Guide · Agent skill
How to use the CMO Advisor agent skill
Updated · written with AI from the project's own documentation and checked against our catalogue data
The CMO Advisor is an agent skill that gives an AI agent the working habits of a chief marketing officer at a scaling company. Once it is installed, the agent can answer questions about brand positioning, growth models, marketing budgets and marketing team structure. This guide explains what the skill does, how to install it, how to trigger it with plain requests, and what to check before you rely on its output.
CMO Advisoralirezarezvani/claude-skills · MIT Download the skill Quick start
- 1Download the ZIP. Download the cmo-advisor ZIP from this page and unzip it. Confirm the folder contains SKILL.md, references and scripts.
- 2Place the skill folder. Move the unzipped folder into ~/.claude/skills/ for personal use, or into the project's .claude/skills/ folder for one project.
- 3Or upload it in the Claude apps. If you use the Claude apps, open Settings, go to Capabilities, then Skills, and upload the skill.
- 4Ask a strategy question. Describe your company, stage, product and known metrics, then ask a question about positioning, growth model, budget or team structure.
- 5Edit the script inputs. Before running either script, open it and replace the example values in the INPUTS section with your own CAC, conversion rates and churn.
- 6Run the scripts with Python 3. Run python scripts/marketing_budget_modeler.py or python scripts/growth_model_simulator.py from the skill folder, then check the outputs against your own data.
What the CMO Advisor skill makes the agent do
An agent skill is a folder of instructions and reference files that an AI agent loads when a request matches the skill's description. The CMO Advisor is strategy only. It is built around four questions: who the company is for, why customers choose it, how they find it, and whether marketing is working.
When the skill is active, the agent works backward from revenue targets to the leads and spend needed to reach them. It pushes for channel-level CAC, LTV:CAC and payback period rather than vanity numbers. The skill also includes two Python scripts that model budget scenarios and projected monthly recurring revenue (MRR) growth.
- Brand positioning and category design, with a reference file on messaging and competitive positioning
- Growth model selection between product-led (PLG), sales-led (SLG), community-led (CLG) and hybrid, with playbooks for each
- Marketing budget allocation from revenue target to required customers, conversion rates, MQLs and channel spend
- Marketing org design by company stage, including hiring sequence and agency versus in-house choices
- Board reporting on pipeline contribution, CAC by channel, payback period and LTV:CAC
Install the cmo-advisor skill from the ZIP
Download the cmo-advisor ZIP from this page and unzip it. The skill folder contains SKILL.md, the references folder and the scripts folder. Put that folder where your agent looks for skills. For a personal setup, use ~/.claude/skills/. For a single project, use the .claude/skills/ folder inside the project.
If you use the Claude apps rather than a folder-based setup, you can upload the skill instead. Open Settings, go to Capabilities, then Skills, and upload the skill there.
- Personal install: unzip into ~/.claude/skills/
- Project install: unzip into the project's .claude/skills/ folder
- Claude apps: Settings → Capabilities → Skills, then upload
Trigger the skill with natural requests
You do not need a special command. The skill's description lists the situations it covers, so the agent loads it when your request matches. Requests that mention CMO, brand strategy, growth model, CAC, LTV, channel mix or marketing ROI are the clearest triggers. Describe your company, stage, product and the numbers you have, because the advice depends on them.
The skill's own outputs follow the kind of request you make. A budget request should yield a channel allocation model with CAC targets per channel. A positioning request should yield a positioning map, messaging framework and proof points. A growth model request should yield a growth projection with channel mix scenarios.
- "We are a 40-person B2B software company. Should we grow product-led or sales-led? Our ACV is high and buyers are IT leads."
- "Plan our marketing budget for next year. We spend 300k across paid search, events and outbound. Our blended CAC is 4,000."
- "Position us against two larger competitors and give me a messaging framework."
- "Build a hiring plan for the marketing team at our Series A stage."
- "Prepare the marketing section of the board deck with pipeline contribution and channel CAC."
Run the budget and growth scripts
The skill includes two scripts. marketing_budget_modeler.py models budget allocation across channels and projects MQL output by scenario. growth_model_simulator.py projects MRR growth by model and shows the effect of channel mix shifts. Both are run from the skill folder with Python 3 and use only the standard library, according to their imports.
Before you run either script, open it and edit the INPUTS section with your own company metrics, such as CAC, conversion rates and churn. The outputs depend entirely on those inputs. The example values in the scripts are estimates, not verified company data, so do not make spending decisions from the output alone.
- Requires Python 3
- Edit the INPUTS section of each script before running
- Scripts run locally; the skill does not use the network
python scripts/marketing_budget_modeler.py
python scripts/growth_model_simulator.pySafety notes: scripts and network use
The skill runs scripts, so read them before you run them, as you would with any code you download. The skill is documented as not using the network, which means the scripts do not send your data elsewhere. Your company metrics stay in the files on your machine unless you share them through your agent.
Treat the script outputs as a model, not a forecast. The skill itself says that its outputs depend on the example inputs the user types in, which are estimates. Check any figure that goes into a board report or budget against your own CRM and finance data.
- Review the scripts before running them
- Replace the example inputs with your real numbers
- Verify outputs against CRM and finance data before acting on them
Tips for getting useful answers
The skill asks for specifics, and the answers improve with them. Give channel-level CAC rather than a blended number, the payback period on your largest channel, and your LTV:CAC ratio if you know it. The skill's diagnostic questions also ask where your best customers come from and why prospects don't buy.
Use the skill as a reviewer for your plans as well as a generator. Ask it to critique a draft strategy from the customer's perspective, since the skill's reasoning method is to draft, critique and refine.
- Give channel-level CAC, not only a blended figure
- Tell the agent whether the work is brand or performance marketing, since they have different timelines and metrics
- Ask for a critique of your draft strategy, not only a new one
- Keep execution requests for other skills; this one covers strategy
What people use it for
- A founder at a scaling B2B company decides whether customers should find them through a free product, a sales team or a community.
- A marketing lead plans next year's budget by splitting spend across channels, with CAC targets for each channel.
- A marketing team reviews a draft positioning statement and asks for a critique and proof points.
- A head of marketing prepares board reporting on pipeline contribution, channel CAC and payback period.
Frequently asked questions
Is the CMO Advisor agent skill free to use?
The skill is published under the MIT licence, which is stated in its SKILL.md. Check the licence file in the download for the full terms before you use it in commercial work.
What do I need to run the CMO Advisor skill?
You need an agent that supports skills and Python 3 to run the two included scripts. The scripts use only the standard library, according to their imports. You also need your own company metrics, such as CAC, conversion rates and churn, entered into the INPUTS section of each script.
Where do I install the cmo-advisor skill?
Unzip the downloaded folder into ~/.claude/skills/ for personal use or into the project's .claude/skills/ folder for one project. In the Claude apps, you can instead upload it under Settings, then Capabilities, then Skills.
Does the CMO Advisor skill write ad copy, campaigns or social posts?
No. The skill covers strategy only. Its documentation says that campaign execution and content creation are handled by other skills.
Does the skill use the internet?
The skill is documented as not using the network. It does run Python scripts, so review them before running and replace the example inputs with your own data.
Can I trust the numbers from the budget and growth scripts?
Only as a model. The outputs depend on the inputs you enter, and the example values are estimates rather than verified company data. Check any figure against your CRM and finance records before making a spending decision.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
The CMO Advisor is a good fit for founders and small teams at scaling B2B companies who need to decide how customers find them, and for marketing leads planning budgets, channel mix or board reporting. It is not the right choice if you need campaign, ad copy or social content, or if you expect the scripts to produce verified forecasts without entering your own data carefully.
Download the skill