This project provides an AI-powered SEO auditing skill for agents, capable of generating both beginner SEO audits and advanced technical SEO reports for any given URL. It offers actionable insights and structured HTML reports, benefiting AI agents and developers seeking to optimize web page performance and search engine visibility.

How It Works

The skill employs a two-layer architecture. The first layer utilizes Python scripts for deterministic checks, such as parsing robots.txt, validating Title/Description/Keywords (TDK), checking canonical tags, and integrating with the PageSpeed Insights API. The second layer leverages an LLM for semantic judgment on aspects like keyword intent alignment, content quality, and page type inference. This hybrid approach ensures factual accuracy from scripts while using LLM intelligence for nuanced SEO analysis, with the LLM only intervening when scripts flag a need for semantic review.

Quick Start & Requirements

Installation is straightforward via CLI using npx skills add JeffLi1993/seo-audit-skill or as a Claude Code Plugin via /plugin marketplace add JeffLi1993/seo-audit-skill. Specific tiers (seo-audit or seo-audit-full) can be installed with the --skill flag. The primary dependency is pip install requests. No specific hardware or advanced software prerequisites like GPUs are mentioned for basic operation.

Highlighted Details

• Offers two tiers: seo-audit (basic, 20+ checks) and seo-audit-full (advanced, including Core Web Vitals, GSC data, competitor gap analysis).
• Provides comprehensive audit coverage, encompassing site-level checks (e.g., robots.txt, sitemap, canonicalization, i18n, Schema) and page-level checks (e.g., PageSpeed, TDK, headings, word count, internal links).
• Generates detailed, standalone HTML reports featuring an audit summary, site/page checks, priority actions, and an insight walkthrough for each finding.
• Python scripts handle specific tasks like RFC 9309 robots.txt parsing, JSON-LD validation, and PageSpeed Insights API integration.

Maintenance & Community

The provided README does not contain specific details regarding notable contributors, sponsorships, community channels (e.g., Discord, Slack), or a public roadmap.

Licensing & Compatibility

The project is released under the MIT license, which is permissive and generally suitable for commercial use and integration into closed-source projects.

Limitations & Caveats

The README does not explicitly detail limitations such as alpha status, known bugs, or unsupported platforms. The effectiveness of the semantic analysis layer is dependent on the capabilities of the underlying LLM. Advanced features in the seo-audit-full tier may have higher resource requirements or dependencies not detailed here.