Clustova AI Readiness Inspector

Inspect llms.txt, Markdown pages, ACP, UCP, robots.txt, and sitemap readiness on the website you are viewing.

See what AI systems can publicly discover on any website with one click. Clustova AI Readiness Inspector is a privacy-first technical audit for the page currently open in Chrome. It checks public discovery files, machine-readable page representations, crawler policies, and agentic-commerce signals. Results include observable evidence, confidence-aware statuses, limitations, and practical remediation guidance. AI crawler analysis: - Evaluate robots.txt rules for the current page path—not just whether robots.txt exists. - Separate search discovery, model training, dataset collection, and user-triggered retrieval policies. - Review OpenAI OAI-SearchBot, GPTBot, and ChatGPT-User. - Review Googlebot and Google-Extended. - Review Microsoft Bingbot for Bing Search and Copilot discovery. - Review Anthropic ClaudeBot and Claude-User. - Review PerplexityBot and Perplexity-User. - Review Common Crawl CCBot. - Show transparent “not documented” labels where Qwen or DeepSeek lack a confirmed first-party crawler identity. - Detect specific-agent overrides, conflicting Allow/Disallow rules, and page-path restrictions. Website readiness checks: - Find the most relevant root or path-scoped llms.txt file. - Validate llms.txt structure and sample resource links. - Check the optional llms-full.txt convention without treating it as mandatory. - Detect advertised or conventional Markdown versions of the current page. - Review Markdown media type, content quality, and HTML conversion structure. - Check XML sitemap and HTTPS availability. - Validate public UCP discovery/profile metadata at /.well-known/ucp. - Identify public ACP product/integration evidence without running a checkout. - Avoid commerce-score penalties on non-commerce websites. - Export the report as Markdown or JSON. - Open detailed findings in Chrome's side panel. - Switch between persistent light and dark display modes. Privacy first: - Runs only after you click the extension. - Uses temporary active-tab access instead of permanent access to every website. - Does not upload page content during the local scan. - Does not create checkout sessions or submit customer/payment data. - Does not sell inspection data or use it for behavioral advertising. Technical results are evidence-based signals, not guarantees of AI ranking, citation, inclusion, eligibility, crawler compliance, or transactions. Robots analysis reflects published policy; it does not prove that a crawler can pass a WAF/CDN, retrieve the page, or render client-side content.