Agentic-SEO-Skill  by Bhanunamikaze

LLM-first SEO analysis skill for agent IDEs

Created 1 month ago
328 stars

Top 83.4% on SourcePulse

GitHubView on GitHub
Project Summary

An LLM-first SEO analysis skill designed for agent IDEs like Antigravity, Claude, and Codex. It provides 16 specialized sub-skills and 10 specialist agents to conduct comprehensive SEO audits, content optimization, technical analysis, and GitHub repository SEO, delivering evidence-backed insights and actionable plans.

How It Works

This skill employs an "LLM-first" and "reasoning-first" workflow. It begins by collecting page evidence, optionally using utility scripts. This evidence is then analyzed by an LLM, with explicit proof supporting each finding and confidence labels (Confirmed, Likely, Hypothesis). Findings are prioritized by impact and effort, culminating in a structured action plan. Specialist agents handle distinct SEO domains, and a global verifier ensures deduplication before final reporting.

Quick Start & Requirements

  • Primary Install: A install.sh script is provided for Antigravity (project-local), Claude (user-global), or Codex (user-global), with options for installing all targets or from a local repository checkout. Direct installation from GitHub via curl is also supported.
  • Manual Installation: Clone the repository, then install Python dependencies: pip install requests beautifulsoup4.
  • Non-default Prerequisites: playwright and its browser binaries are optional but required for visual analysis (screenshots, layout checks).
  • IDE Compatibility: Antigravity IDE, Claude Code, Codex.
  • Links: GitHub repository: https://github.com/Bhanunamikaze/Agentic-SEO-Skill.

Highlighted Details

  • Features 16 specialized sub-skills, including full website audits, article optimization, technical SEO, schema markup, Core Web Vitals analysis, and GitHub repository SEO.
  • Employs 10 specialist agents for domains like Technical SEO, Content Quality, Performance, Schema Markup, Visual Analysis, and GitHub analysis.
  • Supports LLM-driven analysis with explicit proof, confidence labeling, and prioritization of findings.
  • Includes updated reference data (Feb 2026) for Core Web Vitals (INP), E-E-A-T, and Schema.org types.
  • Offers pre-built strategy templates for various business types (SaaS, E-commerce, Local Business, etc.).
  • Generates GITHUB-SEO-REPORT.md and GITHUB-ACTION-PLAN.md for repository analysis.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), or project roadmap were found in the provided README.

Licensing & Compatibility

Licensed under the MIT License. This license is permissive and generally compatible with commercial use and closed-source linking.

Limitations & Caveats

The README does not explicitly detail known bugs, alpha status, or unsupported platforms. Visual analysis features are optional and require additional setup (playwright). Integration with Google Search Console necessitates providing credentials.

Health Check
Last Commit

1 month ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
1
Star History
190 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.