#204204th of 389 in Skills, plugins and promptsFor finance and business, e-commerce, marketing and sales
geo-seo-claude
Claude Code skill that audits websites for AI search citability and SEO
- Stars
- 11.6k
- License
- MIT
- Last commit
- Oct 2026
- Language
- Python
6,480 on 21 Apr 202611,621 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A set of Claude Code skills and subagents that run GEO (generative engine optimization) audits on a URL through /geo commands. It fetches pages with Python scripts, scores citability, checks robots.txt for 14+ AI crawlers, analyzes or generates llms.txt and JSON-LD schema, and produces a 0-100 composite score. Reports export as markdown or PDF.
Who it is for: SEO practitioners and agencies using Claude Code for AI search audits
Strengths
- Full audit runs 5 parallel subagents and returns a weighted 0-100 GEO score
- Dependencies install into an isolated venv at ~/.claude/skills/geo/.venv, with an uninstall script
- Covers AI crawler access, llms.txt generation and JSON-LD templates in one command set
- Exports client-ready reports in markdown or PDF via ReportLab
Weaknesses
- Requires the Claude Code CLI; not usable standalone
- Installer is piped from curl into bash; Windows needs Git Bash
- Scoring weights and citability heuristics are not validated in the README
- README market statistics are unsourced and it promotes a paid community
What it needs
- no GPU
- Needs Claude Code CLI, Python 3.10+, Git, Playwright (optional), uv (optional)
- Models: Claude (via Claude Code)
Quick answers
Is geo-seo-claude open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |