AI SEO skill
Plan AI-search visibility work while separating citations, recommendations and evidence.
Community · Corey Haines| Author | Corey Haines |
|---|---|
| Licence | MIT |
| Source | coreyhaines31/marketingskills · SKILL.md on GitHub |
| Project website | marketing-skills.com |
| Works in | Claude Code · Codex, Gemini CLI, Cursor, Copilot |
| Read from the source on |
ai-seo: Plan AI-search visibility work while separating citations, recommendations and evidence.
The source routes engine-specific and time-sensitive claims to references and distinguishes published platform rules from observational studies.
From the skill's SKILL.md: # AI SEO
What it does
- Audit discoverability, content extraction and a repeatable prompt portfolio.
What you get
- Visibility audit, content recommendations and measurement plan.
When to use it
- Investigate AI citations or incorrect product descriptions.
When not to use it
- Promising that one file format or study percentage guarantees citations.
What it needs
- Current source evidence and agent research tools; external visibility platforms or APIs may require accounts and fees.
Files in the skill
| File or folder | What it is for |
|---|---|
SKILL.md | Entry instructions and task-specific workflow. |
Licence as found in the repository on 2026-11-16: MIT.
Example prompts
Type one of these after installing; naming the skill makes sure it is used.
- Audit citation and recommendation separately.
- Build a repeatable prompt portfolio.
- Trace an incorrect AI product claim to its source.
How to install ai-seo
Prepare the workflow
Copy the complete skill with references. Configure research/measurement tools separately and recheck dated platform claims before repeating them.
A skill is a folder with a SKILL.md file. You install it once; the agent reads its short description at the start of each session and loads the full instructions only when a request matches. Pick the place you use:
Claude Code: copy the folder into your skills folder
Put the skill's folder in ~/.claude/skills/ to use it in every project on this computer, or in .claude/skills/ inside a repository to share it with everyone who works there (commit it).
git clone --depth 1 https://github.com/coreyhaines31/marketingskills.git
mkdir -p ~/.claude/skills
cp -R marketingskills/skills/ai-seo ~/.claude/skills/Claude Code notices new or changed skills in these folders during the session. If the skills folder did not exist when the session started, run /reload-skills once. Then type /ai-seo or just describe the task.
On Windows, run the commands in Git Bash or WSL, or copy the folder into the same place with File Explorer.
Codex, Gemini CLI, Cursor and GitHub Copilot
These agents read the same SKILL.md folders. The one folder all four accept inside a project is .agents/skills/, so this copies the skill there:
git clone --depth 1 https://github.com/coreyhaines31/marketingskills.git
mkdir -p .agents/skills
cp -R marketingskills/skills/ai-seo .agents/skills/| Agent | Project folder | Your user folder | Notes |
|---|---|---|---|
| OpenAI Codex | .agents/skills/ | ~/.agents/skills/ | Type $ or run /skills to pick a skill; Codex also chooses one when your task matches. |
| Gemini CLI | .agents/skills/.gemini/skills/ | ~/.agents/skills/~/.gemini/skills/ | Or install from Git with gemini skills install <git URL> --path <folder> --consent. Google replaced Gemini CLI with Antigravity CLI for free-tier and Google One users on 18 June 2026; Antigravity uses .agents/skills/ in a project and ~/.gemini/config/skills/ for you. |
| Cursor | .agents/skills/.cursor/skills/ | ~/.agents/skills/~/.cursor/skills/ | Type / in Agent chat to pick a skill. Cursor also reads Claude Code's .claude/skills/ folders. |
| GitHub Copilot | .github/skills/.agents/skills/.claude/skills/ | ~/.copilot/skills/~/.agents/skills/ | Works in Copilot CLI, the cloud agent, and agent mode in VS Code, Visual Studio and JetBrains (IDE support depends on the version). Or run gh skill install OWNER/REPOSITORY SKILL (public preview, GitHub CLI 2.90.0 or later). |
Sources for these steps
Checked against each vendor's documentation on 2026-11-14:
Evidence changes by platform
Use official platform documentation for eligibility and crawler controls. Treat vendor datasets and case studies as bounded observations, with date, market and methodology recorded.
Measure repeated scenarios
Prompt samples, engines and dates matter. Referral visits alone can miss delayed behavior, while one successful answer does not establish a stable trend.
Questions about ai-seo
Does this website execute the skill?
No. This is a source-based installation guide. Your agent runs the skill in its own configured environment.
Are full cloud workflows verified here?
No. Generic cloud upload and API execution steps are omitted; source-specific local requirements and host capabilities still apply.
Does a citation mean a recommendation?
No. A brand may be cited without being shortlisted or recommended. Track those outcomes separately.
Does llms.txt guarantee AI visibility?
No. Discovery files and content formats are hypotheses or platform-dependent aids, not a universal ranking requirement.
More AI skills
Related skills
Schema Markup skill
Community · Corey HainesImplement and validate JSON-LD that matches visible page content.SEO Audit skill
Community · Corey HainesDiagnose crawlability, indexing and on-page problems with traceable evidence.Content Strategy skill
Community · Corey HainesPlan evidence-backed topics, clusters and distribution around the audience’s needs.Free Tools skill
Community · Corey HainesEvaluate free-tool ideas against user value, business fit and maintenance cost.Programmatic SEO skill
Community · Corey HainesPlan data-driven page sets with unique value, clean URLs and internal links.Site Architecture skill
Community · Corey HainesDesign page hierarchy, navigation, URL maps and useful internal linking.