# AI SEO

> AI SEO is an open-source agent skill for marketing and seo. Audits and improves how a site gets cited and recommended in AI answers and by AI agents. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

- **Kind:** Skill
- **Pricing:** Open source
- **Platforms:** Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- **Website:** https://github.com/coreyhaines31/marketingskills/tree/main/skills/ai-seo
- **Repository:** https://github.com/coreyhaines31/marketingskills
- **GitHub stars:** 60,928
- **License:** MIT
- **Skill name:** ai-seo
- **Collection:** https://github.com/coreyhaines31/marketingskills
- **Categories:** marketing and SEO
- **Listing updated:** 2026-11-17

## About

The workflow starts with an AI visibility audit: test ten to twenty revenue-relevant prompts across Google AI Overviews, ChatGPT and Perplexity, record who is cited, compare competitor citation patterns, check page extractability with a pass/fail table, and audit AI crawler access by purpose, since search discovery, user-triggered retrieval, training and Google product-control tokens are different controls. Because AI answers are non-deterministic, queries should be run several times and reported as rates with sample sizes.

Optimization is organized as structure, authority and presence. Structure means standalone answer blocks, definitions, comparison tables and FAQs with 40 to 60 word answer passages. Authority draws on cited sources, statistics, expert quotes and freshness signals, referencing a published generative-engine optimization study with a caveat that numbers drift. Presence covers third-party surfaces such as review sites, Wikipedia, forums, LinkedIn and YouTube, plus consistent positioning across profiles. It adds machine-readable files such as a pricing markdown file and llms.txt, notes an emerging open knowledge format, and lists schema types.

The skill is candid about Google's stance that no special markup or AI-only content is needed and that chunking pages for AI or fabricating mentions can hurt, while other engines reward extractable structure. It separates being cited from being recommended, and a routing table points to reference files on agent readiness, attribution, answer accuracy, prompt tracking, format volatility, multilingual and commerce, and platform factors. Tool lists name visibility monitors, with a monthly manual check as a no-tool option.

## When your agent uses it

> When the user wants to get cited and recommended in AI answers (ChatGPT, Perplexity, AI Overviews), or asks why AI cites a competitor, which content gets cited, or whether llms.txt or a page format is worth it: AEO, GEO, AI visibility, agent-readable sites. For technical and on-page SEO, see seo-audit. For structured data, see schema.

## What it can access

From a static check of the files on GitHub; nothing was run.

- [Instructions only, no scripts](https://github.com/coreyhaines31/marketingskills/tree/HEAD/skills/ai-seo)
- [License: MIT](https://github.com/coreyhaines31/marketingskills/tree/HEAD/skills/ai-seo)

## Features

- **AI visibility audit:** Tests key prompts across assistants and records citations and competitors.
- **Crawler access check:** Separates search, retrieval, training and Google product-control agents.
- **Structure patterns:** Uses answer blocks, tables and FAQs with short self-contained passages.
- **Authority signals:** Adds sourced statistics, expert attribution and freshness dates.
- **Machine-readable files:** Suggests pricing markdown, llms.txt and schema where useful.
- **Citation versus recommendation:** Treats shortlist recommendation as driven by third-party consensus.
- **Reference routing:** Points to deeper guides on attribution, accuracy and agent readiness.

## Good for

- Find out why AI answers cite a competitor instead of us
- Audit robots.txt rules for AI search and training crawlers
- Restructure comparison and FAQ pages so assistants can extract answers
- Add a machine-readable pricing page for AI agents
- Set up monthly tracking of AI citation rates

## Install

### Claude Code

This skill ships in the `marketing-skills` plugin. In Claude Code, add the marketplace and install the plugin (it may include other skills too):

```sh
/plugin marketplace add coreyhaines31/marketingskills
/plugin install marketing-skills@marketingskills
```

Or copy only this skill to `~/.claude/skills/ai-seo`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/coreyhaines31/marketingskills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/ai-seo &&
cp -R "$tmp/skills/ai-seo" ~/.claude/skills/ai-seo &&
rm -rf "$tmp"
```

For one project only, put the folder in `.claude/skills/ai-seo` inside it instead.

### Codex

Copy the skill folder to `~/.agents/skills/ai-seo` to use it in every repository:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/coreyhaines31/marketingskills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/ai-seo &&
cp -R "$tmp/skills/ai-seo" ~/.agents/skills/ai-seo &&
rm -rf "$tmp"
```

For one repository only, put the folder in `.agents/skills/ai-seo` inside it instead.

### Cursor

Copy the skill folder to `~/.cursor/skills/ai-seo` to use it in every project:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/coreyhaines31/marketingskills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/ai-seo &&
cp -R "$tmp/skills/ai-seo" ~/.cursor/skills/ai-seo &&
rm -rf "$tmp"
```

For one project only, put the folder in `.cursor/skills/ai-seo` inside it instead.

### Gemini CLI

Run in a terminal (add `--scope workspace` to install it for the current workspace only):

```sh
gemini skills install https://github.com/coreyhaines31/marketingskills.git --path skills/ai-seo
```

Or copy the folder to `~/.gemini/skills/ai-seo` yourself.

### VS Code

For GitHub Copilot in VS Code, copy the skill folder to `~/.copilot/skills/ai-seo`:

```sh
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/coreyhaines31/marketingskills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/ai-seo &&
cp -R "$tmp/skills/ai-seo" ~/.copilot/skills/ai-seo &&
rm -rf "$tmp"
```

For one project only, put the folder in `.github/skills/ai-seo` inside it instead.

### Other agents

Get the folder:

```sh
git clone --depth 1 https://github.com/coreyhaines31/marketingskills.git
```

Then copy `marketingskills/skills/ai-seo` into your agent's skills folder as `ai-seo`. Agents that support SKILL.md read one folder per skill.

## FAQ

### Is this separate from normal SEO?

No. It treats good traditional SEO as the foundation and adds structure, authority and presence on top; Google's own guidance says no special files are required.

### Does blocking a training crawler stop citations?

The skill says not to assume so: discovery, retrieval and training agents are separate controls, so check each user agent individually.

### How should I measure results?

Run each prompt several times per platform and track a mention rate with its sample size, plus delayed branded and direct visits.

### What does it avoid recommending?

Writing separate content for AI, chunking pages into fragments, mass-generating thin pages and fabricating mentions or reviews.

### How do I install AI SEO in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/ai-seo to use it in all your projects, or to .claude/skills/ai-seo in one project. Or install the marketing-skills plugin, which includes it: /plugin marketplace add coreyhaines31/marketingskills, then /plugin install marketing-skills@marketingskills.

### Does AI SEO run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

### Which AI agents can use AI SEO?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

### What are the best alternatives to AI SEO?

The closest alternatives to AI SEO are Competitor profiling, SEO audit, Link building, Product marketing and Co marketing.

## Alternatives

- [Competitor profiling](https://ai-powered.com/skills/competitor-profiling): Competitor profiling is an open-source agent skill for sales and crm.
- [SEO audit](https://ai-powered.com/skills/seo-audit-coreyhaines31): SEO audit is an open-source agent skill for marketing and seo.
- [Link building](https://ai-powered.com/skills/link-building): Link building is an open-source agent skill for marketing and seo.
- [Product marketing](https://ai-powered.com/skills/product-marketing): Product marketing is an open-source agent skill for marketing and seo.
- [Co marketing](https://ai-powered.com/skills/co-marketing): Co marketing is an open-source agent skill for marketing and seo.
- [Reverse engineer marketing](https://ai-powered.com/skills/reverse-engineer-marketing): Reverse engineer marketing is an open-source agent skill for marketing and seo.
- [Attribution](https://ai-powered.com/skills/attribution): Attribution is an open-source agent skill for marketing and seo.
- [Marketing ideas](https://ai-powered.com/skills/marketing-ideas): Marketing ideas is an open-source agent skill for marketing and seo.

---
Source: https://ai-powered.com/skills/ai-seo-coreyhaines31
