Marketing AGI skill
One skill with 14 modules for a marketer: a 0–100 site audit, copy, hooks, ads, GEO, email and launches
- 238 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill is Markdown and holds no executable code
- With an ad-generation MCP server connected, the skill hands it generation jobs and the terms come from that service
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/marketing-agiDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill is Markdown and holds no executable code
- With an ad-generation MCP server connected, the skill hands it generation jobs and the terms come from that service
This is third-party code. Review the repository files before installing.
What it does
Marketing AGI packs a marketer's work into one skill with modules. A router loads first and each task pulls only its own module, so the rest cost nothing until needed. The `audit` module checks a site or funnel and gives a weighted 0 to 100 score with a queue of fixes. `geo` looks at how citable pages are in ChatGPT, Perplexity and AI Overviews. `copy` produces 15 to 20 variants, scores them with an expert panel and strips AI slop. `hooks` builds a matrix from 18 hook tactics for ads, and `paid-ads` diagnoses fatigue of ad concepts and outputs a production brief. The other modules: `email` writes welcome sequences and launch emails in full, `social` prepares LinkedIn and X posts, `launch` gives a launch playbook including Product Hunt, `positioning` builds positioning, offer and pricing, `competitive` tears down competitors from public sources, `app-store` prepares ASO, and `analytics` reads data and plans tests. Three rules apply across all of them: score with a number, deliver a finished artifact instead of advice, and end every report by listing what could not be determined.
Who it is for. Marketers and founders with no marketing department who need an audit, copy, emails and a launch plan from one skill in Claude Code.
Good fit when
- A landing page does not convert and you need an audit scored by section with ready headline replacements
- A sequence of emails and LinkedIn and X posts is written for a product launch in one style
- Ads have gone stale and you need to see which concept is fatigued and get a brief for new ones
- You want pages cited in ChatGPT and Perplexity answers and need a GEO check
- You prepare the description, keywords and screenshot sequence before an App Store release
Not a fit when
- You need to run campaigns and change bids: the skill is Markdown and does not connect to ad accounts
- The task is narrow and covers one channel, such as only LinkedIn: the catalog has LinkedIn Marketing Skills for Claude Code and Codex
- You need a ready check with data from counters: the skill reads what you give it and does not reach analytics systems itself
Example request
Audit the landing page https://example.com and give a 0 to 100 score with a fix queue and new headlinesLimitations
Audit scores are heuristic, and the author labels each one as a heuristic. Multi-dimensional work such as audits fans out to parallel subagents when the client supports them. Without a `brand-context.md` file with the product, audience and positioning the output comes out competent but interchangeable. SKILL.md and the reference files are written in English. Claude on the web requires code execution to be enabled, and in Codex and Cursor the `skills/marketing-agi/` folder is copied by hand.
How to disable. Run `/plugin uninstall marketing-agi@marketing-agi` or delete the `marketing-agi` folder from your skills directory (`~/.claude/skills/marketing-agi/`). The `brand-context.md` file stays in your project and can be removed by hand.
FAQ
Where do I start after installing?
Copy `brand-context.template.md` to `brand-context.md`, fill it in and put it in the project root or `.claude/`. Every module reads that file: it holds the product, audience, positioning, proof, voice and constraints.
How do I put the skill into Claude on the web?
In Settings open Skills, press "+" and upload `marketing-agi.zip` from the latest release page. Code execution must be enabled for it to work.
How does the skill grade copy?
The `copy` module generates 15 to 20 variants, scores them with an expert panel and shows you only the ones that pass. A run through the `slop-patterns` catalog of AI tells then strips typical phrasings.
Can the skill create ad images?
Only if an ad-generation MCP server such as MaxFusion AI is connected: then after diagnosis and brief it produces the assets in the same session. Without such a server the output is the brief.
Does it take a lot of context?
The router weighs about two thousand tokens and a module loads on request. Fourteen modules cost nothing until you call them.
Discussion
No questions or reviews yet.
Related
SkillsMarketing Skills for AI agents
Marketing Skills for AI Agents
About fifty skills for CRO, copywriting, SEO, analytics, ads and launches, built for coding agents
AI Marketing Suite
AI Marketing Suite for Claude Code
A set of marketing skills for Claude Code: site audit, copywriting, emails, content calendars, competitor analysis and client reports
Nine skills for taking a product overseas: Meta, Google and TikTok ads, cold email, UGC, social media and a 90-day strategy.
Marketing & SEO Skills
Marketing & SEO Skills for AI Agents
A library of hundreds of marketing and SEO skills for agents: content, page types, channels, ads and strategies
Skills for positioning, content, LinkedIn, cold outreach and landing page audits with quick and deep modes
Five skill modules for Claude Code covering marketing, a creative agency, product work, webinars and release automation.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Marketing AGI (this card) | no | 238 | |
| Marketing Skills for AI agents | no | 58,756 | about fifty separate skills on CRO, SEO, ads and launches, while Marketing AGI is one skill with a router |
| AI Marketing Skills | no | 301 | the author's principles that the agent reads before copy and funnels, while Marketing AGI produces scores and finished artifacts |
| LinkedIn Marketing Skills | no | 5,672 | a narrow LinkedIn set, while here LinkedIn and X sit in the social module next to the other channels |
README in short
The author built the skill by dissecting the most-starred marketing repositories on GitHub and added what they lacked: scores on everything, finished artifacts instead of advice and an explicit list of what is undetermined. The README has a table of modules, three install routes, the principles and a note that the project has no executable code.
README badge
Original SKILL.md
--- name: marketing-agi description: A complete marketing department in one skill. Website and landing-page audits with weighted 0-100 scores, copywriting with panel scoring and AI-slop removal, an 18-tactic ad hook engine, GEO/AEO for getting cited by ChatGPT/Perplexity/AI Overviews, paid-ads creative diagnosis and production briefs, email sequences, LinkedIn/X writing, launch playbooks, positioning and offer design, competitor teardowns, app store optimization, honest analytics and test design. Use for ANY marketing task — audit, write, rewrite, diagnose, score, plan, launch, position, price, analyze — whenever the user mentions marketing, growth, conversion, copy, ads, hooks, CPM, ROAS, SEO, GEO, email, social, landing pages, funnels, launches, competitors, brand, positioning, pricing, or app stores, or says "my landing page sucks", "nobody's converting", "why are my CPMs up", "AI doesn't recommend us", "write me 20 hooks". Route via the table inside; fan out subagents for multi-dimensional work. Not for pure engineering, legal, or finance. license: MIT metadata: author: Ori Silver version: "1.2" --- # Marketing AGI One skill, fourteen modules, the full surface a working marketer touches. Built by tearing down the most-starred marketing skill repos on GitHub (48K-star collections down to 100-star craft pieces), keeping what worked, and fixing what every one of them got wrong. Three rules hold across every module, because they are what the existing ecosystem uniformly lacks: 1. **Score everything.** Findings without a number are hard to act on and easy to argue with. Every audit ends in a weighted 0-100. 2. **Ship artifacts, not advice.** Write the replacement headline, the JSON-LD block, the email, the screenshot caption. "Your headline is vague" is worthless; the rewritten headline is the deliverable. 3. **State what you couldn't determine.** Every report ends with an explicit gaps section. A stated gap is credible; a silently filled one destroys the document. ## Setup — always do this first **Read `brand-context.md`** if it exists (working directory, `.claude/`, or `.agents/`). It holds the product, ICP, positioning, proof, voice and constraints, and it changes nearly every judgement below. If absent: proceed, say the output is un-contextualised, and offer to generate the file from what you learn — `brand-context.template.md` in this skill is the blank. **Identify the task type**, then open ONLY the module file(s) needed. Do not load all references — the routing below exists so you load ~1 file, not 13. ## Routing | The user wants to... | Module | Also often needed | |---|---|---| | Audit/review/score/roast a website, landing page, funnel; "why isn't this converting" | `references/audit.md` | `audit-rubric.md` | | Get cited by ChatGPT/Perplexity/AI Overviews; GEO, AEO, llms.txt, "AI doesn't recommend us" | `references/geo.md` | `geo-engines.md` | | Write/rewrite anything: headlines, ads, pages, "make this punchier", "sounds AI-written" | `references/copy.md` | `copy-frameworks.md`, `slop-patterns.md` | | Hooks for ads/video: "write me 20 hooks", thumbstop problems, hook batches per segment | `references/hooks.md` | `paid-ads.md`, `slop-patterns.md` | | Diagnose paid ads: CPM up, ROAS down, fatigue, "what to test next", competitor's ads | `references/paid-ads.md` | `ads-diagnostics.md`, `hooks.md` | | Email: welcome/nurture/launch sequences, subject lines, deliverability | `references/email.md` | `slop-patterns.md` | | LinkedIn/X posts, personal brand, content that doesn't read as AI | `references/social.md` | `slop-patterns.md` | | Launch a product, feature, or Product Hunt run | `references/launch.md` | `copy.md` | | Positioning, category, offer design, pricing page strategy | `references/positioning.md` | — | | Tear down a competitor: site, ads, positioning | `references/competitive.md` | `paid-ads.md` | | App Store / Google Play: listing, screenshots, keywords, install rate | `references/app-store.md` | `store-specs.md` | | Read performance data honestly, design a test, "did this work?" | `references/analytics.md` | — | Multi-part requests load multiple modules. "Audit my site and rewrite the homepage" = `audit.md` then `copy.md`, carrying the audit findings forward rather than re-researching. Every de-slop pass — copy, email, social — runs `slop-patterns.md` before delivery. No exceptions. A reader who clocks output as AI-written discounts the claim, not just the prose.