AI Visibility reads the AI referral reports in Google Analytics 4 and reports how many sessions each AI engine sends, how that changed against the previous period, and which landing pages receive the visits. It works from recorded clicks, so the numbers are real traffic.
After the measurement it reads the two or three most cited pages, describes the pattern they share, and cross-checks Search Console for pages that rank well but receive no AI visits. The result is a short list of pages to restructure, with the exact change for each.
What You Get
- A verdict on AI traffic share of organic, its trend and the top engine
- An engine table and a cited-pages table with conversions
- The citation pattern seen on your winning pages
- A top-five list of pages to restructure, each with the exact change
Common Use Cases
- Checking whether ChatGPT, Perplexity, Claude or Gemini send visitors to a site
- Finding out which pages AI engines cite and why
- Planning GEO or AEO content changes from measured data
- Spotting a spike that shows something started citing the site
What Makes It Unique
Most AI visibility trackers sample prompts and estimate. This skill starts from the clicks GA4 recorded, then ties them to the pages that earned them and to Search Console queries. It also carries a fallback report built from a raw GA4 query filtered on known AI referrer domains, so it still works when the dedicated AI tools are missing from the workspace.
Under The Hood
The skill is a single instruction file with no scripts. It tells the agent to call tools on the Ryze MCP connector, which reads your Google Analytics 4 and Search Console accounts over the network. It also tells the agent to fetch the two or three top cited pages from the web to read their structure. Its setup note names a shell command for adding the connector to Claude Code; the skill itself writes no files. It needs the Ryze connector added first and your Google accounts connected through it.