thevibegarage

Geo Visibility Skill — Security skill for Claude Code

Security community

Claude skill for Generative Engine Optimization (GEO): audit and improve how your brand gets found, cited and recommended in ChatGPT, Claude, Gemini, Perplexity and Google AI Overviews.

How to install Geo Visibility Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open thevibegarage/geo-visibility-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Geo Visibility Skill does

Claude skill for Generative Engine Optimization (GEO): audit and improve how your brand gets found, cited and recommended in ChatGPT, Claude, Gemini, Perplexity and Google AI Overviews. Prompt-set audits, crawler/schema fixes, and measurement scripts. MIT, by Garage Labs Technologies.

Alternatives in Security

  • Tech Debt Skill — Claude Code skill that produces a thorough, file-cited tech debt audit of an entire codebase 590 ★
  • Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★
  • Perplexity Super Skills — Complete collection of 12 Perplexity Computer Super-Skills merging Perplexity + Claude Code capabilities acros 346 ★

README

GEO Visibility — a Claude Skill for Generative Engine Optimization

[![Release](https://img.shields.io/github/v/release/thevibegarage/geo-visibility-skill)](https://github.com/thevibegarage/geo-visibility-skill/releases) [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE) [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)

Audit and improve how a brand is found, cited and recommended inside **ChatGPT, Claude, Gemini, Perplexity, Copilot and Google AI Overviews** — while keeping classic SEO strong.

**See what it produces → [sample audit report](examples/sample-report.md)** · Install in 30 seconds below.

Built and open-sourced by [Garage Labs Technologies](https://www.garagelabstech.com), an AI transformation partner headquartered in India.

What it does

The skill works on one idea: **AI engines recommend what they can retrieve, understand and trust.** It runs a six-phase process:

  1. Baseline audit — 25–50 buyer prompts run across engines, scored for mentions, citations, position and share of voice. The key output is the ranked list of domains the engines actually cite in your category.
  2. Technical readiness — crawler access (robots.txt, WAF), rendering without JavaScript, Bing/Google indexing, structured data, llms.txt.
  3. Entity and content — a canonical brand fact sheet, answer-first page rewrites, content briefs for every prompt you lose.
  4. Off-site authority — a ranked, ethical plan for review sites, "best of" lists, press and community presence.
  5. Engine-specific tuning — per-engine playbooks with confidence levels.
  6. Measurement — a frozen prompt set, tracker CSV, roll-up script, and a treated-vs-control page experiment.

It also includes two standard-library Python scripts:

  • scripts/check_ai_readiness.py — checks robots.txt rules for AI agents, WAF behavior, llms.txt, sitemap, JSON-LD, and whether key text survives without JavaScript.
  • `script