GEO SEO Claude GitHub Tutorial: Install in Claude Code, Audit Websites and Export PDF Reports
Summary
A YouTube walkthrough from Alex Hitt shows how to install GEO SEO Claude, an open source skill by zubair-trabzada that adds generative engine optimization checks to Claude Code. The video covers setup on Windows through Git Bash, on macOS with uv and on Linux with python3-venv, keeping the skill in its own Python environment, and fixing an unknown command error after install.
Once installed, the skill offers three commands: /geo quick for a fast check, /geo audit to send several agents across a site at once, and /geo report-pdf to export the results. The audit looks at AI visibility, technical SEO, content quality and schema markup, then combines them into one GEO score. The video also covers fixing PDF export with Playwright and uninstalling the skill without deleting client data.
Demonstration by Alex Hitt, embedded from YouTube. AIOTruth did not reproduce the test.
Why it matters
Anyone who can run Claude Code can now produce an AI search readiness audit and a client ready PDF for any website. That makes GEO audits cheap and common, and many of the reports in circulation will come from the same scoring logic. The tutorial says plainly that a high GEO score is an estimate, not proof that a site gets cited in AI answers. So a site owner who uses the tool can decide what to fix first, but still has to check live AI answers separately to see whether the changes made the brand easier to find, understand or cite.
Source
- github.com/zubair-trabzada/geo-seo-claude the item itself, published by Alex Hitt, created by Alex Hitt
- github.com/zubair-trabzada/geo-seo-claude/tree/main/docs Public source code or repository, first party
- youtube.com/watch?v=xwK8uy1jqs4where AIOTruth found it
What was checked
- read the item page (200)
- https://github.com/zubair-trabzada/geo-seo-claude/tree/main/docs: supports the item, tier 6 (Public source code or repository)
- https://docs.github.com/en/site-policy/github-terms/github-terms-of-service: does not mention 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/features/copilot: does not mention the item, tier 6 (Public source code or repository)
- https://github.com/features/ai/github-app: does not mention the item, tier 6 (Public source code or repository)
- https://docs.github.com/en: does not mention the item, tier 6 (Public source code or repository)
Limitations
- Everything checked traces back to a single domain, so this is one party's account.
- The demonstration was not independently reproduced by AIOTruth.
AIOTruth judgment
The item scored 8.2 because it sits squarely on the subject AIOTruth covers, which is why relevance is 10. Usefulness is 8 because the video takes a practical workflow from prerequisites all the way to an exported report. Evidence is 7: the Supported status rests on the public repository and its documentation, which confirm the tool exists and does what the video describes, but every source traces back to one party and AIOTruth has not reproduced the audit. Originality is 7 because the value is a clear setup and troubleshooting path for an existing open source project, not a new method.
How this score was calculated
| Dimension | Weight | Score | What produced it |
|---|---|---|---|
| AIO relevance | 30% | 10 | geo, ai visibility, ai search, generative engine optimization, schema markup; 5 scope question(s) matched |
| Usefulness | 30% | 8 | 2 artifact(s), 6 actionable marker(s), 0 measured figure(s) |
| Evidence | 25% | 7 | Public source code or repository; 2 verified source(s) across 1 domain(s) |
| Originality | 15% | 7 | no original testing found; closest archive match 0.074 |
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.
Review the documentation Open the source
Found something wrong here? AIOTruth corrects material errors openly. Have something we should review? Submit a find.