Geo Citability

If you're creating content that needs to show up when people ask ChatGPT or Claude questions, this scores how quotable your writing actually is. It checks whether you lead with direct answers, keep passages self-contained (no pronoun soup), use the 134-167 word sweet spot that AIs prefer to cite, and pack in specific stats with sources. Based on 2024 research showing GEO-optimized content gets 30-115% more AI citations. The rubric is thorough, maybe even rigid, but it's addressing a real problem: most web content is written for humans scrolling, not for extraction by language models. Worth running on any FAQ or documentation you want cited instead of paraphrased.

skills.sh installs: 957
GitHub stars: 11.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add zubair-trabzada/geo-seo-claude --skill geo-citability --agent claude-code

Installs into .claude/skills of the current project.

Files

AI Citability Scoring Skill

Core Insight

AI language models cite passages that meet specific structural criteria. Research from Princeton, Georgia Tech, and IIT Delhi (2024) found that GEO-optimized content achieves 30-115% higher visibility in AI-generated responses. The key finding: AI systems preferentially extract and cite passages that are 134-167 words long, self-contained (understandable without surrounding context), fact-rich (containing specific statistics, dates, or named entities), and directly answer a question in the first 1-2 sentences.

This is fundamentally different from traditional SEO copywriting, which optimizes for keyword density and user engagement metrics. GEO citability optimizes for extractability -- the ease with which an AI system can pull a passage from your content and present it as a direct answer.