Guide · Agent skill
How to use the CRO Advisor agent skill: setup and examples
Updated · written with AI from the project's own documentation and checked against our catalogue data
CRO Advisor is an agent skill that makes an AI agent answer revenue strategy questions the way a chief revenue officer would for a B2B software company. This guide explains what agent skills are, how to install the cro-advisor skill, how to trigger it, and what its two bundled Python scripts need. By the end you will be able to ask the agent for a revenue review and run the forecast and churn tools on your own CSV data.
Quick start
- 1Download the ZIP. Download the cro-advisor ZIP from this page.
- 2Unzip the skill. Unzip it into ~/.claude/skills/ for a personal install, or into a project's .claude/skills/ folder.
- 3Or upload in the Claude apps. In the Claude apps, go to Settings → Capabilities → Skills and upload the ZIP.
- 4Ask a revenue question. Describe your situation in plain language, mentioning NRR, pipeline, churn or pricing as relevant.
- 5Answer the diagnostic questions. The agent will ask about NRR, GRR, pipeline coverage, quota attainment and pricing. Provide your figures.
- 6Run a script on your CSV. Install nothing extra; run python scripts/revenue_forecast_model.py or python scripts/churn_analyzer.py with your data file, after checking its expected format.
What an agent skill is and what cro-advisor makes the agent do
An agent skill is a folder of instructions and reference files that an AI agent loads when a task matches the skill's description. The cro-advisor skill is written for revenue leadership at B2B SaaS companies: revenue forecasting, sales model design, pricing strategy, net revenue retention (NRR), and sales team scaling.
Once installed, the agent asks diagnostic questions before recommending anything. These cover NRR, what share of ARR comes from expansion versus new logos, pipeline coverage against quota, quota attainment, and pricing pushback. It then applies playbooks from its reference files on pricing, sales models, retention and board reporting.
- SKILL.md: the main instructions and diagnostic questions
- references/sales_playbook.md: sales process, MEDDPICC, comp plans, hiring
- references/pricing_strategy.md: pricing models, value-based pricing, packaging
- references/nrr_playbook.md: NRR deep dive, churn anatomy, health scoring, expansion
- scripts/revenue_forecast_model.py: weighted pipeline forecast with conservative, base and upside scenarios
- scripts/churn_analyzer.py: NRR, GRR, cohort retention, at-risk accounts
Install the cro-advisor skill
Download the cro-advisor ZIP from this page and unzip it. For a personal install that applies to all your projects, place the skill folder in ~/.claude/skills/. To limit it to one project, place it in that project's .claude/skills/ folder.
If you use the Claude apps instead, go to Settings → Capabilities → Skills and upload the ZIP there.
- Personal install: ~/.claude/skills/cro-advisor/
- Project install: .claude/skills/cro-advisor/ inside your project
- Claude apps: Settings → Capabilities → Skills, then upload the ZIP
Trigger the skill with natural requests
You do not need a special command. The skill's description lists the situations it applies to, so ask in plain language about the topic. Mentioning terms such as CRO, chief revenue officer, revenue strategy, sales model, ARR growth, NRR, expansion revenue, churn, pricing strategy or sales capacity helps the agent match the skill.
The skill's own output list shows the kinds of results to expect for common requests: a pipeline-based forecast, a cohort churn analysis with at-risk accounts, a pricing review, a capacity model for scaling sales, and a revenue board section.
- "Review our revenue engine. Our NRR is 96% and pipeline coverage is 2.5x."
- "Forecast next quarter from this pipeline export."
- "Analyze our churn using this customer ARR file."
- "Help me set quotas and ramp plans for four new account executives."
- "Draft the revenue section for our board deck."
Run the forecast and churn scripts on your own data
The skill includes two command-line scripts. Both use only the Python 3 standard library, so you do not install extra packages. To run them on your own numbers, you need a CSV of pipeline deals or customer ARR data. The skill's quick start shows the commands below; check each script's header or help output for the input format it expects before you run it on real data.
The scripts run locally. The skill does not use the network.
python scripts/revenue_forecast_model.py
python scripts/churn_analyzer.pySafety notes on scripts and data
The skill runs scripts, so read them before running them on sensitive files. The skill's metadata says it runs scripts and does not use the network. Keep customer data in your own environment and do not paste credentials or personal data into prompts that you would not share with the agent.
The benchmarks are generic rules of thumb. Treat outputs as a structured starting point for discussion, not as final financial, legal or pricing decisions. Have a qualified finance professional review them before acting.
- The scripts use only the Python 3 standard library and no network access is stated in the skill
- Check the CSV you feed in for customer names or personal data you do not need to share
- Review the forecast with finance before it goes into board materials
Tips for better results
Give the agent real numbers. The diagnostic questions depend on figures such as NRR, pipeline coverage, win rate and quota attainment, and answers improve when you supply them. Ask for the explicit pipeline math, since the skill is written to show conversion rates at each stage.
Ask one area at a time. A focused request about pricing or churn gets a more usable answer than a request to fix the whole company.
- State your segment (for example, SMB or enterprise) and business model (PLG, sales-led or hybrid)
- Compare your figures against the NRR and magic number benchmarks in the skill
- Use the scripts for numbers and the agent for interpretation
What people use it for
- Reviewing whether NRR is healthy enough to justify more sales hiring
- Preparing a board forecast with conservative, base and upside scenarios
- Modelling churn by cohort and listing at-risk accounts from a customer ARR file
- Designing quota, ramp and territory plans for a growing sales team
- Checking whether pricing is too low based on prospect pushback
Frequently asked questions
How do I install the cro-advisor agent skill?
Download the cro-advisor ZIP from this page and unzip it into ~/.claude/skills/ for a personal install, or into a project's .claude/skills/ folder. In the Claude apps, you can instead upload the ZIP under Settings → Capabilities → Skills.
What does the cro-advisor skill need to run?
It needs Python 3. The scripts use only the standard library, so no extra packages are required. To run the scripts on your own numbers you need a CSV of pipeline deals or customer ARR data.
Is the cro-advisor skill free to use?
The skill is released under the MIT licence, as stated on its page. Check the LICENSE file in the repository for the full terms.
Does cro-advisor work for consumer or non-SaaS businesses?
It is not designed for them. The benchmarks and models assume recurring subscription revenue, and the benchmarks may mislead outside B2B SaaS.
Does the skill send my data over the network?
The skill's metadata says it does not use the network. Its scripts run locally on the files you provide, so review the scripts and keep sensitive data in your own environment.
What should I do if the agent does not use the skill?
Mention a specific trigger term from the skill's description, such as NRR, chief revenue officer, pipeline coverage or churn, and confirm the folder sits in the correct skills directory. If the scripts fail, check that Python 3 is installed and that your CSV matches the format the script expects.
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
Use cro-advisor if you run or advise a B2B SaaS company and want a structured review of your revenue engine, forecast or retention numbers. Pick something else if your business is consumer or non-subscription, or if you need final financial, legal or pricing decisions made without a qualified finance professional's review.
Download the skill