seo Skill for Claude: Technical SEO Audit and Fixes
Makes Claude audit and fix technical SEO on your site: crawling, metadata, structured data, mobile and international tags.
- Installs
- 53.3K
- on skills.sh
- Stars
- 3K
- on GitHub
- Files
- 1
- besides SKILL.md
- Updated
- Aug 2026
- last repo commit
Ask Claude to improve SEO, fix meta tags, add structured data or optimize your sitemap, and this skill gives it a checklist based on Lighthouse SEO audits and Google Search guidelines. It separates crawl and index problems from content quality, and says not to promise ranking changes.
When a rendered page is available it runs a live Lighthouse check if it can (with Chrome DevTools MCP it uses lighthouse_audit), otherwise Lighthouse CLI output and direct source and HTTP inspection. A structured-data reference file holds JSON-LD examples.
Good for
- Developers and site owners who want a technical SEO check on their pages
- Anyone adding JSON-LD structured data or fixing meta tags and canonicals
- Teams who want AI-crawler rules and llms.txt reviewed without hype
Install seo
Claude Code
- 1
Copy this prompt.
Install the seo skill in Claude Code. Run this command: npx skills add https://github.com/addyosmani/web-quality-skills --skill seo Then check that it loaded and tell me how to use it.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
Requires Node.js.
From its listing on skills.sh. Source.
What's in the skill
When it loads
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".
Sections in SKILL.md
- Evidence-led audit workflow
- Technical SEO
- Crawlability
- XML sitemap
- URL structure
- HTTPS & security
- On-page SEO
- Title tags
- Meta descriptions
- Heading structure
- Image SEO
- Internal linking
- Structured data (JSON-LD)
- Agentic browsing and AI discoverability
- Crawler controls are product-specific
- llms.txt is optional
Key facts
- Author
- addyosmani
- Repository
- addyosmani/web-quality-skills
- License
- MIT
- Installs on skills.sh
- 53,269 (Nov 2, 2026)
- GitHub stars
- 3,022 (Nov 2, 2026)
- Last repo commit
- Aug 24, 2026
- Skill version
- 2.0
What it includes
Runs Lighthouse SEO checks, then inspects headers, redirects, robots.txt and sitemap
Uses Chrome DevTools MCP lighthouse_audit when available, else Lighthouse CLI. Keeps crawl findings apart from content quality and does not invent ranking weights.
Runs code ·
Evidence-led audit workflowrobots.txt, meta robots, canonicals, XML sitemap, URL structure, HTTPS, security headers
Read ·
Technical SEOTitle tags, meta descriptions, heading structure, image SEO, internal linking
Length numbers (50 to 60 characters, 150 to 160) are described as rough linting proxies, not hard limits.
Read ·
On-page SEOReads references/STRUCTURED-DATA.md for Organization, Article, Product, FAQ and Breadcrumb
Says to describe visible content and validate rendered output.
Read ·
Structured data (JSON-LD)Keeps Agentic Browsing, search ranking and AI citation apart; reviews each crawler's rules
Covers OAI-SearchBot, PerplexityBot, Claude-SearchBot, Claude-User and Google-Extended. Calls llms.txt optional and experimental.
Read ·
Agentic browsing and AI discoverabilityViewport, tap targets, font sizes, hreflang tags and the lang attribute
Read ·
Mobile and international SEOCritical, high priority, medium priority and ongoing items
Ends with a tools table: Search Console, PageSpeed Insights, Rich Results Test, Lighthouse CLI, Screaming Frog.
SEO audit checklist
From the official docs
Permissions
Low risk
It may run Lighthouse and request your pages to check headers, robots.txt and sitemaps, and its workflow has it fix the source. Use it on sites you control and review the diff.
What it can do
- Read your data
- Create and change things
- Delete things
- Read-only mode
Watch out for
Its workflow tells it to fix your source
Step 4 of the audit workflow says to fix the source and re-run the same checks, so expect edits to your pages, templates or config. Use a branch and review the diff.
It may fetch your live pages
SKILL.md describes direct HTTP inspection of headers, redirects, robots.txt and sitemaps, and a Lighthouse run. Point it at sites you own or may test.
It can use Search Console data if you give access
The workflow mentions Search Console evidence only when you provide access. Share only what you are comfortable having the model read.
Technical details
| Talks to | The site you ask it to audit |
|---|---|
| Scopes |
|
Questions
What does the seo skill do?
It gives Claude a technical SEO workflow: audit crawlability, metadata, structured data, mobile and international tags, then fix the source and re-run the same checks. It says not to promise rankings.
How do I install the seo skill?
Use the install box above. The skill is SKILL.md plus one structured-data reference file.
Does it need Chrome DevTools MCP or Lighthouse?
It prefers a live Lighthouse run, and names the lighthouse_audit tool from Chrome DevTools MCP. If live tools are unavailable it falls back to Lighthouse CLI output plus direct source and HTTP inspection.
Will it improve my rankings?
SKILL.md says no promises. A Lighthouse SEO score covers a useful subset of technical checks and is not a prediction of rankings, and indexing validation stays pending after a fix.
Is the seo skill safe?
Its workflow tells it to fix the source and re-run the checks, so it edits files in your project: use a branch and review the diff. It may also run Lighthouse and fetch pages you point it at. It bundles no scripts (only a structured-data reference file) and names no API key.
How is it different from the other web-quality skills?
Per the collection's README, seo covers search optimization and crawlability. Its siblings cover performance, core-web-vitals, accessibility, best-practices and an overall web-quality-audit.
Should I add an llms.txt file?
The skill calls llms.txt an experimental proposal, not a cross-vendor standard. It says to add one only when you request it or a documented consumer supports it.
Information
updated Nov 2, 2026
- Repository
- addyosmani/web-quality-skills
- Folder
skills/seo
Sources
Docs, issue trackers and discussions this page is built from.
Show all 4Hide
- seo SKILL.md · github.com
- STRUCTURED-DATA.md · github.com
- web-quality-skills README · github.com
- seo on skills.sh · skills.sh