Guide · Agent skill

How to use the Chief Data Officer Advisor agent skill

Updated 2026-10-29 · written with AI from the project's own documentation and checked against our catalogue data

The Chief Data Officer Advisor is an agent skill that makes an AI agent answer strategic data-leadership questions the way a chief data officer would. It is written for startup founders and early leaders who do not have a CDO yet and need a structured way to decide things like whether they can train a model on customer data. After this guide you will know what the skill does, how to install it, how to phrase requests so it activates, and what to check before trusting its output.

Chief Data Officer Advisoralirezarezvani/claude-skills · MIT Download the skill

Quick start

1Download the ZIP. Download the skill ZIP from this page.
2Unzip into a skills folder. Unzip it into ~/.claude/skills/ for personal use, or into a project's .claude/skills/ folder for one project.
3Or upload in the Claude apps. In the Claude apps, go to Settings → Capabilities → Skills and upload the skill.
4Ask a strategic data question. Describe a decision such as training on customer data or choosing an architecture, using terms like data strategy or training data.
5Provide optional input files. For a sharper result, prepare a JSON file describing your sources, company profile or corpus and pass it to the matching script.
6Check the output with counsel. Treat any legal or consent conclusion as a starting point and confirm it with qualified counsel.

What is an agent skill?

An agent skill is a folder of instructions, reference documents and optional scripts that an AI agent loads when a task matches the skill's description. The agent reads the skill's SKILL.md file to decide when and how to use it.

This skill is licensed under MIT and its main instruction file is SKILL.md, supported by reference frameworks and three Python tools.

What the skill makes the agent do

Once installed, the agent handles four kinds of strategic decision: whether training a model on a given data source is allowed and how risky it is, whether to choose a warehouse, lakehouse or data mesh, how to value customer data for fundraising or acquisition, and which data role to hire next.

The skill bundles reference frameworks on AI training data rights, data product strategy, customer data as an asset and data team organisation. It also includes three small Python tools that score a described data inventory, company profile or customer corpus and return a recommendation.

AI training data rights: origin, data class and use case, with GO, MITIGATE or NO-GO verdicts
Data product strategy: warehouse vs lakehouse vs mesh, plus build-vs-buy per layer
Customer data as asset: strategic value, M&A considerations and productization paths
Data team evolution: which role to hire next and when to centralise vs embed

Install the skill

Download the ZIP of the skill from this page and unzip it. You can install it in one of two places, depending on whether you want it for all your projects or just one.

For a personal install available across projects, unzip it into ~/.claude/skills/. To limit it to a single project, unzip it into that project's .claude/skills/ folder.

If you use the Claude apps instead, upload the skill under Settings → Capabilities → Skills.

Personal (all projects): ~/.claude/skills/
Single project: .claude/skills/ inside your project folder
Claude apps: Settings → Capabilities → Skills, then upload

Trigger the skill with natural requests

The skill's description lists the situations it applies to, so you do not need special syntax. Ask in plain language about a strategic data decision. Requests that mention CDO, chief data officer, data strategy, data mesh, lakehouse, training data, data product, data monetization or customer data asset are the most likely to activate it.

Ask about strategy, not implementation. The skill is explicitly not a tactical data engineering tool, so questions about writing schemas, queries or pipelines fall outside it.

"Can we fine-tune our model on customer support tickets, given that our terms only cover service delivery?"
"Should a 12-person startup use a warehouse, a lakehouse or a data mesh?"
"What could our customer data be worth to an acquirer, and what should we fix before diligence?"
"Should our next data hire be an analytics engineer or a data scientist?"

What the skill needs to run

The bundled scripts need Python 3 and use only the standard library, so no extra packages are required. Each script can run on a built-in embedded sample, or you can pass it an optional JSON file describing your data sources, company profile or corpus.

The skill runs scripts, but according to its metadata it does not use the network.

Python 3 (standard library only)
Optional JSON input files describing data sources, company profile or corpus

python scripts/ai_training_data_audit.py path/to/sources.json
python scripts/data_product_strategy_picker.py path/to/profile.json
python scripts/data_asset_valuator.py path/to/corpus.json

Safety notes: scripts and legal limits

The skill runs Python scripts, so read them before you run them on sensitive data, and run them with the same care you would give any local script. Its metadata states that it does not use the network.

Its training-data guidance is not legal advice. The audit script itself states that it is not legal advice, so any consent or copyright conclusion should be checked with qualified counsel before you act on it.

The skill is written for startups. Its stage-based heuristics are not designed for large enterprises with complex governance.

Do not treat a GO verdict as legal clearance
Keep sensitive data inventories local when you run the scripts
Use the skill for strategy, not as a substitute for a data engineer

Tips for better results

Describe the decision you need to make and what data it depends on. The skill's own key questions start with what decision the data drives, so answering those up front gives the agent better inputs.

For the audit and valuation tools, prepare a JSON file that lists each source with its origin, data class and intended use. Include contractual constraints such as customer carve-outs, since the skill treats them as decisive.

State your stage (pre-seed, Series A, Series B and so on)
Name the use case: personalization, fine-tuning, foundation model training or external sharing
List any customer contracts that restrict data use

What people use it for

Deciding whether customer support tickets can be used to fine-tune a model under existing terms
Choosing between a warehouse, lakehouse or data mesh for a small startup with a few data consumers
Preparing a customer data corpus for fundraising or M&A diligence by checking contractual constraints
Deciding whether the next data hire should be an analytics engineer, data engineer or data scientist

Frequently asked questions

How do I install the chief data officer advisor skill?

Download the ZIP from this page and unzip it into ~/.claude/skills/ for personal use, or into a project's .claude/skills/ folder for one project. In the Claude apps, you can instead upload it under Settings → Capabilities → Skills.

Is the chief-data-officer-advisor skill free?

The skill is licensed under MIT. The source does not state any price, so check the licence terms for what you may do with it.

What do I need to run the skill's scripts?

You need Python 3. The scripts use only the standard library, so no extra packages are required. You can run them on the built-in sample or pass an optional JSON file.

Does this skill write SQL or build data pipelines?

No. The skill is explicitly for strategic decisions only. For tactical work such as schema design or queries, the skill points to other tools in its collection, such as database and SQL assistants.

Does the skill give legal advice on training AI on customer data?

No. The audit script states it is not legal advice, so consent and copyright conclusions need review by qualified counsel before you rely on them.

Is this skill suitable for large enterprises?

Not ideally. Its stage-based heuristics are written for startups, so large enterprises with complex governance should not rely on them alone.

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 this skill if you are a founder or early leader at a startup without a chief data officer and want a structured framework for training-data, architecture, valuation and hiring decisions. Pick something else if you need hands-on data engineering, formal legal opinions, or governance designed for a large enterprise.

Download the skill