Generative Engine Optimization (GEO) Audit Tool with Claude Code
Key Concepts:
- Generative Engine Optimization (GEO): Optimizing websites for AI search engines like ChatGPT, Perplexity, and Gemini, rather than traditional search engines like Google and Bing.
- Claude Code: A platform allowing users to build and run AI-powered tools using “skills” – essentially plugins providing specialized functionality.
- Skills: Instructions given to Claude Code to enable it to perform specific tasks or become an expert in a particular area.
- Sub-agents: Specialized AI components within a skill, delegated to analyze specific aspects of a website during a GEO audit.
- GEO Audit: A comprehensive assessment of a website’s visibility and performance in AI search results.
Introduction to GEO and the Tool
The video introduces a new approach to SEO called Generative Engine Optimization (GEO), focusing on optimizing websites for AI-powered search engines. The presenter demonstrates a tool built using Claude Code that automates GEO audits, providing detailed reports on a website’s AI visibility. The tool is offered freely for viewers to test and utilize. The presenter highlights the potential of this market, projecting growth to $7 billion in the next few years, driven by the 500%+ year-over-year growth in AI search traffic. Currently, only 23% of marketers are actively considering GEO.
Demonstration: Dscript.com GEO Audit
The presenter begins by showcasing a completed GEO audit on dscript.com, a video editing tool. The audit utilized 11 skills and 5 AI agents simultaneously. Key findings include:
- Overall GEO Score: 58/100, indicating significant room for improvement.
- Scored Categories: AI Citability, Brand Authority, Technical Content, Quality, and Schema were individually scored, revealing specific weaknesses.
- Platform-Specific Performance: The tool assesses performance on different AI platforms (ChatGPT, Perplexity, Google AI Overviews, Gemini) as performance varies significantly between them.
- Critical Findings & Prioritized Action Plan: The report identifies issues hindering AI visibility and provides a prioritized list of fixes. This report is presented as a deliverable ready for client presentation, saving significant time and effort compared to manual report creation. The presenter states agencies typically charge thousands of dollars and spend a week creating similar reports, while this tool generates one in approximately 60 seconds.
Live Audit: Typeform.com & Tool Functionality
The presenter then performs a live GEO audit on Typeform.com, a form-building website, to demonstrate the tool’s workflow.
Step-by-Step Process:
- Accessing Claude Code: The tool is run within a Claude Code instance, accessible through Visual Studio Code or a terminal.
- Invoking the GEO Audit Skill: The command
/geo-auditis used to initiate the audit, followed by the target website URL (e.g., typeform.com). - Audit Phases: The audit proceeds through three phases:
- Phase 1: Discovery & Fetching: Retrieves the homepage and identifies the website’s business type.
- Phase 2: Parallel Sub-Agent Analysis: Runs five specialized AI agents concurrently to analyze different aspects of the website.
- Phase 3: Aggregate Scores & Report Generation: Combines the results from the sub-agents to generate an overall GEO score and detailed report.
- Accessing the GitHub Repository: The presenter provides a link to the GitHub repository containing the code and installation instructions. Installation is simplified with a single command.
Skill Breakdown:
The GEO audit relies on a “skill” defined in a skills.mmd markdown file. This file contains detailed instructions for Claude Code, outlining the audit workflow and specific tasks for each phase. Phase 2 utilizes five sub-agents:
- AI Citability Analysis: Assesses content for readability and usability by AI systems.
- Brand Analysis: Evaluates brand recognition and authority.
- Technical GEO Infrastructure: Examines the website’s technical setup for AI crawlability.
- Content Quality Analysis: Analyzes the quality and relevance of website content.
- Schema Markup Analysis: Checks for proper schema implementation to help AI understand the content.
The sub-agent approach is likened to hiring subcontractors for a construction project, each specializing in a specific task to improve efficiency.
Data & Results: Typeform.com Audit
The live audit of Typeform.com yielded the following results:
- Overall GEO Score: 62/100 (Moderate)
- Critical Findings:
- Pricing Page Invisibility: Pricing data is rendered in JavaScript via API calls, making it inaccessible to AI crawlers. AI systems cannot answer the question "How much does Typeform cost?".
- Schema Markup Deficiency: Limited schema markup implementation, particularly lacking software application, FAQ page, and offer schemas.
- LLM.txt File Non-Compliance: The
llm.txtfile exists but is incorrectly formatted.
- Top Strengths: Strong brand recognition (Wikipedia page, 85+ LinkedIn followers, 4.5-star G2 rating).
- AI Platform Readiness: Good performance on Google AI Overviews and ChatGPT, but weaker on Bing Copilot.
Generating a PDF Report
The presenter demonstrates how to convert the audit results into a professional PDF report using another Claude Code skill, GEO report. This skill utilizes instructions in GEO report skills.mmd to format the data into a visually appealing and client-ready document. The report includes:
- Executive Summary
- GEO Score Breakdown
- AI Platform Readiness
- Critical Findings
- Prioritized Action Plan (Quick Wins, Medium-Term Improvements, Strategic Initiatives)
Monetization & Community Resources
The presenter suggests a sales approach: presenting the free GEO audit report to potential clients and offering a paid service to implement the recommended improvements. He promotes a Claude Code community offering:
- Step-by-step tutorials on building and using the tool.
- Guidance on selling GEO services.
- Access to additional projects and courses.
- Live Q&A sessions.
Conclusion
The video concludes by emphasizing the potential of GEO as a rapidly growing field and the value of the presented tool for SEO professionals and agencies. The tool, built with Claude Code, automates a complex audit process, providing actionable insights and a deliverable report in a fraction of the time compared to manual methods. The presenter encourages viewers to explore the resources provided and leverage this new opportunity in the evolving landscape of search engine optimization.
AI summaries can miss context or contain errors. Check important details against the original video.