual QA checks of layout, typography, spacing, and component styling against references.
  • Deterministic JSON verdicts with score, verdict, category_match, differences, suggestions, and reasoning to guide iterations.
  • Works across design-review workflows for UI regression and visual QA.

Quick Start

Provide reference_images and a generated_screenshot to obtain a strict 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 visual QA checks for UI screenshots against reference images?

Automate visual QA by comparing generated UI screenshots against reference images to produce a strict JSON verdict, applying visual fidelity checks across layouts, typography, and spacing in design-review workflows.

What is image diff testing for UI regression and how does it work?

Image diff testing for UI regression compares generated screenshots against reference images to identify visual discrepancies. It returns a deterministic JSON schema containing score, verdict, category_match, differences, suggestions, and reasoning to guide iterations.

Can I get a structured JSON verdict from a design review screenshot comparison?

Yes, a design review screenshot comparison returns a deterministic JSON schema containing score, verdict, category_match, differences, suggestions, and reasoning to automate iterations and guide visual fidelity checks.

How do I perform visual fidelity checks on layout, typography, and component styling?

Perform visual fidelity checks by comparing generated UI screenshots against reference images. This validates layout, typography, spacing, and component styling, returning a strict JSON verdict to automate design-review workflows.

Do I need any dependencies to run automated UI testing for visual regression?

No dependencies are required to run automated UI testing for visual regression. Provide reference_images and a generated_screenshot to obtain a strict JSON verdict with score, differences, and suggestions.

What components are included for deterministic screenshot QA in design workflows?

Deterministic screenshot QA in design workflows requires no external components. Provide reference_images and a generated_screenshot to obtain a strict JSON verdict containing score, verdict, category_match, differences, suggestions, and reasoning.