Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PMDevSolutions/Aureliusnpx agentmods add skills/pmdevsolutions/aurelius/visual-qa-verificationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pmdevsolutions/aurelius/visual-qa-verification)<a href="https://agentmods.dev/skills/pmdevsolutions/aurelius/visual-qa-verification"><img src="https://agentmods.dev/badge/skills/pmdevsolutions/aurelius/visual-qa-verification/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pmdevsolutions/aurelius/visual-qa-verification"><img src="https://agentmods.dev/badge/skills/pmdevsolutions/aurelius/visual-qa-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.03761 |
| Opus 5.5 | $0.00032 | $0.01504 |
| Sonnet 5.5 | $0.00016 | $0.00752 |
| Haiku 4.5 | $0.00008 | $0.00376 |
Grade A, and why
visual-qa-verification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual QA Verification
Overview
After the figma-react-converter agent generates React components and pages, this skill guides verification that the output matches the Figma source design. It covers screenshot comparison, responsive behavior, accessibility, performance, and asset rendering.
Core Principle: Every converted design must be visually verified before delivery. Build checks validate structure and types; this skill validates what the user actually sees in the browser.
When to Use
Use this skill when:
- A Figma-to-React conversion has just completed
- Verifying generated components match their Figma source
- Running post-conversion visual QA
- Checking responsive behavior of generated pages
- Validating that all images and assets render correctly
Symptoms that trigger this skill:
- "verify app"
- "visual QA"
- "compare to Figma"
- "check screenshots"
- "does it match the design"
- "responsive check"
- "pixel-perfect"
Verification Checklist
Run these checks in order after conversion completes.
Step 1: Start Development Server
Start the React application and verify it builds and renders without errors.
# Install dependencies
pnpm install
# Start dev server
pnpm dev
# Verify build passes (catches TypeScript errors, missing imports)
pnpm build
Check the terminal output for:
- Zero TypeScript errors
- Zero import resolution failures
- No runtime console errors on initial load
Open the browser console and verify no errors or warnings appear on page load.
Step 2: Automated Visual Diff Loop
This is the core pixel-perfect iteration loop. It compares app screenshots against Figma source screenshots using pixelmatch via scripts/visual-diff.js.
Configuration: Read .claude/pipeline.config.json for thresholds and iteration limits:
iterationLoop.maxVisualIterations— max fix attempts (default: 5)iterationLoop.diffPassThreshold— max mismatch ratio to pass (default: 0.02 = 2%)iterationLoop.diffWarnThreshold— mismatch ratio that triggers warning (default: 0.05 = 5%)iterationLoop.regionAnalysis— enable per-region diff reporting (default: true)visualDiff.breakpoints— breakpoints to test
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +2 lines 5e4b72c65561
- 1mo ago First seen · 389 lines · 81 tokens per session scan A e95f2527268a
visual-qa-verification is a skill published in the GitHub repository PMDevSolutions/Aurelius (9 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 3,761 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
figma-codegen
Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…
mk:figma
Read-first Figma gateway via Figma MCP: analyze designs, implement Figma-to-code for 1–3 screens, extract design tokens, produce a Figma Evidence Packet for planning handoff, screenshot fallback. Advanced operations (Code Connect, canvas writes, design-system/library patterns) are gated references loaded only on…
generate-project-design-system
A draft generator that studies a project's code and Figma design data to prepare a design-system skill. A design system is a shared set of colors, sizes, components, and usage rules for keeping interfaces consistent.
Figma Developer
Extract components from Figma, convert designs to React components, sync design tokens, and generate code from designs. Bridge the gap between design and code with automated workflows.
high-plains-drifter
Align a design to your real Storybook components instead of reconstructing it. Use when turning a Figma frame into React built from an existing component library (Build mode), or when pulling scrappy exploratory code into line with the library once a direction feels right (Align mode). Triggers include "build this…
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…