Seo Audit
Run a full-site SEO health audit with crawls, specialist checks, and a scored action plan before you scale content or paid acquisition.
Overview
seo-audit is an agent skill most often used in Launch (also Ship perf, Grow content) that crawls your site, runs up to 15 specialist SEO checks, and returns a health score with prioritized fixes.
Install
npx skills add https://github.com/agricidaniel/claude-seo --skill seo-auditWhat is this skill?
- Crawls up to 500 internal pages while respecting robots.txt
- Delegates to up to 15 SEO specialists (8 always-on + 7 conditional by business type)
- Covers technical SEO, E-E-A-T content, schema, sitemap quality, Core Web Vitals, and AI-search GEO signals
- Detects business type from homepage signals to route conditional specialists
- Produces a consolidated website health score and prioritized fixes
- Crawls up to 500 pages
- Up to 15 specialist subagents (8 always + 7 conditional)
- Generates a consolidated health score
Adoption & trust: 2.2k installs on skills.sh; 8.5k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know something is wrong with organic traffic or AI citations but you do not have a single prioritized audit across technical, content, schema, and performance signals.
Who is it for?
Solo founders shipping marketing sites, docs, or content products who want one orchestrated audit before SEO or GEO investments.
Skip if: Single-page spot checks only, offline apps with no crawlable site, or teams that already maintain a continuous SEO platform with live rank tracking baked in.
When should I use this skill?
User says audit, full SEO check, analyze my site, or website health check (optional URL argument).
What do I get? / Deliverables
You get a business-type-aware crawl, multi-domain SEO findings, and a health score you can turn into a fix roadmap for metadata, content, and technical changes.
- Business-type detection summary
- Multi-area SEO findings (technical, content, schema, performance, GEO)
- Prioritized health score and remediation themes
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Launch is the canonical shelf because the skill is invoked for site-wide visibility, ranking, and citability checks—not a one-off page tweak during build. SEO subphase fits the orchestrated technical, content, schema, performance, and GEO subagent workflow aimed at organic discovery.
Where it fits
Score a new marketing site before you announce on Product Hunt so titles, schema, and sitemaps are coherent.
Check llms.txt, AI crawler access, and citability signals before pitching AI-native distribution.
After a deploy, re-measure LCP, INP, and CLS as part of the same audit narrative.
Diagnose thin pages and E-E-A-T gaps when blog traffic stops compounding.
How it compares
Use instead of running disconnected Lighthouse, Search Console, and schema validators without a weighted site-wide narrative.
Common Questions / FAQ
Who is seo-audit for?
Indie builders and small teams with a live website who need a structured, multi-area SEO and GEO health review before scaling content or ads.
When should I use seo-audit?
At launch when you want baseline discoverability; after a redesign in Ship when performance and canonicals may have regressed; and in Grow when rankings or AI citations plateau and you need a full diagnostic crawl.
Is seo-audit safe to install?
Review the Security Audits panel on this Prism page and treat crawls as production traffic; the skill fetches live URLs and may invoke multiple analysis steps—confirm scope and rate limits on your domain.
SKILL.md
READMESKILL.md - Seo Audit
MIT License - see repository root LICENSE file for complete terms. Copyright (c) 2026 AgriciDaniel https://github.com/AgriciDaniel/claude-seo --- name: seo-audit description: "Full website SEO audit with parallel subagent delegation. Crawls up to 500 pages, detects business type, delegates to up to 15 specialists (8 always + 7 conditional), generates health score. Use when user says audit, full SEO check, analyze my site, or website health check." user-invokable: true argument-hint: "[url]" license: MIT metadata: author: AgriciDaniel version: "2.0.0" category: seo --- # Full Website SEO Audit ## Process 1. **Fetch homepage**: use `scripts/fetch_page.py` to retrieve HTML 2. **Detect business type**: analyze homepage signals per seo orchestrator 3. **Crawl site**: follow internal links up to 500 pages, respect robots.txt 4. **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) - `seo-maps` -- Geo-grid rank tracking, GBP audit, review intelligence, competitor radius mapping (spawn when Local Service detected AND DataForSEO MCP available) - `seo-google` -- CWV field data (CrUX), URL indexation (GSC), organic traffic (GA4) (spawn when Google API credentials detected via `python scripts/google_auth.py --check`) - `seo-backlinks` -- Backlink profile data: DA/PA, referring domains, anchor text, toxic links (spawn when Moz or Bing API credentials detected via `python scripts/backlinks_auth.py --check`, or always include Common Crawl domain-level metrics) - `seo-cluster` -- Semantic clustering analysis (spawn when content strategy signals detected: blog, pillar pages, topic clusters) - `seo-sxo` -- Search experience analysis: page-type mismatch, user stories, persona scoring (always include in full audits) - `seo-drift` -- Drift analysis: compare against stored baseline (spawn when drift baseline exists for the URL via `python scripts/drift_history.py <url>`) - `seo-ecommerce` -- Product schema, marketplace intelligence (spawn when E-commerce industry detected) 5. **Score** -- aggregate into SEO Health Score (0-100) 6. **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) - **PDF Report** (recommended): Generate a professional A4 PDF using `scripts/google_report.py --type full`. This produces a white-cover enterprise report with TOC, executive summary, charts (Lighthouse gauges, query bars, index donut), metric cards, threshold tables, prioritized recommendations with effort estimates, and implementation roadmap. Always offer PDF generation after completing an audit. ## 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