SEO + GEO audits for AI coding agents: health scores, technical checks, Schema.org, E-E-A-T, AI search visibility. 35 scripts; HTML/XLSX/PDF. Default reports use seed URL + capped crawls; generate_report.py --crawl-deep for broader link/canonical scans. Optional MCP (Firecrawl, DataForSEO). Progressive disclosure via SKILL + references/procedures/. LLM-agnostic.
npx claudepluginhub mykpono/ultimate-seo-geoScored SEO audits, technical health checks, Schema.org JSON-LD, E-E-A-T content scoring, domain authority rating, and GEO for AI Overviews, ChatGPT, and Perplexity. 24 diagnostic scripts. Modes: Audit → Plan → Execute.
The definitive SEO and Generative Engine Optimization agent for AI coding tools. LLM-agnostic — works on any platform that reads AGENTS.md. Runs full site audits with scored findings, generates ready-to-deploy fixes, and optimizes content for both Google Search and AI search engines (Google AI Overviews, AI Mode, ChatGPT Search, Perplexity). Exports HTML and Excel reports.
Works with any AGENTS.md-compatible tool: Claude Code, Cursor, OpenAI Codex, Gemini CLI, GitHub Copilot, Windsurf, Cline, Aider, Devin, and more.
Author: Myk Pono · Lab · LinkedIn
Give it a URL and it returns a scored audit, prioritized action plan, and executable fixes — not vague advice.
Three modes, one skill:
| Mode | What It Does | Output |
|---|---|---|
| Audit | Fetches site, runs all checks, scores findings | SEO Health Score (0–100) + prioritized findings |
| Plan | Converts findings into phased roadmap | Implementation table with effort/impact/owner |
| Execute | Produces the actual fixes + verifies them | JSON-LD, meta rewrites, redirect maps, robots.txt |
Most requests run all three in sequence. Skip to Mode 2 if you already have audit findings; skip to Mode 3 if you know exactly what to fix.
| Platform | How It Loads Instructions | Script Execution | Setup |
|---|---|---|---|
| OpenAI Codex | AGENTS.md auto-loaded (32 KiB limit) | Full (shell access) | Clone repo, start coding |
| Google Gemini CLI | GEMINI.md → imports AGENTS.md | Full (shell access) | Clone repo, start coding |
| Claude Code | Plugin marketplace + SKILL.md | Full (shell access) | /plugin install (see below) |
| Cursor IDE | AGENTS.md + .cursor/rules/ + skill auto-discovery | Full (shell access) | Clone repo or install skill |
| GitHub Copilot | AGENTS.md + .github/copilot-instructions.md | Full (agent mode) | Clone repo, start coding |
| Windsurf | AGENTS.md auto-loaded | Full (shell access) | Clone repo, start coding |
| Cline | AGENTS.md auto-loaded | Full (shell access) | Clone repo, start coding |
| Aider / Devin / Goose / Amp | AGENTS.md auto-loaded | Full (shell access) | Clone repo, start coding |
| ChatGPT Custom GPT | Uploaded instructions + knowledge files | Limited (no scripts) | See chatgpt/README.md |
| Claude Desktop (claude.ai) | Upload SKILL.md to Project Knowledge | No shell access | Manual upload |
Harness-native ECC skills, hooks, rules, MCP conventions, and operator workflows
Claude Code marketplace entries for the plugin-safe Antigravity Awesome Skills library and its compatible editorial bundles.
Production-ready workflow orchestration with 84 marketplace plugins, 192 local specialized agents, and 156 local skills - optimized for granular installation and minimal token usage