AgriciDaniel/chatgpt-seo

Turn a page, draft, or SEO export into a sourced fix plan inside ChatGPT.

What it solves

SEO work often suffers from vague advice or hunches. This plugin gives you a structured way to get actionable, evidence-based SEO recommendations directly inside ChatGPT. Instead of asking for general tips, you bring real evidence—a page URL, an HTML file, a content draft, or a Search Console CSV export—and get a prioritized fix plan with verification steps for each change.

How it works

You install the plugin as a ZIP file in ChatGPT’s Plugins menu (manual upload). After that, you pick one of three main “quests”: inspect a page, plan a content brief, or decode a search export. Each quest gives you a copyable prompt to paste into ChatGPT. The plugin loads the relevant skill (out of 27 total) and supporting references, then uses ChatGPT’s built-in tools—like public browsing or file handling—to analyze only the evidence you provided. The response always follows a structure: evidence observed, finding, suggested fix, how to verify, and what remains unknown. The plugin includes no server, API key, crawler, or Google account connection. Optional offline Python commands can inspect local HTML, XML, CSV, JSON, or image headers when file execution is available, but they only use Python’s standard library and never fetch URLs.

Who it’s for

This is for anyone who works on SEO and already uses ChatGPT—solo SEO specialists, content marketers, site owners, or small agency teams. It’s especially useful if you want a clear, evidence-driven process without buying another SEO tool or paying for an API key. You should be comfortable uploading your own page URLs, HTML, or CSV exports, and you should expect to verify the suggested fixes yourself.

Highlights

  • Three guided “quests” (Inspect a page, Brief a writer, Read a Search Console export) with ready-to-use prompts.
  • 27 workflow skills covering page audits, technical SEO, schema, sitemaps, hreflang, local SEO, ecommerce, content briefs, and more.
  • No API key, no separate SEO account, no Google connection, no telemetry, and no publisher-operated server.
  • Every recommendation includes evidence, a prioritization, and a way to verify the change after you make it.
  • Clearly labels missing data or assumptions—it won’t invent search volumes or audience claims.
  • Optional offline Python commands for inspecting local files when execution is available, with a note that unavailable capabilities are reported rather than simulated.

Related

  • Project
    Yeti-791/Tsec-Hackathon

    Tsec-Hackathon is the official resource hub for Tencent Cloud's Intelligent Penetration Hackathon, aggregating defense slides, event materials, and open-source repositories from the top teams across two editions. It serves as a one-stop navigation page for learning how LLM-based penetration testing agents are built and evolved.

  • Project
    kody-hq/kody

    Kody is a Cloudflare Workers‑based platform that provides persistent memory, credential storage, code packages, and job scheduling for AI agents via the Model Context Protocol (MCP). It offers a Remix UI, OAuth‑protected endpoints, and a four‑worker architecture (origin, platform, runtime, jobs) to serve individual or team accounts. The repo is a full‑stack TypeScript monorepo (Nx) with local dev support, extensive docs, and a functional‑source license.

  • Project
    langchain-ai/react-agent

    A LangGraph template for implementing a ReAct agent that iteratively reasons and executes tool-based actions to solve complex user queries.

  • Project
    elstongun/leviathan

    Leviathan is a Rust‑based CLI that indexes CSV/JSON/SQLite data into a single SQLite FTS5 file, enabling fast, token‑budgeted natural‑language search for AI agents. It supports group‑scoped queries, incremental upserts, optional key‑value memory, and can be wrapped as a skill for Claude, Gemini, VS Code/Copilot, etc. Benchmarks show ~436‑token answers for 1 M records with 33 ms latency, far smaller than raw grep approaches.