Borrowing it
Nothing to install: this file belongs to tan-yong-sheng/ai-vision-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tan-yong-sheng/ai-vision-mcp/main/.claude/skills/web-quality-audit/SKILL.mdgit clone --depth 1 https://github.com/tan-yong-sheng/ai-vision-mcpWrote 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/tan-yong-sheng/ai-vision-mcp/web-quality-audit)<a href="https://agentmods.dev/skills/tan-yong-sheng/ai-vision-mcp/web-quality-audit"><img src="https://agentmods.dev/badge/skills/tan-yong-sheng/ai-vision-mcp/web-quality-audit/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/tan-yong-sheng/ai-vision-mcp/web-quality-audit"><img src="https://agentmods.dev/badge/skills/tan-yong-sheng/ai-vision-mcp/web-quality-audit.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 | $0.00052 | $0.01571 |
| Opus 5 | $0.00026 | $0.00785 |
| Sonnet 5 | $0.00010 | $0.00314 |
| Haiku 4.5 | $0.00005 | $0.00157 |
Grade A, and why
web-quality-audit 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 12d ago.
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.
This is a copy
97% identical to web-quality-audit — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web quality audit
Comprehensive quality review based on Google Lighthouse audits. Covers Performance, Accessibility, SEO, and Best Practices across 150+ checks.
How it works
- Analyze the provided code/project for quality issues
- Categorize findings by severity (Critical, High, Medium, Low)
- Provide specific, actionable recommendations
- Include code examples for fixes
Audit categories
Performance (40% of typical issues)
Core Web Vitals — Must pass for good page experience:
- LCP (Largest Contentful Paint) < 2.5s. The largest visible element must render quickly. Optimize images, fonts, and server response time.
- INP (Interaction to Next Paint) < 200ms. User interactions must feel instant. Reduce JavaScript execution time and break up long tasks.
- CLS (Cumulative Layout Shift) < 0.1. Content must not jump around. Set explicit dimensions on images, embeds, and ads.
Resource Optimization:
- Compress images. Use WebP/AVIF with fallbacks. Serve correctly sized images via
srcset. - Minimize JavaScript. Remove unused code. Use code splitting. Defer non-critical scripts.
- Optimize CSS. Extract critical CSS. Remove unused styles. Avoid
@import. - Efficient fonts. Use
font-display: swap. Preload critical fonts. Subset to needed characters.
Loading Strategy:
- Preconnect to origins. Add
<link rel="preconnect">for third-party domains. - Preload critical assets. LCP images, fonts, and above-fold CSS.
- Lazy load below-fold content. Images, iframes, and heavy components.
- Cache effectively. Long cache TTLs for static assets. Immutable caching for hashed files.
Accessibility (30% of typical issues)
Perceivable:
- Text alternatives. Every
<img>has meaningfulalttext. Decorative images usealt="". - Color contrast. Minimum 4.5:1 for normal text, 3:1 for large text (WCAG AA).
- Don't rely on color alone. Use icons, patterns, or text alongside color indicators.
- Captions and transcripts. Video has captions. Audio has transcripts.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 171 lines · 52 tokens per session scan A aaada64b636b
web-quality-audit is a skill published in the GitHub repository tan-yong-sheng/ai-vision-mcp (78 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 1,571 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to web-quality-audit, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…