跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 web-quality-audit

Web Quality Audit

开展以证据为主导的网络质量审计,审计内容包括业绩、可访问性、标准作业程序、最佳做法和代理浏览。 当被要求"审计我的网站","审查网站质量","运行灯塔审计","检查页面质量",或"优化我的网站"时使用.

38218 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

开展以证据为主导的网络质量审计,审计内容包括业绩、无障碍、标准作业程序、最佳做法和代理浏览

何时用

要求"审计我的网站","审查网站质量","运行灯塔审计","检查页面质量",或"优化我的网站"

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Web quality audit、How it works、Tool routing、Audit categories、Performance、Accessibility。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/MEASUREMENT.md、scripts/analyze.sh,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".

Web quality auditHow it worksTool routingAudit categoriesPerformanceAccessibilitySEOBest practicesAgentic browsingSeverity levelsAudit output formatAudit results

· 许可:MIT

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
web-quality-audit
description
Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".
许可
MIT
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 2
  • references/MEASUREMENT.md
  • scripts/analyze.sh

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「web-quality-audit」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-857f0d47c6d6a407-%E7%BD%91%E7%BB%9C%E8%B4%A8%E9%87%8F%E5%AE%A1%E8%AE%A1.html
请存为 .cursor/skills/web-quality-audit/SKILL.md 或 .claude/skills/web-quality-audit/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/addyosmani/web-quality-skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/addyosmani/web-quality-skills' --list

npx skills add 'https://github.com/addyosmani/web-quality-skills' --skill 'web-quality-audit'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: web-quality-audit description: Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website". license: MIT metadata: author: web-quality-skills version: "2.0" --- # 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](https://developer.chrome.com/blog/moving-lighthouse-to-insights)). 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 1. Establish the audit target: representative URLs, important states and journeys, public versus authenticated access, and mobile/desktop scope. 2. If a page can run, read [the measurement workflow](../performance/references/MEASUREMENT.md) and collect a minimal live baseline before searching the codebase broadly. 3. Use runtime failures to localize source inspection. Keep measured findings separate from hypotheses found only in code. 4. Categorize by user impact and confidence, then make or recommend specific fixes. 5. 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 ` | Direct source inspection | Chrome DevTools MCP's `lighthouse_audit` intentionally excludes performance. Its navigation mode reloads the page; use snapshot mode when preserving the current authenticated or user-created state matters. The static analyzer is a fast smoke test, not a substitute for a rendered-page audit. ## Audit categories ### Performance **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 `` 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 **Perceivable:** * **Text alternatives.** Every `` has meaningful `alt` text. Decorative images use `alt=""`. * **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. **Operable:** * **Keyboard accessible.** All functionality available via keyboard. No keyboard traps. * **Focus visible.** Clear focus indicators on all interactive elements. * **Skip links.** Provide "Skip to main content" for keyboard users. * **Sufficient time.** Users can extend time limits. No auto-advancing content without controls. **Understandable:** * **Page language.** Set `lang` attribute on ``. * **Consistent navigation.** Same navigation structure across pages. * **Error identification.** Form errors clearly described and associated with fields. * **Labels and instructions.** All form inputs have associated labels. **Robust:** * **Valid HTML.** No duplicate IDs. Properly nested elements. * **ARIA used correctly.** Prefer native elements. ARIA roles match behavior. * **Name, role, value.** Interactive elements have accessible names and correct roles. ### SEO **Crawlability:** * **Valid robots.txt.** Doesn't block important resources. * **XML sitemap.** Lists all important pages. Submitted to Search Console. * **Canonical URLs.** Prevent duplicate content issues. * **No noindex on important pages.** Check meta robots and headers. **On-Page SEO:** * **Unique title tags.** Make each title descriptive and concise; display truncation varies by device and result type. * **Meta descriptions.** Write useful, page-specific summaries; search engines may choose a different snippet. * **Heading hierarchy.** The primary heading is descriptive and the structure is logical; do not fail valid HTML solely for using more than one `

`. * **Descriptive link text.** Not "click here" or "read more". **Technical SEO:** * **Mobile-friendly.** Responsive design. Tap targets ≥ 48px. * **HTTPS.** Secure connection required. * **Page experience signals.** Use field Core Web Vitals as evidence, without promising a ranking change. * **Structured data.** JSON-LD for rich snippets (Article, Product, FAQ, etc.). ### Best practices **Security:** * **HTTPS everywhere.** No mixed content. HSTS enabled. * **No vulnerable libraries.** Keep dependencies updated. * **CSP headers.** Content Security Policy to prevent XSS. * **No exposed source maps.** In production builds. **Modern Standards:** * **No deprecated APIs.** Replace `document.write`, synchronous XHR, etc. * **Valid doctype.** Use ``. * **Charset declared.** `` as first element in ``. * **No browser errors.** Clean console. No CORS issues. **UX Patterns:** * **No intrusive interstitials.** Especially on mobile. * **Clear permission requests.** Only ask when needed, with context. * **No misleading buttons.** Buttons do what they say. ### Agentic browsing Use the Lighthouse Agentic Browsing results as technical signals for how well assistants can understand and interact with the rendered page. * **Accessible interaction surface.** Semantic HTML, labels, names, roles, and states must expose meaningful controls in the accessibility tree. * **WebMCP integrations are valid when present.** Review registered tools, schemas, and form coverage; do not add WebMCP solely to raise an audit score. * **`llms.txt` is optional.** A valid file may help compatible tools discover curated content, but a Lighthouse pass does not prove that search or AI products will ingest, rank, or cite it. * **Keep this category separate from SEO claims.** Agentic browsability is not evidence of search ranking or AI visibility. ## Severity levels | Level | Description | Action | |-------|-------------|--------| | **Critical** | Security vulnerabilities, complete failures | Fix immediately | | **High** | Core Web Vitals failures, major a11y barriers | Fix before launch | | **Medium** | Performance opportunities, SEO improvements | Fix within sprint | | **Low** | Minor optimizations, code quality | Fix when convenient | ## Audit output format When performing an audit, structure findings as: ```markdown ## Audit results ### Evidence | Signal | Scope/conditions | Result | Source | |--------|------------------|--------|--------| | LCP | URL, phone, p75/28 days | 3.1s (needs improvement) | CrUX | | Accessibility | URL, mobile navigation | 92 | Lighthouse | ### Critical issues (X found) - **[Category]** Issue description. File: `path/to/file.js:123` - **Impact:** Why this matters - **Evidence:** Measured failure, runtime observation, or source hypothesis - **Fix:** Specific code change or recommendation ### High priority (X found) ... ### Summary - Performance: measured status and X findings - Accessibility: automated status, X findings, manual checks pending/passed - SEO: X findings - Best Practices: X findings - Agentic Browsing: X findings or not available ### Recommended priority 1. First fix this because... 2. Then address... 3. Finally optimize... ### Verification - Re-run results under the same conditions - Manual checks completed - Field validation still pending ``` ## Quick checklist ### Before every deploy - [ ] Core Web Vitals passing - [ ] No accessibility errors (axe/Lighthouse) - [ ] No console errors - [ ] HTTPS working - [ ] Meta tags present ### Weekly review - [ ] Check Search Console for issues - [ ] Review Core Web Vitals trends - [ ] Update dependencies - [ ] Test with screen reader ### Monthly deep dive - [ ] Full Lighthouse audit - [ ] Performance profiling - [ ] Accessibility audit with real users - [ ] SEO keyword review ## References For detailed guidelines on specific areas: - [Performance Optimization](../performance/SKILL.md) - [Core Web Vitals](../core-web-vitals/SKILL.md) - [Accessibility](../accessibility/SKILL.md) - [SEO](../seo/SKILL.md) - [Best Practices](../best-practices/SKILL.md)

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…