AI visibility skill
Measure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they cite — from actual GA4 referral data, not prompt sampling.
by Ryze-AI-Adgent·MIT license·★ 3,135 Stars on the repo·GitHub ↗
npx degit Ryze-AI-Adgent/open-seo-mcp-skills/skills/ai-visibility#main ~/.claude/skills/ai-visibilityChecked ·commit main
Files of AI visibility
Show the full text30 lines
AI Visibility
Requires
The free Ryze MCP connector (https://connector.get-ryze.ai/mcp). Claude Code: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp. claude.ai / Desktop / Cursor: add it as a custom connector with the same URL. Setup: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp
Every "AI visibility tracker" samples prompts and guesses. GA4 records the actual clicks AI engines send. Measure the real thing first, then diagnose.
Workflow
- Traffic by engine.
google_analytics__getAiTrafficByEngine— sessions per AI source (ChatGPT, Perplexity, Gemini, Claude, Copilot…), current vs previous period. - Trend.
google_analytics__getAiTrafficDaily— is AI traffic growing, and did anything spike (a spike = something started citing you; find it). - Cited pages.
google_analytics__getAiLandingPages— which URLs AI engines actually send people to. These are your proven-citable pages. - Referral detail.
google_analytics__getAIReferralsfor source-level detail and conversions — is AI traffic converting better or worse than organic. - Diagnose the winners. Read the top 2–3 cited pages (fetch them). Note the pattern: direct answers high on the page, stats/definitions, clean headings, schema. That pattern is the citation recipe for this site.
- Find the misses. Cross-reference with
google_search_console__runRawSearchAnalytics: pages with strong organic queries but zero AI referrals — candidates to restructure toward the citation recipe from step 5.
Output
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.
Fallback
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).
| 1 | |
| 2 | name ai-visibility |
| 3 | description 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". |
| 4 | |
| 5 | |
| 6 | # AI Visibility |
| 7 | |
| 8 | ## Requires |
| 9 | |
| 10 | The free Ryze MCP connector (`https://connector.get-ryze.ai/mcp`). Claude Code: `claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp`. claude.ai / Desktop / Cursor: add it as a custom connector with the same URL. Setup: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp |
| 11 | |
| 12 | Every "AI visibility tracker" samples prompts and guesses. GA4 records the actual clicks AI engines send. Measure the real thing first, then diagnose. |
| 13 | |
| 14 | ## Workflow |
| 15 | |
| 16 | **Traffic by engine.** `google_analytics__getAiTrafficByEngine` — sessions per AI source (ChatGPT, Perplexity, Gemini, Claude, Copilot…), current vs previous period. |
| 17 | **Trend.** `google_analytics__getAiTrafficDaily` — is AI traffic growing, and did anything spike (a spike = something started citing you; find it). |
| 18 | **Cited pages.** `google_analytics__getAiLandingPages` — which URLs AI engines actually send people to. These are your proven-citable pages. |
| 19 | **Referral detail.** `google_analytics__getAIReferrals` for source-level detail and conversions — is AI traffic converting better or worse than organic. |
| 20 | **Diagnose the winners.** Read the top 2–3 cited pages (fetch them). Note the pattern: direct answers high on the page, stats/definitions, clean headings, schema. That pattern is the citation recipe for this site. |
| 21 | **Find the misses.** Cross-reference with `google_search_console__runRawSearchAnalytics`: pages with strong organic queries but zero AI referrals — candidates to restructure toward the citation recipe from step 5. |
| 22 | |
| 23 | ## Output |
| 24 | |
| 25 | 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. |
| 26 | |
| 27 | ## Fallback |
| 28 | |
| 29 | 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). |
| 30 |
Discussion
Alternatives
Browse more free Claude skills or everything in Marketing.