Web Quality Skills is a collection of agent skills for measuring and improving website performance, accessibility, search optimization, and browser usability. Developers use it with any web framework to run Lighthouse and Chrome DevTools checks, analyze Core Web Vitals and CrUX data, and apply WCAG and SEO guidance. The catalogue entries are the project's own skills, instructions, and plugin for agent-assisted web-quality work.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add addyosmani/web-quality-skills --skill web-quality-auditgit clone --depth 1 https://github.com/addyosmani/web-quality-skillsWrote 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/addyosmani/web-quality-skills/web-quality-audit)<a href="https://agentmods.dev/skills/addyosmani/web-quality-skills/web-quality-audit"><img src="https://agentmods.dev/badge/skills/addyosmani/web-quality-skills/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/addyosmani/web-quality-skills/web-quality-audit"><img src="https://agentmods.dev/badge/skills/addyosmani/web-quality-skills/web-quality-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00058 | $0.02328 |
| Opus 5 | $0.00029 | $0.01164 |
| Sonnet 5 | $0.00012 | $0.00466 |
| Haiku 4.5 | $0.00006 | $0.00233 |
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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web quality audit
Comprehensive quality review that combines live browser evidence with source inspection. Covers Performance, Accessibility, SEO, Best Practices, and Agentic Browsing without treating an aggregate score as proof of quality.
Lighthouse 13+. The Performance category now uses shared Performance Insights across Lighthouse and the DevTools Performance panel (announcement). Follow current insight names and evidence. Do not require removed audit IDs or automatically recreate their recommendations; some were retired because they were noisy, inactionable, or easy to over-recommend.
How it works
- Establish the audit target: representative URLs, important states and journeys, public versus authenticated access, and mobile/desktop scope.
- If a page can run, read the measurement workflow and collect a minimal live baseline before searching the codebase broadly.
- Use runtime failures to localize source inspection. Keep measured findings separate from hypotheses found only in code.
- Categorize by user impact and confidence, then make or recommend specific fixes.
- Re-run equivalent automated checks and the affected manual flows. Report what is verified and what still needs field or human validation.
Tool routing
Use the best capability already available; do not block the audit on optional setup.
| Need | Preferred route | Fallback |
|---|---|---|
| Performance and Core Web Vitals | Record a browser performance trace and analyze focused insights; with Chrome DevTools MCP, use performance_start_trace then performance_analyze_insight |
Lighthouse CLI or PageSpeed Insights lab data |
| Real-user performance | CrUX values included in current DevTools trace summaries | PageSpeed Insights/CrUX Vis; direct CrUX API only when a key is already available or automation is requested |
| Accessibility, SEO, Best Practices, Agentic Browsing | Run a live Lighthouse audit; with Chrome DevTools MCP, use lighthouse_audit |
Category-specific Lighthouse CLI audits plus manual checks |
| Rendered semantics and interaction | Inspect the accessibility tree and exercise the UI; with Chrome DevTools MCP, use take_snapshot and focused evaluate_script |
Browser/manual testing |
| Source smoke test | scripts/analyze.sh <path> |
Direct source inspection |
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 · 210 lines · 58 tokens per session scan A 1903cfb4dcba
web-quality-audit is a skill published in the GitHub repository addyosmani/web-quality-skills (2,779 stars, last pushed 18d ago), licensed MIT. It adds 58 tokens to every session and 2,328 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
agent-ready-scan-site
Sub-skill: Scan any URL for agent readiness. Checks 18 standards across 5 categories, returns readiness level (0-5), status of all checks, and fix instructions.
agent-ready-webmcp
Sub-skill de agent-ready-cloudflare: Implement WebMCP.
web-data-extraction
Use when extracting data from web pages. Covers choosing between an API, static parsing, and a browser, handling JavaScript-rendered content, resilient selectors, rate limiting, and scraping responsibly.
e2e-playwright
Use when writing end-to-end browser tests with Playwright. Covers resilient locators, auto-waiting, network interception, authentication reuse, parallelization, and eliminating flakiness.
web-app-testing
Use when testing a web application interactively — verifying a feature, reproducing a bug, or checking a flow in a real browser. Covers systematic exploration, console and network inspection, and reporting what you find.
fuse-browser-usage
Use when about to call any mcpfuse-browser tool. Routes fetch/crawl/SERP vs live browser session vs screenshot capture, and enforces the 4 ZERO-TOLERANCE rules -- read BEFORE the tool call.