Claude Code Just Ran a Full AI On-Page Audit (Copy My Exact Setup)
Summary
A YouTube video from Total Authority walks through installing a free Claude Code skill that runs SEO, GEO and AEO audits, then points it at a MedSpa site and reads out the resulting scores. The walkthrough covers what the traditional SEO portion catches, where the GEO analysis falls short, and where the AEO section misreads the page. Along the way it lists the signals the presenter argues AI search weighs: factual consistency, named expert credentials, transparent pricing, third-party citations, and whether AI crawlers can reach the site at all.
The skill itself is real and inspectable. Its source lives in a public GitHub repository, SNLabat/SEO-GEO-AEO-Skill, and the landing page at claudeseoskill.com describes the same behavior: give it a URL, it crawls homepage, About, Services and Blog pages, scores across SEO, GEO and AEO dimensions, and produces a downloadable report. The publisher also sells a paid visibility audit and runs a free gap calculator, both linked from the video.
Demonstration by Total Authority, embedded from YouTube. AIOTruth did not reproduce the test.
Why it matters
Most audit tooling still grades a page against ranking criteria, while the thing that decides whether an assistant cites you is whether your claims are stable, attributable, and reachable. A free, open source skill that scores those separately gives anyone a cheap first pass at finding the gaps: an About page with no named practitioner, pricing hidden behind a contact form, no outside source that repeats what you say about yourself, or a robots file that quietly excludes AI crawlers. Those are the failures that keep a brand out of an answer entirely rather than merely lower in a list, and they are fixable once you can see them.
Source
- claudeseoskill.com/ the item itself, published by Total Authority, created by Total Authority
- github.com/SNLabat/SEO-GEO-AEO-Skill Public source code or repository
- totalauthority.com/llm-visibility-audit Reputable reporting
- totalauthority.com/llm-visibility-gap-calculator Reputable reporting
- youtube.com/watch?v=GxlQBGrxajQwhere AIOTruth found it
What was checked
- canonical URL taken from the page itself
- read the item page (200)
- https://github.com/SNLabat/SEO-GEO-AEO-Skill: supports the item, tier 6 (Public source code or repository)
- https://www.claudeseoskill.com/: supports the item, tier 8 (Named expert analysis, or a first-party claim about itself)
- https://totalauthority.com/llm-visibility-audit: supports the item, tier 9 (Reputable reporting)
- https://totalauthority.com/llm-visibility-gap-calculator: supports the item, tier 9 (Reputable reporting)
Limitations
- The demonstration was not independently reproduced by AIOTruth.
AIOTruth judgment
The item scores well on evidence because the underlying tool is verifiable: the code is public on GitHub and the vendor page states the same capability the video shows, which supports the Supported status and the evidence score of 9. Relevance is high at 8 since AI-crawler access, entity clarity and third-party corroboration are exactly the mechanics of AI-era discovery. Usefulness lands at 7 because the setup is genuinely copyable but the audit output is presenter-narrated rather than benchmarked, and the video sits alongside two of the publisher's own commercial offers. Originality is 5: a Claude skill wrapping a scoring rubric is a familiar pattern, and the video is a demonstration rather than new research. AIOTruth did not reproduce the audit run.
How this score was calculated
| Dimension | Weight | Score | What produced it |
|---|---|---|---|
| AIO relevance | 30% | 8 | ai visibility, ai search, geo, aeo, llm visibility; 6 scope question(s) matched |
| Usefulness | 30% | 7 | 1 artifact(s), 4 actionable marker(s), 0 measured figure(s) |
| Evidence | 25% | 9 | Public source code or repository; 4 verified source(s) across 3 domain(s) |
| Originality | 15% | 5 | no original testing found; closest archive match 0 |
aioRelevance x 0.30 + usefulness x 0.30 + evidence x 0.25 + originality x 0.15. The rubric is published in full on the Editorial Method page. Scoring is deterministic: the same item scores the same on every run.
Watch the demonstration Open the source
Found something wrong here? AIOTruth corrects material errors openly. Have something we should review? Submit a find.