Skip to content
SkillModel-led524 tokens in use

AI Visibility

Measure the traffic ChatGPT, Perplexity, Claude and Gemini send to your site from GA4 referral data, and find which pages they cite.

10,603 stars on the repository MIT LicenseRyze-AI-Adgent/open-seo-mcp-skills · skills/ai-visibility
claude plugin marketplace add Ryze-AI-Adgent/open-seo-mcp-skills /plugin install open-seo-mcp-skills@ryze
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing AI Visibility costs

80tokens idle
524tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure25/25
  • Examples0/15
  • Output5/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Fair
  • Development activity64
  • Maintenance36
  • Community44
  • Maturity16
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers