Full Website SEO Audit
Process
- Fetch homepage: use
web_open to open page, then web_seo_audit for baseline
- Detect business type: analyze homepage signals per seo orchestrator
- Crawl site: use
web_open + web_read_html to navigate key pages, respect robots.txt
- Delegate to subagents (if available, otherwise run inline sequentially):
seo-technical -- robots.txt, sitemaps, canonicals, Core Web Vitals, security headers
seo-content -- E-E-A-T, readability, thin content, AI citation readiness
seo-schema -- detection, validation, generation recommendations
seo-sitemap -- structure analysis, quality gates, missing pages
seo-performance -- LCP, INP, CLS measurements
seo-visual -- screenshots, mobile testing, above-fold analysis
seo-geo -- AI crawler access, llms.txt, citability, brand mention signals
seo-local -- GBP signals, NAP consistency, reviews, local schema, industry-specific local factors (spawn when Local Service industry detected: brick-and-mortar, SAB, or hybrid business type)
- Score -- aggregate into SEO Health Score (0-100)
- Report -- generate prioritized action plan
Crawl Configuration
Max pages: 500
Respect robots.txt: Yes
Follow redirects: Yes (max 3 hops)
Timeout per page: 30 seconds
Concurrent requests: 5
Delay between requests: 1 second
Output Files
FULL-AUDIT-REPORT.md: Comprehensive findings
ACTION-PLAN.md: Prioritized recommendations (Critical > High > Medium > Low)
screenshots/: Desktop + mobile captures (if Playwright available)
Scoring Weights
| Category |
Weight |
| Technical SEO |
22% |
| Content Quality |
23% |
| On-Page SEO |
20% |
| Schema / Structured Data |
10% |
| Performance (CWV) |
10% |
| AI Search Readiness |
10% |
| Images |
5% |
Report Structure
Executive Summary
- Overall SEO Health Score (0-100)
- Business type detected
- Top 5 critical issues
- Top 5 quick wins
Technical SEO
- Crawlability issues
- Indexability problems
- Security concerns
- Core Web Vitals status
Content Quality
- E-E-A-T assessment
- Thin content pages
- Duplicate content issues
- Readability scores
On-Page SEO
- Title tag issues
- Meta description problems
- Heading structure
- Internal linking gaps
Schema & Structured Data
- Current implementation
- Validation errors
- Missing opportunities
Performance
- LCP, INP, CLS scores
- Resource optimization needs
- Third-party script impact
Images
- Missing alt text
- Oversized images
- Format recommendations
AI Search Readiness
- Citability score
- Structural improvements
- Authority signals
Priority Definitions
- Critical: Blocks indexing or causes penalties (fix immediately)
- High: Significantly impacts rankings (fix within 1 week)
- Medium: Optimization opportunity (fix within 1 month)
- Low: Nice to have (backlog)
DataForSEO Integration (Optional)
If DataForSEO MCP tools are available, spawn the seo-dataforseo agent alongside existing subagents to enrich the audit with live data: real SERP positions, backlink profiles with spam scores, on-page analysis (Lighthouse), business listings, and AI visibility checks (ChatGPT scraper, LLM mentions).
Error Handling
| Scenario |
Action |
| URL unreachable (DNS failure, connection refused) |
Report the error clearly. Do not guess site content. Suggest the user verify the URL and try again. |
| robots.txt blocks crawling |
Report which paths are blocked. Analyze only accessible pages and note the limitation in the report. |
| Rate limiting (429 responses) |
Back off and reduce concurrent requests. Report partial results with a note on which sections could not be completed. |
| Timeout on large sites (500+ pages) |
Cap the crawl at the timeout limit. Report findings for pages crawled and estimate total site scope. |
1---2name: seo-audit3description: >4 Full website SEO audit with parallel subagent delegation. Crawls up to 5005 pages, detects business type, delegates to 7 specialists, generates health6 score. Use when user says "audit", "full SEO check", "analyze my site",7 or "website health check".8user-invokable: true9argument-hint: "[url]"10allowed-tools:11 - web_open12 - web_read_text13 - web_read_html14 - web_seo_audit15 - web_exec_js16 - web_click17 - web_type_input18 - web_press_key19 - term_run_command20metadata:21 source: https://skillmd.com/skills/mits-pl/seo-audit22---2324# Full Website SEO Audit2526## Process27281. **Fetch homepage**: use `web_open` to open page, then `web_seo_audit` for baseline292. **Detect business type**: analyze homepage signals per seo orchestrator303. **Crawl site**: use `web_open` + `web_read_html` to navigate key pages, respect robots.txt314. **Delegate to subagents** (if available, otherwise run inline sequentially):32 - `seo-technical` -- robots.txt, sitemaps, canonicals, Core Web Vitals, security headers33 - `seo-content` -- E-E-A-T, readability, thin content, AI citation readiness34 - `seo-schema` -- detection, validation, generation recommendations35 - `seo-sitemap` -- structure analysis, quality gates, missing pages36 - `seo-performance` -- LCP, INP, CLS measurements37 - `seo-visual` -- screenshots, mobile testing, above-fold analysis38 - `seo-geo` -- AI crawler access, llms.txt, citability, brand mention signals39 - `seo-local` -- GBP signals, NAP consistency, reviews, local schema, industry-specific local factors (spawn when Local Service industry detected: brick-and-mortar, SAB, or hybrid business type)405. **Score** -- aggregate into SEO Health Score (0-100)416. **Report** -- generate prioritized action plan4243## Crawl Configuration4445```46Max pages: 50047Respect robots.txt: Yes48Follow redirects: Yes (max 3 hops)49Timeout per page: 30 seconds50Concurrent requests: 551Delay between requests: 1 second52```5354## Output Files5556- `FULL-AUDIT-REPORT.md`: Comprehensive findings57- `ACTION-PLAN.md`: Prioritized recommendations (Critical > High > Medium > Low)58- `screenshots/`: Desktop + mobile captures (if Playwright available)5960## Scoring Weights6162| Category | Weight |63|----------|--------|64| Technical SEO | 22% |65| Content Quality | 23% |66| On-Page SEO | 20% |67| Schema / Structured Data | 10% |68| Performance (CWV) | 10% |69| AI Search Readiness | 10% |70| Images | 5% |7172## Report Structure7374### Executive Summary75- Overall SEO Health Score (0-100)76- Business type detected77- Top 5 critical issues78- Top 5 quick wins7980### Technical SEO81- Crawlability issues82- Indexability problems83- Security concerns84- Core Web Vitals status8586### Content Quality87- E-E-A-T assessment88- Thin content pages89- Duplicate content issues90- Readability scores9192### On-Page SEO93- Title tag issues94- Meta description problems95- Heading structure96- Internal linking gaps9798### Schema & Structured Data99- Current implementation100- Validation errors101- Missing opportunities102103### Performance104- LCP, INP, CLS scores105- Resource optimization needs106- Third-party script impact107108### Images109- Missing alt text110- Oversized images111- Format recommendations112113### AI Search Readiness114- Citability score115- Structural improvements116- Authority signals117118## Priority Definitions119120- **Critical**: Blocks indexing or causes penalties (fix immediately)121- **High**: Significantly impacts rankings (fix within 1 week)122- **Medium**: Optimization opportunity (fix within 1 month)123- **Low**: Nice to have (backlog)124125## DataForSEO Integration (Optional)126127If DataForSEO MCP tools are available, spawn the `seo-dataforseo` agent alongside existing subagents to enrich the audit with live data: real SERP positions, backlink profiles with spam scores, on-page analysis (Lighthouse), business listings, and AI visibility checks (ChatGPT scraper, LLM mentions).128129## Error Handling130131| Scenario | Action |132|----------|--------|133| URL unreachable (DNS failure, connection refused) | Report the error clearly. Do not guess site content. Suggest the user verify the URL and try again. |134| robots.txt blocks crawling | Report which paths are blocked. Analyze only accessible pages and note the limitation in the report. |135| Rate limiting (429 responses) | Back off and reduce concurrent requests. Report partial results with a note on which sections could not be completed. |136| Timeout on large sites (500+ pages) | Cap the crawl at the timeout limit. Report findings for pages crawled and estimate total site scope. |