# AI use cases for Marketing OS (Yuzzyuk/marketing-os) Repo: [Yuzzyuk/marketing-os](https://github.com/Yuzzyuk/marketing-os) | Use cases: 5 | Page: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/ Marketing OS is a pure-markdown agent skill with 14 modules that covers audits, copy, hooks, ads, GEO, email, launches, pricing and analytics. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Score a website funnel and get prioritized fixes: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/score-website-funnel-audit/ - Diagnose ad fatigue and brief the next creatives: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/diagnose-ad-fatigue-production-brief/ - Generate and grade 20 copy variants before review: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/grade-copy-variants-before-publishing/ - Build a hook matrix from 18 hook tactics: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/build-hook-matrix-for-short-video/ - Check how citable a page is for AI search: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/check-ai-search-citability-of-a-page/ ## How to score a website funnel and get prioritized fixes with Marketing OS Repo: [Yuzzyuk/marketing-os](https://github.com/Yuzzyuk/marketing-os) | Difficulty: Intermediate | Time: PT30M | Basis: From the README Get a weighted 0-100 funnel audit with a ranked list of fixes in one agent session. **Who it is for:** A founder or marketing lead whose landing page or signup funnel is converting poorly and who needs a clear list of what to fix first. **The problem:** Generic advice about a funnel is hard to rank and hard to act on, so teams fix the wrong things. **The outcome:** A scored audit with prioritized fixes and a section listing what the audit could not determine. ### Steps 1. Install the skill in Claude Code with `/plugin marketplace add Yuzzyuk/marketing-os`, then run `/plugin install marketing-os@marketing-os`. 2. Copy brand-context.template.md to brand-context.md, fill it in, and place it in your project root or .claude/ folder. 3. Ask the agent to run the audit module on the URL of the page or funnel you want reviewed. 4. Read the weighted 0-100 score and the prioritized fixes. 5. Check the section on what could not be determined before acting on any fix. ### Prompt to paste into your agent ```text Using the marketing-os skill in the Yuzzyuk/marketing-os repo, run the audit module on and return the weighted 0-100 score with prioritized fixes. Verify that the report includes a what-I-couldn't-determine section and that the score is labeled as a heuristic. ``` ### Caveat The 0-100 score is a heuristic the README labels as such, so use it to rank fixes rather than as a measured benchmark. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/score-website-funnel-audit/ ## How to diagnose ad fatigue and brief the next creatives with Marketing OS Repo: [Yuzzyuk/marketing-os](https://github.com/Yuzzyuk/marketing-os) | Difficulty: Advanced | Time: PT60M | Basis: From the README Find which ad concepts are fatigued and get a ranked brief for the next batch. **Who it is for:** A paid media manager whose ad performance is dropping and who needs to know which concepts to replace and what to make next. **The problem:** Running ads keep losing results and the team cannot tell whether the audience, the offer or the creative concept is wearing out. **The outcome:** A concept-level fatigue diagnosis and a ranked production brief, with generated assets if an ad MCP is connected. ### Steps 1. Install the skill in Claude Code with `/plugin marketplace add Yuzzyuk/marketing-os`, then run `/plugin install marketing-os@marketing-os`. 2. Fill in brand-context.md so the paid-ads module knows your brand and offer. 3. Ask the agent to run the paid-ads module on your current ad performance data for . 4. Review the concept-level fatigue diagnosis and the ranked production brief. 5. If you have an ad-generation MCP such as Arcads connected, ask the agent to produce the briefed assets from the brief. ### Prompt to paste into your agent ```text Using the marketing-os skill in the Yuzzyuk/marketing-os repo, run the paid-ads module on the performance data for and return a concept-level fatigue diagnosis with a ranked production brief. Verify that each ranked brief item names the concept it replaces and that no winner is declared from a handful of conversions. ``` ### Caveat Asset generation only runs if an ad-generation MCP such as Arcads is connected, and the README does not describe any other ad platform integration. Risk, credentials: Connecting an ad-generation MCP such as Arcads means you manage that service's account and credentials, so use keys scoped to the task and rotate them when the work ends. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/diagnose-ad-fatigue-production-brief/ ## How to generate and grade 20 copy variants before review with Marketing OS Repo: [Yuzzyuk/marketing-os](https://github.com/Yuzzyuk/marketing-os) | Difficulty: Intermediate | Time: PT30M | Basis: From the README Produce 15-20 copy variants, score them with an expert panel, and strip AI-sounding phrasing. **Who it is for:** A copywriter or content lead who needs ad, landing page or email copy fast and wants weak drafts removed before anyone reads them. **The problem:** Writing many variants by hand is slow, and most drafts sound generic or AI-written. **The outcome:** A scored shortlist of copy variants with AI-tell phrasing removed. ### Steps 1. Install the skill in Claude Code with `/plugin marketplace add Yuzzyuk/marketing-os`, then run `/plugin install marketing-os@marketing-os`. 2. Fill in brand-context.md with your voice, audience and offer. 3. Ask the agent to run the copy module on to generate 15-20 variants. 4. Read the expert-panel scores and keep the top variants. 5. Check the de-slopped output for remaining phrasing you would not publish. ### Prompt to paste into your agent ```text Using the marketing-os skill in the Yuzzyuk/marketing-os repo, run the copy module on the brief for and return 15-20 variants with expert-panel scores and de-slopped text. Verify that the top variants are ranked by score and that the scores are described as heuristics. ``` ### Caveat The expert-panel score is a heuristic, so the final pick still needs a human read against your brand voice. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/grade-copy-variants-before-publishing/ ## How to build a hook matrix from 18 hook tactics with Marketing OS Repo: [Yuzzyuk/marketing-os](https://github.com/Yuzzyuk/marketing-os) | Difficulty: Intermediate | Time: PT30M | Basis: From the README Turn one offer into a hook matrix and a diagnostic funnel for testing openings. **Who it is for:** A social or video marketer who has to produce many opening hooks for one product and wants a structured set to test. **The problem:** Hook ideas tend to repeat the same tactic, so the test set teaches little about which opening works. **The outcome:** A hook matrix spanning the 18 tactics and a diagnostic funnel for choosing which hooks to test. ### Steps 1. Install the skill in Claude Code with `/plugin marketplace add Yuzzyuk/marketing-os`, then run `/plugin install marketing-os@marketing-os`. 2. Fill in brand-context.md with the product, audience and proof you are allowed to use. 3. Ask the agent to run the hooks module on to produce the 18-tactic hook matrix. 4. Review the diagnostic funnel and pick the hooks to test first. 5. Record which tactic each hook used so results map back to tactics. ### Prompt to paste into your agent ```text Using the marketing-os skill in the Yuzzyuk/marketing-os repo, run the hooks module on and return the 18-tactic hook matrix and the diagnostic funnel. Verify that no hook claims proof that is absent from brand-context.md. ``` ### Caveat The README does not say how the hook matrix performs in any particular platform, so treat the output as a test plan rather than a forecast. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/build-hook-matrix-for-short-video/ ## How to check how citable a page is for AI search with Marketing OS Repo: [Yuzzyuk/marketing-os](https://github.com/Yuzzyuk/marketing-os) | Difficulty: Intermediate | Time: PT15M | Basis: From the README Assess a page for AI-search citability across ChatGPT, Perplexity and AI Overviews. **Who it is for:** A content or SEO lead who wants their product pages to be quoted by AI answer engines and needs to know what to change. **The problem:** Pages written for search rankings are not always easy for AI answer engines to quote accurately. **The outcome:** A GEO report on the page's AI-search citability with specific changes to make. ### Steps 1. Install the skill in Claude Code with `/plugin marketplace add Yuzzyuk/marketing-os`, then run `/plugin install marketing-os@marketing-os`. 2. Ask the agent to run the geo module on the page at . 3. Read the citability assessment for ChatGPT, Perplexity and AI Overviews. 4. Apply the suggested edits to the page text. 5. Re-run the module after the edits to compare the two reports. ### Prompt to paste into your agent ```text Using the marketing-os skill in the Yuzzyuk/marketing-os repo, run the geo module on and return a citability assessment with specific edits. Verify that the report separates what was determined from what could not be determined. ``` ### Caveat The README describes citability as an assessment, so it does not promise that any AI engine will cite the page after edits. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/yuzzyuk-marketing-os/check-ai-search-citability-of-a-page/