GeoRank

GEO-first toolkit for auditing and improving AI search visibility across ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews, and Bing Copilot.

This repository includes:

• Python audit scripts for citability, brand authority, llms.txt, semantic coverage, competitor analysis, and PDF report generation.
• Skill and agent definitions for Claude Code workflows.

What GEO Means

Generative Engine Optimization (GEO) focuses on making your content easier for AI systems to discover, understand, and cite in generated answers.

Repository Layout

GeoRank/
├── scripts/                     # Core GEO analysis scripts
├── schema/                      # JSON-LD templates
├── agents/                      # Subagent definitions
├── skills/                      # Modular GEO skills
├── geo/                         # Main skill definition
├── geo-audit-data/              # Generated audit artifacts
├── install.sh                   # Skill installer
├── uninstall.sh                 # Skill uninstaller
└── requirements.txt             # Python dependencies

Prerequisites

• Python 3.10+

Optional:

• Playwright browsers (for any screenshot-enabled workflows)
• Claude Code CLI (if you are using this as a Claude skill package)

Quick Start

1. Create and activate a virtual environment.

# Windows PowerShell
python -m venv .venv
.\.venv\Scripts\Activate.ps1

# macOS/Linux
python3 -m venv .venv
source .venv/bin/activate

2. Install dependencies.

pip install -r requirements.txt

3. Run a script.

python scripts/citability_scorer.py https://example.com

Core Script Commands

All commands print JSON output.

# Page-level citability scoring
python scripts/citability_scorer.py <url>

# Brand mention/authority scan
python scripts/brand_scanner.py "<brand_name>" [domain]

# Competitor benchmarking
python scripts/competitor_analyzer.py <target_url> <competitor1> [competitor2] ...

# llms.txt validation or generation
python scripts/llmstxt_generator.py <url> [validate|generate]

# Semantic keyword coverage scoring
python scripts/semantic_scorer.py <url> [anthropic_api_key]

# Fetch page/robots/llms/sitemap/blocks/full bundle
python scripts/fetch_page.py <url> [page|robots|llms|sitemap|blocks|full]

# Generate PDF report from JSON payload
python scripts/generate_pdf_report.py <audit_data.json> [output.pdf]

Claude Skill Installation

If you want to install this into ~/.claude as a local skill package:

bash install.sh

Uninstall:

bash uninstall.sh

Output Artifacts

Generated data and reports are written under:

• geo-audit-data/

Typical outputs include:

• GEO audit markdown reports
• JSON score payloads
• competitor analysis snapshots
• PDF reports

License

Add your preferred license here (for example: MIT, Apache-2.0, or proprietary internal use).