Measure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they cite — from actual GA4 referral data, not prompt sampling. Use when asked "AI visibility", "GEO/AEO check", "do LLMs cite us", "traffic from ChatGPT", or "how do we show up in AI search".
npx skills add https://github.com/Ryze-AI-Adgent/open-seo-mcp-skills --skill ai-visibility
Every "AI visibility tracker" samples prompts and guesses. GA4 records the actual clicks AI engines send. Measure the real thing first, then diagnose.
google_analytics__getAiTrafficByEngine — sessions per AI source (ChatGPT, Perplexity, Gemini, Claude, Copilot…), current vs previous period.google_analytics__getAiTrafficDaily — is AI traffic growing, and did anything spike (a spike = something started citing you; find it).google_analytics__getAiLandingPages — which URLs AI engines actually send people to. These are your proven-citable pages.google_analytics__getAIReferrals for source-level detail and conversions — is AI traffic converting better or worse than organic.google_search_console__runRawSearchAnalytics: pages with strong organic queries but zero AI referrals — candidates to restructure toward the citation recipe from step 5.Verdict (AI traffic share of organic, trend, top engine), then: engine table, cited-pages table with conversions, the citation recipe observed on winning pages, and a top-5 list of pages to restructure. Keep it concrete — name the pages and the exact change.
If the GA4 AI-traffic tools aren't available in the workspace, build the same report with google_analytics__runRawReport filtered on sessionSource matching known AI referrers (chatgpt.com, perplexity.ai, gemini.google.com, claude.ai, copilot.microsoft.com).
Take ryze-ai-adgent/ai-visibility from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.