What can Claude Code really do for GEO? 30 skills tested
Summary
GEO Tool Blog examined a list of 30 Claude Code skills marketed for SEO and GEO work and asked whether any of them can prove that a site is cited by ChatGPT or Perplexity. Its conclusion is that the skills do real work on tasks such as technical audits and schema markup, but the citability score shipped by one of them has not been independently validated as a measure of AI citability.
The piece compares what the public repositories promise against what can be checked, and sets that against the original GEO research paper. The companion video discloses that its voices are AI-generated.
Demonstration by GEO Tool Blog, embedded from YouTube. AIOTruth did not reproduce the test.
Why it matters
A score produced inside a coding skill is easy to mistake for a measurement of how AI systems treat a page. If that score has not been validated against real citations in ChatGPT or Perplexity, a brand can raise it and still not know whether it is cited more often. Anyone using these skills to get found or cited by AI should treat them as audit and markup helpers, and confirm citations by checking the answer engines directly.
Source
- geo-tool.com/en/blog/30-claude-code-skills-for-seo-aeo-and-geo the item itself, published by GEO Tool Blog, created by GEO Tool Blog
- arxiv.org/abs/2311.09735 Original dataset with disclosed methods
- github.com/AgriciDaniel/claude-seo Public source code or repository
- github.com/zubair-trabzada/geo-seo-claude Public source code or repository
- github.com/coreyhaines31/marketingskills Public source code or repository
- arxiv.org/abs/2311.09735v1 Original dataset with disclosed methods, first party
- arxiv.org/abs/2311.09735v3 Original dataset with disclosed methods, first party
- youtube.com/watch?v=7crObK9dH3swhere AIOTruth found it
What was checked
- canonical URL taken from the page itself
- read the item page (200)
- https://arxiv.org/abs/2609.07559: does not mention the item, tier 5 (Original dataset with disclosed methods)
- https://arxiv.org/abs/2311.09735: supports the item, tier 5 (Original dataset with disclosed methods)
- https://github.com/AgriciDaniel/claude-seo: supports the item, tier 6 (Public source code or repository)
- https://github.com/zubair-trabzada/geo-seo-claude: supports the item, tier 6 (Public source code or repository)
- https://github.com/coreyhaines31/marketingskills: supports the item, tier 6 (Public source code or repository)
- https://www.geo-tool.com/en/blog/30-claude-code-skills-for-seo-aeo-and-geo: supports the item, tier 8 (Named expert analysis, or a first-party claim about itself)
Limitations
- The demonstration was not independently reproduced by AIOTruth.
AIOTruth judgment
The evidence status is Supported because the repositories and the GEO paper the item relies on were fetched and confirmed to discuss it, which is why evidence scored 10. Relevance scored 9 because the question of whether a citability score reflects real AI citation goes to the center of AI-era discovery. Usefulness scored 8 because the piece separates the tasks the skills handle well from the claim they cannot support. Originality scored 7 because it is a review of other people's tools and research, not new measurement. The demonstration was not independently reproduced by AIOTruth, and the publisher promotes its own GEO product alongside the article.
How this score was calculated
| Dimension | Weight | Score | What produced it |
|---|---|---|---|
| AIO relevance | 30% | 9 | geo, generative engine optimization, aeo, schema markup; 5 scope question(s) matched |
| Usefulness | 30% | 8 | 2 artifact(s), 5 actionable marker(s), 0 measured figure(s) |
| Evidence | 25% | 10 | Original dataset with disclosed methods; 5 verified source(s) across 3 domain(s) |
| Originality | 15% | 7 | no original testing found; closest archive match 0.087 |
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.
Read the source Open the source
Found something wrong here? AIOTruth corrects material errors openly. Have something we should review? Submit a find.