AKCodez

SEO God — Security skill for Claude Code

Security community

Turn Claude Code into an agentic SEO operator for your own site — audit, measure, daily loop, AI visibility, scheduled runs.

How to install SEO God

This entry records only its repository, not the path inside it, so there is no exact command to give. Open AKCodez/seo-god and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What SEO God does

Turn Claude Code into an agentic SEO operator for your own site — audit, measure, daily loop, AI visibility, scheduled runs. Free path, no paid keys.

Alternatives in Security

  • Free Code — The free build of Claude Code 8.1k ★
  • Claudit Sec — Security audit tool for Claude Desktop and Claude Code on macOS — single-command visibility into MCP servers 115 ★
  • Audit Claude Components — Comprehensive audit of .claude folder 63 ★

README

SEO-GOD — a Claude Code skill. Point Claude Code at your own site: it audits, fixes and measures, then runs the whole loop again tomorrow. Under the title, the whole install: clone, then /seo-god, then it runs again tomorrow at 05:00. Beside it, the skill's own menu: setup, audit and measure done; ai_visibility and schedule pending; act on demand; power-ups optional.

Works with Claude Code Platforms: Windows, macOS and Linux Paid keys: none required License: MIT

`seo-god` turns Claude Code into an SEO operator for a site you own.

It crawls your site with a local [OpenSEO](https://github.com/every-app/open-seo) container. It fixes what it finds, in your repo, behind your own build. It reads your real numbers out of Google Search Console and diffs today against yesterday. Then it does the whole thing again tomorrow, on a schedule you install once.

It never scrapes Google. The entire free path runs without a single paid API key.

Proof

The five phases here are a rewrite of a pipeline that runs daily on a production site.

The code in this repo is new. The method survived production. So did the review order, and the failure modes it guards against.

You do not have to take my word for any of it. The [smoke report](./docs/SMOKE.md) is an end-to-end run against a live test fixture, failures included. The [eval](./docs/EVAL.md) is 240 runs with the numbers. Both are in t