Yuzzyuk/marketing-os

An entire marketing department as one Claude skill. 14 modules: audits scored 0-100, an 18-tactic hook engine, copy graded before you see it, ad diagnosis, GEO, email, launches, pricing. Works in Claude, Codex and Cursor.

What it solves

Marketing OS is a comprehensive set of AI agent skills designed to replace generic AI marketing advice with structured, score-based audits and production-ready artifacts. It transforms a general-purpose LLM into a specialized marketing engine that can perform detailed audits, generate high-converting copy, and produce specific deliverables like ad briefs or email sequences.

How it works

The project consists of 14 specialized modules (such as audit, geo, copy, and positioning) that are delivered as pure markdown files. These modules act as instructions for AI agents (like Claude Code or Cursor) to follow. By using a brand-context file, the agent can tailor its output to a specific brand identity. The system uses a "progressive disclosure" design, meaning the agent only loads the specific module needed for a task to save tokens. If connected to an external tool like Arcads, it can move from diagnosis to asset production directly.

Who it’s for

For marketers, founders, and AI agent users who want a professional-grade marketing workflow that produces concrete artifacts rather than generic advice.

Highlights

  • Comprehensive Module Set: Covers everything from AI-search citability (GEO) and ASO diagnosis to competitive teardowns and competitive positioning.
  • Score-Based Evaluation: Replaces vague advice with weighted scores (0-100) and prioritized fixes.
  • Curbing AI Slop: Includes a dedicated "slop-patterns" catalogue to identify and remove typical AI-generated prose patterns.
  • Subagent-Native: Designed to fan out complex tasks in parallel when supported by the host agent.
  • No Executable Code: Built entirely in markdown for security and transparency.

Related

  • Project
    coreyhaines31/marketingskills

    A collection of AI agent skills that provide specialized marketing knowledge and workflows for tasks like SEO, copywriting, and conversion optimization.

  • Project
    nowork-studio/notfair-plugin

    A library of open-source marketing skills and workflows that enable AI agents to perform professional SEO, GEO, and paid media audits using live platform data.

  • Project
    msitarzewski/agency-agents

    A comprehensive library of specialized AI agent personalities and installation tools to transform generic LLMs into domain-specific experts across engineering, design, and marketing.

  • Project
    aaron-he-zhu/aaron-marketing-skills

    An installable AI marketing staff consisting of 120 agent skills across seven disciplines, providing a structured, benchmark-driven approach to brand strategy and campaign execution.

  • Project
    nexscope-ai/Amazon-Skills

    A collection of 53 plain-text AI agent skills that provide LLMs with specialized expertise in Amazon selling, from keyword research to FBA profit calculations.