Marketing Skills is a collection of skills for AI coding agents that assist with conversion optimization, copywriting, SEO, analytics, and growth engineering. Technical marketers and founders use it to apply agents to marketing work in tools such as Claude Code, OpenAI Codex, Cursor, and Windsurf. The catalogue entries are the project's own marketing skills and instructions.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add coreyhaines31/marketingskills --skill ai-seogit clone --depth 1 https://github.com/coreyhaines31/marketingskillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/coreyhaines31/marketingskills/ai-seo)<a href="https://agentmods.dev/skills/coreyhaines31/marketingskills/ai-seo"><img src="https://agentmods.dev/badge/skills/coreyhaines31/marketingskills/ai-seo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/coreyhaines31/marketingskills/ai-seo"><img src="https://agentmods.dev/badge/skills/coreyhaines31/marketingskills/ai-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 278 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00253 | $0.08127 |
| Opus 5.5 | $0.00101 | $0.03251 |
| Sonnet 5.5 | $0.00051 | $0.01625 |
| Haiku 4.5 | $0.00025 | $0.00813 |
Grade A, and why
ai-seo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
8 near-identical copies found in the catalogue:
- ai-seo — 100% identical, 156 lines differ
- ai-seo — 88% identical, 165 lines differ
- ai-seo — 88% identical, 165 lines differ
- ai-seo — 84% identical, 158 lines differ
- ai-seo — 84% identical, 162 lines differ
- ai-seo — 84% identical, 173 lines differ
- ai-seo — 84% identical, 10 lines differ
- ai-seo — 84% identical, 162 lines differ
How it starts
The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI SEO
You are an expert in AI search optimization — the practice of making content discoverable, extractable, and citable by AI systems including Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and Copilot. Your goal is to help users get their content cited as a source in AI-generated answers.
Reference Routing
Start with this skill's core workflow. Open a reference when the user's question needs that detail; read additional references only when their topics are relevant.
| User questions | Local reference |
|---|---|
| Why can an agent not read our site? Are bot access, discovery files, or HTML blocking it? Can an agent sign up or check out for the user, through WebMCP or a skill file for our product? | Agent readiness |
| AI barely shows up in referrals. How do we measure delayed visits, branded search, and pipeline from AI answers? | AI attribution |
| Is AI saying something wrong about our price, features, or limits? How do we find and fix the source? | Answer accuracy |
| Which vendor does Claude Code or Cursor pick when a user says "deploy this"? How do we become the tool an agent installs mid-task? | Agent defaults |
| Why are we cited but absent from the shortlist? Can our own buyer's guide help competitors? How should we measure recommendations? | Citations vs. recommendations |
| How should we structure a definition, comparison, or FAQ? What makes an answer block useful on its own? | Content patterns |
| How does the approach differ for product pages, docs, local businesses, or ecommerce? Which content type should we improve? | Content types |
| Did an engine change which page formats it cites? Should we still invest in listicles or comparison pages? How do we separate a shift from noisy measurements? | Format volatility |
| Should we publish LinkedIn posts, articles, or company-page content? What makes that content discoverable and citable? | LinkedIn citations |
| How do we run AEO in other languages and countries? Is ChatGPT Shopping worth it for our product? | Multilingual and commerce |
| What belongs in an OKF bundle? Is it an established AI-search requirement or an emerging experiment? | Open Knowledge Format |
| Which prompts should we track, how often, which topics are we losing, and how do we test multi-turn buying conversations? | Prompt portfolio |
| Where should we start for a particular AI engine? Which search and training crawlers should we distinguish? | Platform ranking factors |
| Why does AI describe our positioning incorrectly? How can third-party consensus reinforce a specific use case? | Positioning and consensus |
| How should a video's title, captions, chapters, or description support citations? What should we check before publishing? | YouTube citations |
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 20 KB
- references/agent-defaults.md 9.1 KB
- references/agent-readiness.md 17 KB
- references/ai-attribution.md 4.2 KB
- references/answer-accuracy.md 5.6 KB
- references/citations-vs-recommendations.md 13 KB
- references/content-patterns.md 13 KB
- references/content-types.md 3.5 KB
- references/format-volatility.md 7.1 KB
- references/linkedin-ai-citations.md 8.5 KB
- references/multilingual-and-commerce.md 4.8 KB
- references/okf.md 5.8 KB
- references/platform-ranking-factors.md 16 KB
- references/positioning-and-consensus.md 7.1 KB
- references/prompt-portfolio.md 7.5 KB
- references/youtube-ai-citations.md 4.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed 8e5532f13d06
- 10d ago Changed 01de1dc92839
- 18d ago Changed · +1 lines 1293062b48ce
- 22d ago Changed 8db51a80d71f
- 23d ago Changed · +1 lines 9d45b6d4d639
- 29d ago Changed · +11 lines 97424245fab1
- 1mo ago Changed · +1 lines fec6de3d2b3f
- 1mo ago Changed 5031aca0c1b8
- 1mo ago Changed · -2 lines · +17 tokens per session a4a7d43a0285
- 1mo ago First seen · 489 lines · 236 tokens per session scan A b1ecd93ebc65
ai-seo is a skill published in the GitHub repository coreyhaines31/marketingskills (58,740 stars, last pushed 2d ago), licensed MIT. It adds 253 tokens to every session and 8,127 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
ai-seo compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-seocoreyhaines31/marketingskills | Skill | 59k | 2d ago | MIT | A | 253 | Claude Code |
| marketing-skillsh3rb3rn/moe-sovereign | Skill | 11 | 1mo ago | Apache-2.0 | A | 66 | Claude Code, Codex |
| marketing-skillsferdinandruthben12-dotcom/535-skills | Skill | 2 | 2mo ago | none | A | 66 | Claude Code |
| marketing-skillsartubss/SKILLS-CLAUDE-CODE | Skill | 11 | 5mo ago | none | A | 55 | Claude Code, Codex |
| magazine-web-pptnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 67 | Claude Code, Codex |
| html-ppt-zhangzara-coralnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 55 | Claude Code, Codex |
| product-launchgenspark-ai/genoffice | Skill | 12k | yesterday | Apache-2.0 | A | 27 | Claude Code, Codex |