Skip to main content
skill CX Codex

visual-qa-evaluator — Claude Code skill: interface visual regression analysis

Visual-qa-evaluator is a Claude Code skill that prepares evidence for visual QA and regression analysis. It supports matching interface states to evaluate design changes.

MIT ★ 529 updated 2026-11-17

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ShuaiMXu/happyhands --skill visual-qa-evaluator -a claude-code
Open on GitHub

What visual-qa-evaluator does

This skill prepares structured evidence for visual review by comparing hierarchy, grouping, and reading order between states. It requires desktop and mobile captures, alongside a stated design intent, to build a comprehensive review brief.

The tool focuses on deterministic artifact preparation rather than automated visual judgment. When information is missing, it signals the need for further evidence. It uses a versioned design-language rubric to ensure consistent findings while preserving original brand choices and documenting limitations separately from functional fixes.

What it helps with

  • Compare interface renders before and after changes
  • Identify visual regressions in layout hierarchy
  • Format evidence for professional visual review
  • Validate interface changes against design system rules

Example prompts for the agent

  • visual-qa-evaluator: prepare review brief for these interface captures
  • visual-qa-evaluator: check hierarchy against design rubric
  • visual-qa-evaluator: list current visual findings and limitations

How to install visual-qa-evaluator

1Skills CLI (Vercel)

npx skills add ShuaiMXu/happyhands --skill visual-qa-evaluator -a claude-code

2Manually: put the files in place

~/.claude/skills/visual-qa-evaluator/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/visual-qa-evaluator/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about visual-qa-evaluator

How to install visual-qa-evaluator in Claude Code?

Run npx skills add ShuaiMXu/happyhands --skill visual-qa-evaluator -a claude-code.

What does visual-qa-evaluator do?

It processes matched interface captures to produce structured reports, findings, and design-related observations for independent QA.

What is required to use visual-qa-evaluator?

You need desktop and mobile captures, the critical task description, and defined design intent.

Source text

SKILL.md · MIT
---
name: visual-qa-evaluator
description: "Compare matched before and after renders for task clarity and visual regressions after a product change."
---

# Visual QA Evaluator

Prepare an independent visual decision from matched evidence.

## Required evidence

- same-state desktop and mobile captures
- critical task
- declared design intent

## Decisions

- Compare hierarchy, grouping, contrast and reading order
- Report regressions separately
- State uncertainty rather than inventing a score

## Boundary

The deterministic handler only prepares matched artifacts; screenshot-aware review is required.

Return structured evidence, findings, proposed updates and limitations. Use `needs-evidence` when required inputs or professional review are missing. Never invent an Experience Score or promote a project observation into a universal rule.

## Design language continuity

Read [the shared design-language rubric](../visual-hierarchy-reviewer/rubric.json). Apply it to the confirmed change and introduced regressions, preserving supplied brand choices. Put the visible element, task/brand conflict and minimal remedy in each finding's observation. Existing out-of-scope opportunities belong in limitations, not automatic failure of a narrow fix. The Workbench's independent AI review receives this same versioned rubric and foundation context.

## Bundled OJO methodology

Use the [Harness OJO adapter](../../vendor/ojo/ADAPTER.md), then its linked original Skill and relevant references. The runtime records a verified guidance snapshot in this result; design execution and independent QA receive the same pinned source with mode-specific reading routes. Preserve the existing evidence and approval boundaries.

## Execution contract

The bounded handler prepares source-bound matched originals and a review brief; it does not view the images or execute an independent visual judgment. Keep missing states and mismatched configurations visible. Use the existing independent ai-review/attest record for actual task, hierarchy, interaction, design-system and regression conclusions. A successful evidence pairing cannot stand in for an independent review or final acceptance.

© ShuaiMXu · MIT · ShuaiMXu/happyhands

Similar skills

All skills for Testing and QA →

From the same set34

The whole set →
interaction-reviewer interaction-reviewer is a Claude Code skill that reviews interaction flow and control behavior. It detects missing feedback, unnecessary steps, and unsafe UI state transitions. CX Codex +1 ★ 529repo stars information-architecture-reviewer information-architecture-reviewer is a Claude Code skill that audits navigation and content hierarchy against user tasks. It identifies dead ends and ambiguous labels along target flows. CX Codex +1 ★ 529repo stars foundation-extractor Foundation-extractor is a Claude Code skill that builds an inventory of design tokens and component sources. It maps existing design elements in a repository before proposing foundation updates. CX Codex +1 ★ 529repo stars component-inventory component-inventory is a Claude Code skill that maps components to source paths, variants, composition, and known consumers. It supports reuse decisions and drift analysis. CX Codex +1 ★ 529repo stars brand-foundation-extractor brand-foundation-extractor is a Claude Code skill that gathers candidate brand principles, voice cues, and visual assets from project files and rendered content. It keeps each finding tied to its source. CX Codex +1 ★ 529repo stars token-contrast-auditor The token-contrast-auditor skill for Claude Code verifies color pair contrast against WCAG standards. It runs during project analysis to check design tokens and CSS styles. CX Codex +1 ★ 529repo stars pattern-library-curator pattern-library-curator is a Claude Code skill that gathers accepted interface solutions into a project pattern library. It checks recurring decisions for evidence before they are treated as reusable patterns. CX Codex +1 ★ 529repo stars design-system-drift-detector The design-system-drift-detector skill for Claude Code identifies discrepancies between implementation and design tokens. It detects ungoverned literals, semantic conflicts, and off-scale values. CX Codex +1 ★ 529repo stars

Project sponsors

Companies that keep this analytics open