geo-audit

Audits source code for AI citation readiness across 12 GEO dimensions.

6|Updated Mar 27, 2026
One-click install
npx skills add https://github.com/greglas75/zuvo --skill geo-audit-greglas75
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-audit
Source: https://github.com/greglas75/zuvo/tree/main/skills/geo-audit
Command: npx skills add https://github.com/greglas75/zuvo --skill geo-audit-greglas75

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It determines whether a website's codebase is structured so AI systems like Google AI Overviews, ChatGPT Browse, Perplexity, and Gemini can crawl, parse, and cite its content, producing evidence-backed findings instead of guesswork. ## Core Features & Use Cases - 12-Dimension GEO Audit: Evaluates AI crawler access, schema graph connectivity, llms.txt, SSR rendering, freshness, chunkability, canonicalization, sitemap, BLUF structure, heading quality, citation signals, and anti-patterns. - Tiered Scoring with Critical Gates: Produces an A/B/C/D tier, weighted overall score, and four critical gates (GCG1-GCG4) that can force FAIL or PROVISIONAL results. - Machine-Readable Output: Saves Markdown and JSON reports to zuvo/audits/ for consumption by the geo-fix skill and CI pipelines. - Use Case: Run it against a Next.js marketing site to discover that JSON-LD is injected client-side (invisible to AI crawlers) and robots.txt blocks retrieval bots, then get prioritized fixes with file:line evidence. ## Quick Start Ask the AI to run a GEO readiness audit on the current project and report the tier, critical gates, and top priority findings.

Frequently Asked Questions about geo-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit my website for AI search and GEO readiness?

Run the geo-audit skill against your project directory. It scans source code across 12 dimensions covering crawler access, schema, rendering, and content signals, then produces a tiered report with file:line evidence and a JSON output for automated fixes.

What is the difference between GEO audit and traditional SEO audit?

GEO audit measures readiness for AI citation by systems like ChatGPT and Perplexity, focusing on schema graph connectivity, llms.txt, BLUF structure, and retrieval bot access. Traditional SEO audits target search engine ranking factors and are handled separately by the seo-audit skill.

Does geo-audit support Next.js and Astro projects?

Yes, it auto-detects Next.js, Astro, Hugo, Nuxt, SvelteKit, Gatsby, WordPress, Docusaurus, VitePress, and Remix from config files. Framework-specific checks apply, such as nextjs_metadata_audit for Next.js and client:load island detection for Astro.

Can geo-audit modify my source code to fix issues?

No, the audit is strictly read-only against source code. It only writes report files to zuvo/audits/ and optionally memory/backlog.md. Fixes are suggested in the report and applied separately through the geo-fix skill.

Why does my GEO audit result show PROVISIONAL instead of PASS?

PROVISIONAL means a blocking critical gate returned INSUFFICIENT DATA, typically because static analysis was inconclusive and no live verification was run. Re-run with the --live-url flag to verify gates like crawler access against the deployed site.

What are the limitations of geo-audit on CMS-backed sites?

When a CMS like WordPress, Contentful, or Sanity is detected, content quality dimensions G9-G12 are marked INSUFFICIENT DATA because content lives in the database, not source code. Use --live-url for partial live verification of those dimensions.