Will ChatGPT, Perplexity, or Claude cite this URL?

A robots.txt block on the search crawler (OAI-SearchBot, PerplexityBot, or Claude-SearchBot), a noindex tag, or server HTML with almost no text. A firewall or CDN bot rule can block them even when robots.txt allows the visit.

Search bots fetch pages so an assistant can answer a question and cite you. Training bots such as GPTBot, ClaudeBot, and Google-Extended collect text for model training. Blocking Google-Extended does not by itself remove you from ChatGPT or Perplexity answers. Blocking OAI-SearchBot does.

Most of them do not. They read the HTML your server sends. A site that ships an empty root div and fills it in the browser looks blank to those crawlers. This checker reports that word count. The Shipcheck extension reads the page after Chrome has rendered it.

No. llms.txt is an optional map of pages you want AI tools to read. It does not override robots.txt, noindex, or thin HTML. Publish it after the search crawlers can already read the page.

Bot protection (often Cloudflare), a WAF, or a login wall answered our server instead of your real page. Visitors can still see the site. Install Shipcheck extension 0.3.9+, then run the check again — we retry by reading the page in your browser. You can also open the URL in Chrome and use the extension side panel.

No. A high score means search crawlers can fetch the URL and the server HTML has something worth quoting. Mentions elsewhere, freshness, and whether the page answers the question still decide citations. Treat this as a launch check, not a ranking promise.