Geo Audit

GEO Audit

A fast, real technical audit of how AI-ready a website is. Type a domain, get a streaming scorecard back in under 30 seconds, ending with the three things most worth fixing.

This is the operator-side companion to writing content. It tells you whether your site is even legible to AI agents before you spend a quarter producing for them.

RUNNING AN AUDIT

Extract the domain from the user's message and run the script without asking clarifying questions first. Stream the terminal output back as it happens. When the HTML report opens, mention that it just popped up in their browser and summarize the score in one sentence.

WHEN TO USE THIS SKILL

Use this when someone wants to:

• Quickly understand how AI-friendly a site is
• Diagnose why a site they've written for isn't getting picked up by ChatGPT, Perplexity, Gemini, or Claude
• Produce a demo-able audit on any domain on the fly
• Triage technical GEO issues before kicking off a content program

Do not use this skill for writing articles, comparison pages, or topical hubs. Route those to geo-article-writer.

USAGE

python3 {baseDir}/scripts/audit.py <domain>

Examples:

python3 {baseDir}/scripts/audit.py vellum.ai
python3 {baseDir}/scripts/audit.py https://stripe.com
python3 {baseDir}/scripts/audit.py example.com --json

The script accepts a bare domain (vellum.ai), a full URL (https://vellum.ai), or anything in between. It normalizes.

If the script runs cleanly → stream the output and summarize (default). If the domain is unreachable / DNS fails / times out → report the specific failure plainly, suggest the user double-check the domain or bump --timeout, and do not invent a score. If python3 is unavailable or blocked in this session → say so directly. Do not fabricate a scorecard or paraphrase what the audit "would" find — the numbers only exist if the script ran.

Flags:

• --json — emit the report as JSON instead of streaming markdown (for piping into other tools)
• --no-color — strip ANSI color codes (for logs / CI)
• --no-html — skip the HTML report (default: writes one to a temp file and auto-opens it in your browser)
• --no-open — write the HTML report but don't auto-open it
• --timeout N — per-request timeout in seconds (default: 10)

By default the script does two things at once: streams a clean terminal scorecard live as checks complete, and opens a dark-themed HTML report in your browser at the end with a table, prioritized fixes, and a handoff to geo-article-writer. The terminal version is the watchable moment; the HTML is the keepable artifact.

WHAT IT CHECKS

Six checks, each scored. Total: 100 points.

1. AI crawler access via robots.txt (25 pts)

Pulls /robots.txt and verifies each of the major AI agents is either explicitly allowed or not actively blocked:

• GPTBot, ChatGPT-User, OAI-SearchBot (OpenAI)
• ClaudeBot, anthropic-ai (Anthropic)
• PerplexityBot, Perplexity-User (Perplexity)
• Google-Extended (Gemini / Google AI Overviews — separate from Googlebot)
• CCBot (Common Crawl, feeds many training sets)

A site that blocks Google-Extended is invisible to Gemini and AI Overviews even if it ranks fine in regular Google. This is the most common silent miss.

2. llms.txt presence and shape (15 pts)

Looks for /llms.txt at the domain root. Scores on:

• Exists
• Has a top-level # title
• Lists at least one curated link
• Links resolve (no 404s on the first batch)

llms.txt is the emerging convention for handing AI crawlers a curated map. It's still optional, but it's a cheap differentiator.

3. Server-side rendering (20 pts)

Fetches the homepage without executing JS and checks whether the brand name, primary H1, and primary CTA are present in the initial HTML.

This is the single most under-detected GEO failure. A JS-rendered marketing site can look fine to a human and be completely empty to GPTBot, which generally does not execute JavaScript.