seo-content

Content & GEO

Analyze content quality, E-E-A-T signals, and Generative Engine Optimization (GEO) readiness — how likely an LLM answer engine (AI Overview, ChatGPT, Perplexity, Gemini) is to cite the page.

Procedure

1. Fetch and parse the page, then run the content audit:

   from seo_kit.crawler.page_fetcher import fetch_page, parse_html
   from seo_kit.content.analyzer import run_content_audit
   
   _, html, _, _ = fetch_page("<url>")
   page = parse_html(html, "<url>")
   result = run_content_audit(page)
   print(result.to_dict())
   

2. Run the GEO / AI-search readiness check:

   python -m seo_kit.content.geo "<url>"
   

   or from Python:

   from seo_kit.content.geo import run_geo_check
   print(run_geo_check(page).to_dict())
   

3. Summarize and propose rewrites:

   • Weak heading hierarchy → outline new H2/H3 sections.
   • Thin content → expand with data-backed subsections.
   • Low readability → shorten sentences.
   • Weak E-E-A-T → add author byline, publish date, sources.
   • Low GEO score → add Q&A framing, statistics, and citations.

What it checks (content)

• Word count and depth
• Heading hierarchy (skipped levels, first-heading-is-H1)
• Flesch Reading Ease
• Keyword density / stuffing detection
• E-E-A-T signals (author, dates, canonical, structured data)
• Long-word ratio

What it checks (GEO)

• Question-framed statements (LLM engines love Q&A structure)
• Verifiable claims and citation phrases
• Numeric / data density
• Entity signals (author, dates, schema)
• Word-count floor for LLM citation

Notes

• Inspired by AgriciDaniel/claude-seo and seranking/seo-skills (both MIT).