Bhanunamikaze/Agentic-SEO-Skill

What it solves

This project provides an LLM-first SEO analysis toolkit designed to integrate directly into AI coding assistants and agent IDEs. It automates the tedious process of collecting technical SEO evidence—such as crawlability, indexability, and Core Web Vitals—and provides the structured data necessary for an LLM to perform high-confidence SEO audits and strategic planning.

How it works

The system functions as a "skill" that can be installed into various AI IDEs (like Cursor, Claude Code, or Windsurf). It uses an orchestration layer where the LLM matches a user's natural language request to one of 16 specialized sub-skills. These sub-skills trigger a library of 89 Python scripts that act as evidence collectors (e.g., fetching HTML, checking robots.txt, validating JSON-LD schema, or capturing screenshots via Playwright). The LLM then analyzes this raw evidence against a standardized audit rubric to produce findings with confidence labels (Confirmed, Likely, Hypothesis) and a prioritized action plan.

Who it’s for

It is built for developers, SEO specialists, and site owners who use AI-powered IDEs and want to perform deep technical SEO audits, content optimization, and Generative Engine Optimization (GEO) without leaving their coding environment.

Highlights

• Wide IDE Support: Native installation formats for Claude Code, Cursor, Windsurf, Codex, Continue.dev, GitHub Copilot, and Cline.
• Comprehensive Toolset: Includes 10 specialist agents and 89 scripts covering everything from Core Web Vitals to international hreflang validation.
• AI-Search Ready: Dedicated sub-skills for GEO (Generative Engine Optimization) and AEO (Answer Engine Optimization) to optimize for AI overviews and LLM citations.
• GitHub SEO: Specialized workflows to optimize GitHub repositories, including README quality and community profile analysis.
• Evidence-Based Reasoning: Forces the LLM to use explicit proof for every finding, reducing hallucinations in SEO reports.