About seo-audit
A website audit skill for site owners and SEO practitioners. It reviews public pages, technical settings, and content structure, then produces a scored report. Connected Cogny MCP adds live data from Google Search Console and Bing Webmaster Tools.
Key features
- 01Check titles, descriptions, and metadata
- 02Review robots.txt, sitemaps, and HTTPS
- 03Analyze content, internal links, and schema
- 04Inspect search presence and competing pages
- 05Use live search tool data when connected
- 06Record actionable findings in Cogny
Use cases
- 01Assess a website’s technical SEO
- 02Review metadata and content on key pages
- 03Use search performance to identify optimizations
MCP support
When connected to Cogny MCP, the skill can use Google Search Console and Bing Webmaster Tools data and record actionable audit findings.
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/seo-auditin Claude Code to confirm it loaded.
Details
From the project READMESEO Audit
Perform a comprehensive SEO analysis of a website. Works with public data out of the box — and uses live Google Search Console and Bing Webmaster Tools data when connected via Cogny MCP.
Usage
/seo-audit example.com — audit the given website
Steps
1. Fetch and analyze the homepage
Use WebFetch to load the target URL. Check:
- Title tag (length, keyword placement)
- Meta description (length, compelling copy)
- H1 tag (single, keyword-rich)
- Open Graph / Twitter Card metadata
- Canonical URL
- Language/hreflang tags
2. Check technical SEO
Use WebFetch to check:
/robots.txt— crawl rules, sitemap reference/sitemap.xml— exists, well-formed, number of URLs- Page load indicators (large images, render-blocking scripts)
- Mobile viewport meta tag
- HTTPS enforcement
3. Analyze content structure
From the homepage content:
- Word count (target: 300+ for ranking pages)
- Header hierarchy (H1 → H2 → H3)
- Internal link count and structure
- Image alt text coverage
- Schema markup (JSON-LD)
4. Check search presence
Use WebSearch to find:
site:example.com— indexed page count- Brand name search — what appears in SERP
- Top ranking pages — what keywords they rank for
- Competitor comparison — who ranks for the same terms
5. Analyze key content pages
WebFetch 3-5 important pages (pricing, features, blog):
- Per-page title/meta/H1 analysis
- Content depth and keyword coverage
- Internal linking to/from homepage
6. Report findings
Present as a scored audit:
SEO Audit: example.com
Score: X/100
Technical: X/25
- [PASS/FAIL] HTTPS
- [PASS/FAIL] Robots.txt
- [PASS/FAIL] Sitemap
- [PASS/FAIL] Mobile viewport
- [PASS/FAIL] Canonical URLs
On-Page: X/25
- [PASS/FAIL] Title tags
- [PASS/FAIL] Meta descriptions
- [PASS/FAIL] H1 structure
- [PASS/FAIL] Image alt text
- [PASS/FAIL] Schema markup
Content: X/25
- [PASS/FAIL] Word count
- [PASS/FAIL] Header hierarchy
- [PASS/FAIL] Internal linking
Search Presence: X/25
- Indexed pages: N
- Brand SERP: [description]
- Top keywords: [list]
Top 3 Actions:
1. [Highest impact fix]
2. [Second highest]
3. [Third highest]
Recording Findings
If the Cogny MCP is connected (mcp__cogny__create_finding available), record each actionable finding:
{
"title": "Missing meta descriptions on 12 pages",
"body": "Pages /pricing, /features, /blog/... lack meta descriptions. Average CTR for pages without descriptions is 30% lower.",
"action_type": "seo_optimization",
"expected_outcome": "Improve CTR by 15-30% on affected pages",
"priority": "high"
}
Deeper Analysis with Live Data
If Cogny MCP is connected, this skill automatically enhances the audit with:
Google Search Console: actual queries, click-through rates, rankings, indexing status Bing Webmaster Tools: Bing traffic, crawl stats, keyword data, backlink analysis
Connect your accounts via Cogny ($9/mo per channel), then re-run the audit for live data.
For ongoing monitoring, use /seo-monitor.