explaingit

mars-tw/open-seo-advisor-skill

Analysis updated 2026-05-18

32PythonAudience · developerComplexity · 3/5LicenseSetup · moderate

TLDR

An open source SEO and marketing skill for AI agents that runs site health checks, fixes technical SEO, writes content, and manages ad audits.

Mindmap

mindmap
  root((repo))
    What it does
      Runs SEO health checks
      Coordinates marketing tasks
    Tech stack
      Python
      LLM integrations
      WebsiteConnector
    Use cases
      Fix technical SEO issues
      Audit Meta ad accounts
      Generate SEO content
    Audience
      Developers
      Marketers
      Agencies

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Run a full SEO health check on a website and get a prioritized report of fixes.

USE CASE 2

Automatically repair sitemap, robots.txt, canonical, and structured data issues.

USE CASE 3

Audit a Meta ad account and get a dry-run optimization plan before spending real money.

USE CASE 4

Generate SEO-oriented content or check an ecommerce product listing against a marketing checklist.

What is it built with?

PythonClaudeGPTWordPress REST APICloudflare API

How does it compare?

mars-tw/open-seo-advisor-skillautolearnmem/automembilly-ellis/exr-imageio-poc
Stars323232
LanguagePythonPythonPython
Setup difficultymoderatehardmoderate
Complexity3/55/53/5
Audiencedeveloperresearcherresearcher

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Core scan works with no API keys, optional paid integrations like GA4, PageSpeed Insights, or LLM APIs unlock more modes.

Licensed under Apache License 2.0, so you can use, modify, fork, and redistribute it freely, including commercially, as long as you keep the license notice.

In plain English

Open SEO Advisor is an open source tool that packages up the way experienced SEO consultants, engineers, security reviewers, content writers, and WordPress plugin developers actually do their jobs into checklists, report templates, and runnable code. It is built to work as a skill for AI coding agents such as Claude Code, but it also runs on its own as a command line tool, and it never locks a user into one paid vendor: services like Search Console, GA4, PageSpeed Insights, OpenAI, or Anthropic are all optional add ons rather than required dependencies. It offers seven modes. Consultant mode runs a full site SEO health check and produces a prioritized list of fixes. Engineer mode directly repairs technical problems such as sitemaps, robots.txt files, canonical tags, hreflang, structured data, and Core Web Vitals. Security mode checks for SEO related security risks like leaked files, outdated content management systems, spam injection, and malicious redirects. Content Writer mode calls a language model, whether Claude, GPT, or a locally run model, to draft content aimed at meeting Google's quality guidelines. Plugin Dev mode builds SEO related plugins for WordPress and similar platforms. Meta Ads mode reviews Facebook and Instagram ad accounts and proposes optimizations as a dry run plan, with any action that spends real money locked behind extra safeguards by default. Image Material mode generates images for ads, social posts, or articles with a swappable image provider. Sitting above these modes is an AI matrix system: a user states one goal, and a coordinating role assigns the work across twenty six simulated AI team member roles covering strategy, marketing, sales, product, operations, finance, human resources, legal, and admin, who route tasks to the modes already built and combine the results into one deliverable. Any high risk action, such as publishing something live or spending money, is always escalated to require a human's explicit approval and produces only a plan rather than acting automatically. The project also includes growth marketing tools for UTM tracking, landing page optimization, and cross channel analytics, plus an ecommerce listing health check built on a neutral, fifty point marketing methodology checklist that avoids naming any specific course or brand. Everything can be tried without supplying any API keys. It runs on Python, defaults to read only and dry run behavior, and is released under the Apache License 2.0.

Copy-paste prompts

Prompt 1
Run this tool's consultant mode on my website and summarize the top priority SEO fixes.
Prompt 2
Use the engineer mode to fix my sitemap and robots.txt issues, but explain each change before applying it.
Prompt 3
Set up the AI matrix mode with a one-sentence marketing goal and show me the resulting plan.
Prompt 4
Walk me through installing this tool and running my first free SEO audit without any API keys.

Frequently asked questions

What is open-seo-advisor-skill?

An open source SEO and marketing skill for AI agents that runs site health checks, fixes technical SEO, writes content, and manages ad audits.

What language is open-seo-advisor-skill written in?

Mainly Python. The stack also includes Python, Claude, GPT.

What license does open-seo-advisor-skill use?

Licensed under Apache License 2.0, so you can use, modify, fork, and redistribute it freely, including commercially, as long as you keep the license notice.

How hard is open-seo-advisor-skill to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is open-seo-advisor-skill for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.