AI Search Visibility Audit
Audit whether a website can be found, crawled, and cited by AI answer engines such as...
Install
npx skills add davepoon/buildwithclaude --skill ai-search-visibility-audit -g -a claude-code -y- Repository
- davepoon/buildwithclaude3.7k
- Category
- Marketing
- Updated
- 3d ago
- License
- MIT
- Context cost
- Mediumabout 2,268 tokens
- Runs scripts
- No, instructions only
What it does
Audit whether a website can be found, crawled, and cited by AI answer engines such as ChatGPT Search, Perplexity, Google AI Overviews, and Microsoft Copilot. Use when someone asks why their brand is missing from AI answers, whether AI crawlers can read their site, how to get cited by ChatGPT or Perplexity, or asks for a GEO or AEO (generative / answer engine optimization) review. Produces a citation baseline across buyer-intent prompts, a crawler-access check, a citability review of named pages, and a ranked fix list. Not for keyword rank tracking, paid search, or pages behind a login.
AI search visibility audit
Classic SEO asks "do we rank for this keyword". AI answer engines do not rank. They retrieve a handful of sources and synthesize one answer. A site can sit at the top of page one and never be quoted. This skill audits the second thing.
Run the four phases in order. Do not skip Phase 1: without a citation baseline everything after it is speculation.
Scope and limits
- Read only publicly accessible URLs and
robots.txt. - Respect the target site's
robots.txtand terms of service. Do not attempt to bypass authentication, paywalls, rate limits, or access controls. - If a page requires a login, stop and say the audit covers public pages only.
- Audit sites the user is responsible for, or public competitors for comparison. Do not use this to probe a site the user has no relationship with.
Before you start
Collect from the user, asking only for what is missing:
- The domain to audit.
- The category the brand wants to be recommended in, in the user's own words (for example "expense management software for startups").
- Two or three named competitors. If the user does not know, derive them in Phase 1 and confirm before continuing.
Phase 1 - Citation baseline
Build 10 to 15 prompts a real buyer would type. Cover all four intents. A set that is all category queries will overstate visibility.
| Intent | Shape | Example |
|---|---|---|
| Category | "best X for Y" | best expense tools for seed-stage startups |
| Comparison | "A vs B" | Ramp vs Brex for a 30-person team |
| Alternative | "alternatives to A" | alternatives to Expensify |
| Problem | symptom, no brand named | how do I stop chasing receipts from my team |
For each prompt, search the web and record:
