agentsclimarketplace
Sign in

Geo audit skill

Skill josezuma/geo-audit-skill

Audits a URL for AI-search (GEO) readiness. Checks llms.txt presence, robots.txt AI-crawler rules, JSON-LD schema.org markup, and citability patterns. Outputs a scored report with prioritized fixes. Use when analyzing a website for Generative Engine Optimization (GEO), AI search visibility, or preparing content for LLM citation.From its SKILL.md

Install
npx -y skills add josezuma/geo-audit-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.8 KB, 573 tokens by cl100k_base, as published. Nobody here has run it

GEO Audit Skill

Audits any URL for AI-search (Generative Engine Optimization) readiness. Runs four checks and produces a scored report with actionable fixes.

Quick Start

# Standalone usage (no agent needed)
pip install requests beautifulsoup4
python scripts/audit.py https://example.com

As an agent skill, this SKILL.md is loaded automatically by agent-compatible systems.

Checks Performed

1. llms.txt Check (25 points)

  • Does the site serve an /llms.txt file?
  • Does /llms-full.txt exist?
  • Are the entries valid per the llmstxt.org spec?

2. robots.txt AI Crawler Check (25 points)

  • Does /robots.txt explicitly allow or block AI crawlers?
  • Are GPTBot, ClaudeBot, PerplexityBot, Google-Extended configured?
  • If blocked, the site won't be cited by those AI models.

3. JSON-LD Schema Check (25 points)

  • Does the page have JSON-LD structured data?
  • Which schema.org types are used (Organization, Article, FAQ, Product, etc.)?
  • Are the schemas valid JSON-LD?
  • AI models heavily weight structured data for extraction and citation.

4. Citability Check (25 points)

  • Does the page contain verifiable statistics, quotes, or definitions?
  • Are there author bylines with real names (EEAT signal)?
  • Is there a publish date?
  • Does the page have external reference links?

Scoring

Scores range 0-100 across the four dimensions above. Results include specific findings and prioritized fixes.

Example Output

GEO Audit Report for https://example.com
==========================================
llms.txt:        ❌ Not found (-25 pts)
robots.txt:      ⚠️ No AI crawler rules (-15 pts)
JSON-LD Schema:  ✅ Organization + Article present (+20 pts)
Citability:      ✅ Author bio, publish date, 3 statistics (+20 pts)
----------------------------------------
TOTAL SCORE:     55/100 — Needs improvement

References

Related

  • [[ai-crawlers]] — AI crawler user-agent dataset
  • [[schema-for-ai]] — Annotated JSON-LD templates
  • [[repo-visibility-skill]] — Same concept but for GitHub repos

What ships with it: 26 files

21.0 KB alongside SKILL.md, 8 of them executable

bin/

examples/

scripts/

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.