Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agricidaniel/seo-geo
Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. Generative Engine Optimization (GEO) analysis including brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization.
Passed 24 of 24 test cases with the skill, and 13 of 24 without it.
and 20 more in the full report
11 fixed13 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/2/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our web ops team wants to block ClaudeBot in robots.txt to stop Anthropic from scraping our site, but we still want Claude's built-in search features to find and cite our articles. How should we configure our robots.txt directives for Anthropic's crawlers?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends disallowing ClaudeBot for model training opt-out | Passed | Passed |
| Recommends allowing Claude-SearchBot for Claude search feature citability | Missed | Passed |
The instructions your model reads when the skill loads.
Google's official position, published under Search Central docs:
"From Google Search's perspective, optimizing for generative AI search is optimizing for the search experience, and thus still SEO."
Read references/google-ai-optimization-guide.md for the full synthesis,
myth-busting list (llms.txt, chunking, AI-rephrasing, mention-farming,
all rejected by Google as ineffective), and the Who/How/Why test for
content quality.
Audits should frame GEO findings as SEO fundamentals applied to AI-search surfaces, not as a separate optimization discipline. When community recommendations contradict Google's primary source, defer to Google and note the contradiction in the report.
Third-party figures below were not re-verified on 2026-09-23. Quote them only with their source and date, or leave them out.
| Metric | Value | Source |
|---|---|---|
| AI Overviews reach | 2.5 billion+ monthly active users, reported from Google I/O 2026 keynote coverage; not confirmed on a Google-owned source; 200+ countries | Third-party I/O reporting |
| AI Overviews query coverage | ~50% of queries (third-party measurement; varies by country) | Industry data |
| AI Mode monthly users | 1B+ (Google, I/O 2026, 2026-05-19) | Google (blog.google) |
| AI Mode model | Google upgrades it often (Gemini 3.5 Flash became the default on 2026-05-19, and newer Flash models have shipped since); never tie advice to a model | Google (blog.google) |
| AI-referred sessions growth | 527% (Jan-May 2025) | Third-party (attributed to SparkToro; not re-verified) |
| ChatGPT weekly active users | 1 billion+ (reported August 2026; 900 million in February 2026) | OpenAI, via press reporting |
| Perplexity monthly queries | 500+ million | Perplexity |
Brand mentions correlate 3x more strongly with AI visibility than backlinks. (Ahrefs study of 75,000 brands, published 2025-12-12; it follows Ahrefs' May 2025 AI Overviews study)
| Signal | Correlation with AI Citations |
test cases passed, vs 13 / 24 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.