geo

GEO-SEO Analysis Tool — Claude Code Skill (February 2026)

Philosophy: GEO-first, SEO-supported. AI search is eating traditional search. This tool optimizes for where traffic is going, not where it was.

Quick Reference

Market Context (Why GEO Matters)

Orchestration Logic

Full Audit (/geo audit <url>)

Phase 1: Discovery (Sequential)

1. Fetch homepage HTML (curl or WebFetch)
2. Detect business type (SaaS, Local, E-commerce, Publisher, Agency, Other)
3. Extract key pages from sitemap.xml or internal links (up to 50 pages)

Phase 2: Parallel Analysis (Delegate to Subagents) Launch these 5 subagents simultaneously:

Phase 3: Synthesis (Sequential)

1. Collect all subagent reports
2. Calculate composite GEO Score (0-100)
3. Generate prioritized action plan
4. Output client-ready report

Scoring Methodology

Business Type Detection

Analyze homepage for patterns:

Adjust recommendations based on detected type. Local businesses need LocalBusiness schema and Google Business Profile optimization. SaaS needs SoftwareApplication schema and comparison page strategy. E-commerce needs Product schema and review aggregation.

Sub-Skills (14 Specialized Components)

Subagents (5 Parallel Workers)

Output Files

All commands generate structured output:

PDF Report Generation

The /geo report-pdf <url> command converts GEO-AUDIT-REPORT.md into a styled, client-ready PDF.

Requirements

• pandoc — brew install pandoc
• Google Chrome — /Applications/Google Chrome.app/ (standard Mac install)

No Python dependencies required for PDF generation.

What the PDF Includes

• Cover page — dark navy gradient, GEO score badge, brand/domain/date/location metadata
• Color-coded score tables — cells with XX/100 values are automatically colored green/blue/amber/orange/red
• Severity-tagged findings — Critical/High/Medium/Low sections get colored left-border callout blocks
• Section page breaks — major sections break to new pages automatically
• Styled code blocks — JSON schema templates render with dark monospace theme

Templates

Bundled at ~/.claude/skills/geo/templates/:

• geo-report-style.css — stylesheet (edit colors, fonts, layout here)
• geo-report-template.html — pandoc HTML template (edit cover fields here)

Workflow

1. Run /geo audit <url> to produce GEO-AUDIT-REPORT.md
2. Run /geo report-pdf — extracts metadata from the report and runs:

   pandoc GEO-AUDIT-REPORT.md \
     --to html5 --standalone --embed-resources \
     --template ~/.claude/skills/geo/templates/geo-report-template.html \
     --css ~/.claude/skills/geo/templates/geo-report-style.css \
     --metadata brand_name="..." --metadata geo_score="..." \
     -o GEO-REPORT.html

   "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
     --headless=new --disable-gpu --no-sandbox \
     --print-to-pdf="$(pwd)/GEO-REPORT.pdf" \
     --print-to-pdf-no-header --no-pdf-header-footer \
     --virtual-time-budget=5000 \
     "file://$(pwd)/GEO-REPORT.html"

1. Output: GEO-REPORT.pdf in the current directory

Quality Gates

• Crawl limit: Max 50 pages per audit (focus on quality over quantity)
• Timeout: 30 seconds per page fetch
• Rate limiting: 1-second delay between requests, max 5 concurrent
• Robots.txt: Always respect, always check
• Duplicate detection: Skip pages with >80% content similarity

Quick Start Examples

# Full GEO audit of a website
/geo audit https://example.com

# Check if AI bots can see your site
/geo crawlers https://example.com

# Score a specific page for AI citability
/geo citability https://example.com/blog/best-article

# Generate an llms.txt file for your site
/geo llmstxt https://example.com

# Get a 60-second visibility snapshot
/geo quick https://example.com

# Generate a client-ready report
/geo report https://example.com