seo-geolisted

# GEO / AI-Search Readiness Evaluate how likely a page is to be cited by LLM answer engines, and give concrete fixes to improve LLM visibility. ## Procedure 1. **Fetch and parse the page**, then run the GEO check: ```bash python -m seo_kit.content.geo "<url>" ``` or from Python: ```python from seo_kit.crawler.page_fetcher import fetch_page, parse_html from seo_kit.content.geo import run_geo_check _, html, _, _ = fetch_page("<url>") page = parse_html(html, "<url>") result = run_geo_check(page) print(result.to_dict()) ``` 2. **Report the score and findings**, then recommend improvements: - **Question framing** — add Q&A sections phrased as natural queries. - **Verifiable claims** — attribute statistics and cite sources. - **Data density** — use specific numbers, percentages, and dates. - **Entity signals** — author bylines, publish dates, schema markup. - **Depth** — expand past the LLM citation floor (~600+ words). 3. **Offer to draft the rewrite** (e.g., add an FAQ block, rewrite the intro as a direct answer, or insert sourced statistics). ## Notes - Scores 0-100 with findings per signal. - Inspired by [AgriciDaniel/claude-seo](https://github.com/AgriciDaniel/claude-seo) and [seranking/seo-skills](https://github.com/seranking/seo-skills) (both MIT).