
SEO Audit Skill
Skill输入网址即生成单页 SEO 体检报告(HTML):检查标题与描述、H1、robots、sitemap、结构化数据等,并列出优先修复项。需本机 Python;完整版审计还要 Google PageSpeed API Key。提供中文文档。
seo-audit-skill
English · 中文 · SEO Audit Agent Skill
Reusable Agent Skills for single-page SEO auditing. Give it a URL — get a structured HTML report with actionable findings.
Built on a Script + LLM two-layer architecture: Python scripts handle deterministic checks (HTTP status, XML parsing, string matching), while the LLM handles semantic judgment (keyword intent, content quality, page type inference). Works with Claude Code, Cursor, and any agent runtime that supports SKILL.md.
Best practices
- Run
npx skills add JeffLi1993/seo-audit-skill, then audit your page (for example:audit this page: https://example.com). Open the report atreports/<hostname>-audit.htmland review it yourself: keep what matters for your goals, skip what does not. - Share the report (or the key sections) with Cursor or Claude Code and have the assistant work through the findings and fixes item by item.
Report Output
Each basic audit produces a standalone HTML report saved to reports/<hostname>-audit.html.
Full audits save to reports/<hostname>-full-audit.html.
| Section | What you get |
|---|---|
| Audit Summary | One-line verdict + critical / warnings / passing at a glance |
| Site Checks | Sitemap URL Inventory · Crawlability · URL Canonicalization · i18n · Schema · E-E-A-T |
| Page Speed | Full only — Lighthouse scores, lab metrics, final URL, screenshot availability |
| Page Checks | TDK · H1 · Headings · Word Count · Internal Links · Social Tags |
| Priority Actions | Top 3 highest-impact fixes, ranked |
| Insight Walkthrough | Evidence → Impact → Fix for each major finding |
audit this page: https://openclaw.ai
→ ✅ Report saved → reports/openclaw-ai-audit.html
| Website | Audit Summary | Site Checks | Page Checks & insights |
|---|---|---|---|
| colaos.ai | ![]() | ![]() | ![]() |
Skills
| Skill | Tier | When to use |
|---|---|---|
seo-audit | Basic | Default — give it a URL, get a 20+ check structured report |
seo-audit-full | Full | Deep audit with PageSpeed, sitemap inventory, social tags, content quality, GSC data, competitor gap |
seo-audit-fullrequires a Google PageSpeed Insights API key for PageSpeed checks. SetPAGESPEED_API_KEY/GOOGLE_PAGESPEED_API_KEY, or pass--api-key; without a key, the full audit stops and asks you to configure one.
Audit Coverage
Site-level
| Check | What it verifies | Basic | Full |
|---|---|---|---|
| Sitemap URL Inventory | Standalone table of top sitemap directories: URL count, page type, representative example URL | — | ✅ |
| Staging Subdomain Indexation | Detects public test., staging., dev., preview., beta., uat. hosts that mirror production and may be indexable | — | ✅ |
| robots.txt | RFC 9309 group parsing, Allow/Disallow logic, Googlebot status, Sitemap directives | ✅ | ✅ |
| sitemap.xml | Valid XML, URL count, follows Sitemap directive path from robots.txt, samples child sitemap URLs when needed | ✅ | ✅ |
| 404 Handling | True 404 vs soft 404 (200) vs redirect-to-homepage (301) | ✅ | ✅ |
| URL Canonicalization | HTTP→HTTPS redirect, www consistency, trailing slash, canonical tag match | ✅ | ✅ |
| i18n / hreflang | Reciprocal symmetry, BCP 47 codes, x-default, default-language URL duplication, canonical/hreflang alignment | ✅ | ✅ |
| Schema (JSON-LD) | Parseability, @type detection, required/recommended fields, nested fields, type conflicts, localized schema language/URL alignment | ✅ | ✅ |
| E-E-A-T Trust Pages | About / Contact / Privacy / Terms — exists (HTTP 200) + reachable from footer/nav | ✅ | ✅ |
| GSC Crawl Status | Index coverage, crawl errors, blocked resources | — | ✅ |
| PageSpeed / Lighthouse | Performance · Accessibility · Best Practices · SEO scores, lab metrics, final URL, screenshot availability | — | ✅ |
Sitemap URL Inventory is intentionally rendered as its own table before Crawlability:
| Directory | URL Count | Page Type | Example Page |
|---|---|---|---|
/blog/ | 300 | Blog / Content Pages | https://xx.ai/blog/best-ai-video-tools |
/tools/ | 80 | Tool Pages | https://xx.ai/tools/image-generator |
/alternatives/ | 40 | Alternative / Competitor Pages | https://xx.ai/alternatives/synthesia |
Use it as a site-level map, then choose representative URLs from important directories for deeper full audits.
Page-level
| Check | What it verifies | Basic | Full |
|---|---|---|---|
| URL Slug | Lowercase, hyphenated, keyword present, stop word & stuffing detection | ✅ | ✅ |
| Title Tag | 50–60 chars, keyword position, homepage vs inner page rules | ✅ | ✅ |
| Meta Description | 120–160 chars, keyword match, concrete value prop (not generic fluff) | ✅ | ✅ |
| H1 Tag | Single H1, keyword match (full / partial / none), semantic intent review | ✅ | ✅ |
| Canonical Tag | Self-referencing, matches final URL after redirects | ✅ | ✅ |
| Image Alt Text | Alt attribute check on all <img>, JS-render detection | ✅ | ✅ |
| Word Count | Body text ≥ 500 words, thin content flag | ✅ | ✅ |
| Keyword Placement | Primary keyword within first 100 body words | ✅ | ✅ |
| Heading Structure | H2 count (target 5–7), H3/H2 ratio, keyword distribution in H2s | ✅ | ✅ |
| Internal Links | Same-origin links (excl. nav/footer), equity distribution | ✅ | ✅ |
| OG / Social Tags | og:image, twitter:card, social preview completeness | — | ✅ |
| Content Quality | E-E-A-T depth, readability, specificity vs competitors | — | ✅ |
| Robots Meta | noindex, nofollow, max-snippet directives | — | ✅ |
Structure
seo-audit-skill/
├── seo-audit/
│ ├── SKILL.md # Skill definition + agent workflow
│ ├── references/REFERENCE.md # Field definitions, edge cases
│ ├── assets/report-template.html # HTML output template
│ └── scripts/
│ ├── check-site.py # robots.txt + sitemap → JSON
│ ├── check-page.py # TDK + H1 + canonical + slug → JSON
│ ├── check-schema.py # JSON-LD extraction + validation → JSON
│ └── fetch-page.py # Raw HTML fetcher, SSRF protection
└── seo-audit-full/
├── SKILL.md
├── references/REFERENCE.md
├── assets/report-template.html
└── scripts/
├── check-site.py # staging + sitemap inventory + robots/sitemap → JSON
├── check-pagespeed.py # PageSpeed Insights / Lighthouse → JSON
├── check-social.py # OG + Twitter Card validation → JSON
└── check-schema.py # JSON-LD quality + localized schema validation → JSON
Architecture: Script + LLM
URL
│
▼
┌──────────────────────────────────────────────────┐
│ Layer 1 · Python Scripts │
│ Deterministic checks → structured JSON │
│ │
│ check-site.py sitemap inventory, staging │
│ check-page.py H1 / title / meta / canonical│
│ check-schema.py JSON-LD fields + localization│
│ fetch-page.py raw HTML + SSRF protection │
└───────────────────────┬──────────────────────────┘
│ JSON + llm_review_required flag
▼
┌──────────────────────────────────────────────────┐
│ Layer 2 · LLM Agent │
│ Semantic judgment on flagged fields only │
│ │
│ · Keyword intent alignment (H1 / title) │
│ · Meta description quality & specificity │
│ · Page type → expected Schema @type mapping │
│ · E-E-A-T trust page reachability (footer/nav) │
│ · Content analysis (word count, heading, links) │
└───────────────────────┬──────────────────────────┘
│
▼
report-template.html
→ reports/<hostname>-audit.html
Why two layers? Scripts handle the 80% of checks that are deterministic — does robots.txt exist? Is the title 55 characters? The LLM handles the 20% that require understanding — does this H1 semantically cover the intent of "AI workflow automation"? The llm_review_required flag ensures the LLM only intervenes when the script explicitly cannot make the call. No hallucination on factual checks, no blind spots on semantic ones.
Installation
Option 1: CLI (Recommended)
npx skills add JeffLi1993/seo-audit-skill
# Or install a specific tier
npx skills add JeffLi1993/seo-audit-skill --skill seo-audit
npx skills add JeffLi1993/seo-audit-skill --skill seo-audit-full
Option 2: Claude Code Plugin
/plugin marketplace add JeffLi1993/seo-audit-skill
/plugin install seo-audit-skill
Usage
audit this page: https://example.com
Scripts
All scripts output structured JSON to stdout. Exit code 0 = pass/warn, 1 = any fail.
| Script | What it does |
|---|---|
check-site.py | robots.txt + sitemap + sitemap inventory — RFC 9309 parsing, staging subdomain checks, top directory grouping |
check-page.py | H1 / title / meta / canonical / URL slug — keyword match with stop-word-aware filter |
check-schema.py | JSON-LD extraction, @graph flattening, @type + required field validation, localized schema alignment |
fetch-page.py | Raw HTML fetch — SSRF protection, redirect chain tracking, Googlebot UA option |
check-pagespeed.py | Full only — PageSpeed Insights / Lighthouse scores and lab metrics; requires API key |
check-social.py | Full only — OG tags + Twitter Card validation |
Dependency: pip install requests
License
MIT
相關資源

SEO Audit
Skill诊断网站 SEO 问题:检查抓取与索引、Core Web Vitals、元信息和页面内容,按优先级给出可执行的修复建议。出自 marketingskills 合集。
coreyhaines31/marketingskills61.4k
Claude SEO
SkillSEO 分析技能包:26 个子技能配合 19 个子代理并行做全站审计,覆盖技术 SEO、内容质量(E-E-A-T)、Schema、AI 搜索优化(GEO)与本地 SEO。完整功能需按插件安装并运行 /seo setup。
AgriciDaniel/claude-seo31k
Webflow MCP Server
MCPWebflow 官方 MCP:用对话管理 Webflow 网站的页面、CMS 内容和博客文章,配合设计器里的 MCP Bridge App 还能直接改页面元素与样式,适合设计师和市场人员维护官网、落地页。需要 Webflow 账号和 Node.js 22.3 以上,首次连接会弹出网页授权要使用的站点。
webflow/mcp-server142
Landing Page Design
Skill构建或修改落地页时分两部分工作:先收集目标、受众与证明材料,确定页面结构、版式、转化文案与 SEO;再遵循一套严格的视觉规则,规定字体、Tailwind 字号阶梯、间距、圆角、背景、图标与动效。规则偏主观,例如禁用 Inter 字体与背景渐变。
elayadesign/ai-design-skills16.1k
Lighthouse
CLIGoogle Chrome 团队官方的网页审计工具,命令行即可对页面跑性能、无障碍、最佳实践与 SEO 评分,输出 HTML / JSON / CSV 报告,便于 agent 循环优化网页。需要 Node 22+ 与 Chrome。
GoogleChrome/lighthouse31.2k
GEO-SEO Claude
Skill面向 AI 搜索的网站优化技能:检查网站能否被 ChatGPT、Perplexity、Google AI 概览等引用,覆盖 AI 爬虫访问、llms.txt、结构化数据、内容 E-E-A-T 与传统技术 SEO,并生成给客户的报告。PDF 报告与评分脚本需改用 README 的一键安装脚本安装,要求本机 Python 3.8+ 与 Git。
zubair-trabzada/geo-seo-claude11.8k


