Percerno Skillsbeta
← everything it can do · finance

Cdo Review TEXT

Performs a strategic data governance review of plans involving training data, architecture, or hiring by applying six specific CDO questions to identify risks, consent gaps, and architectural mismatches. It outputs a structured verdict (Ship, Sharpen, or Block) with specific remediation steps and asset valuations.

3 uses this weeksource alirezarezvanilicence MIT
Quality gate: PASS · better answers · measured 2026-10-23
Blind-judged against the bare model on 3 requests: average lift +10.0 points (specificity, structure, method, fit).
won 3/3, lift +10.0, tokens ×12.69
Security scan: clean · 2026-10-24 · 1 files · ran in sandbox
no network calls, shell tricks, credential access or instruction tampering found in its files.

Try asking

Say it in your own words; the assistant finds this recipe by itself. Examples:

“Vi overvejer at bruge kundedata til at træne vores nye model. Kan du køre en CDO-gennemgang for at tjekke samtykket?”
“Gennemgå vores plan om at skifte til et data-mesh. Vi har over 25 interne forbrugere, så jeg vil vide om det er den rigtige arkitektur.”
“Før vi underskriver kontrakten med Fivetran, har jeg brug for en strategisk vurdering af data-aktiverne og M&A-risikoen.”
“We want to start training our LLM on user chat logs. Can you run the CDO review to check if our current TOS covers this?”
“Review this plan for migrating from Snowflake to a data mesh. We have about 30 internal teams consuming data.”
“Before we sign the 3-year Databricks contract, I need a CDO pressure-test on the architecture choice and exit costs.”
Try this skill from Claude, ChatGPT or a chat on your own page. Free plan, no credit card.Get started free

Good for

data-governancecdo-reviewtraining-datadata-architecturecompliancemna-diligencedata-productizationhiring-strategy

Not for

Do not use this skill for general software architecture reviews that do not involve data strategy or AI training; use a CTO review for those. It is not for detailed financial modeling of TCO or revenue projections; use a CFO review for that. It is also not for legal contract drafting or specific license negotiation; use a General Counsel review for those tasks.

Details

When it is the right choice

Use this skill when validating the legal and strategic soundness of a plan to train AI models on customer data, especially regarding consent and provenance. It is also the correct choice when deciding between warehouse, lakehouse, or mesh architectures based on consumer count, or when valuing data assets for M&A or productization. Additionally, use it to verify if a proposed data team hire aligns with the specific business decision being unblocked.

The full recipe the assistant reads

/c-level-agents:cdo-review — CDO Forcing Questions

Command: /c-level-agents:cdo-review <plan>

The decision-driven CDO pressure-tests any plan that touches data strategy. Six questions before any commitment to a data architecture, AI training run, data productization, or data team hire.

When to Run

  • Before approving any new ML model training run that uses customer data
  • Before signing a multi-year data-infrastructure SaaS contract (Snowflake, Databricks, Fivetran)
  • Before productizing any customer data (benchmark report, embedding endpoint, license)
  • Before a major data team hire (head of data, CDO, data PM, ML engineer)
  • Before M&A diligence — yours or theirs
  • When the founder uses the word "monetize" near "data"

The Six CDO Questions

1. What decision does this data drive?

If no decision is unblocked, why are we collecting / training on / productizing it? - "We might need it later" is not a decision. - "It feels like a moat" is not a decision. - A real answer names a specific business call that requires this data.

2. What's the consent provenance for every source?

For each data source: origin, consent flow, data class, intended use. - 1st-party-TOS-only is weaker than 1st-party-explicit-opt-in. - Bundled TOS doesn't cover material new purposes (training on PII for foundation models). - Run ai_training_data_audit.py if there's any AI use case in scope.

3. Who consumes this internally — and how many distinct functional domains?

Drives the centralize-vs-embed and warehouse-vs-mesh decisions. - <5 consumers: warehouse-only. - 5-25 consumers: lakehouse. - 25+ consumers + federated culture: mesh. - Premature architecture choice is the #1 cause of data-team burnout.

4. What's the M&A diligence impact?

If an acquirer asks about this data corpus tomorrow, are we ready? - Is there a documented anonymization process? - What % of customers have MSA carve-outs? - Are training-data provenance logs current? - Run data_asset_valuator.py quarterly.

5. Can the model / decision / report be retrained / re-run / re-published without this source?

Tests how much you depend on a specific data source. - If yes → low blast radius; you can change consent posture later. - If no → high blast radius; you've structurally committed to the source. Vet harder.

6. What role unblocks this — and is it the right next hire?

Wrong hire (data scientist) when right answer (analytics engineer) is a 12-month productivity loss. - Map the decision being unblocked to the specific role. - Confirm prerequisite roles are in place (data engineer before ML engineer, analyst before data scientist).

Workflow

# 1. AI training audit (if any ML / AI use case)
python ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/chief-data-officer-advisor/scripts/ai_training_data_audit.py sources.json

# 2. Architecture decision (if changing the stack)
python ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/chief-data-officer-advisor/scripts/data_product_strategy_picker.py profile.json

# 3. Data asset valuation (if productizing or pre-M&A)
python ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/chief-data-officer-advisor/scripts/data_asset_valuator.py corpus.json

Output Format

# CDO Review: <plan>
**Date:** YYYY-MM-DD

## The Decision Being Made
[one sentence — which of the four CDO decisions: training | architecture | asset | hire]

## Training Audit (if applicable)
- NO-GO sources: N
- MITIGATE sources: N
- GO sources: N
- Top remediation: <one line>

## Architecture (if applicable)
- Recommended: WAREHOUSE / LAKEHOUSE / MESH
- Build-vs-buy summary: <one line>
- Kill criteria: <when to revisit>

## Asset Value (if applicable)
- Strategic value: X/10 | Moat: STRONG / MEDIUM / WEAK
- M&A multiplier: X.Xx – X.Xx ARR
- Recommended productization path: <name>

## Org (if applicable)
- Next hire: <role>
- Why this, not that: <one line>
- Prerequisite hires in place: yes/no

## Verdict
🟢 SHIP | 🟡 SHARPEN | 🔴 BLOCK

## Next Steps
[3 concrete actions]

Routing

  • /c-level-agents:gc-review — for any productization or licensing path
  • /c-level-agents:ciso-review — for any architecture change touching customer data
  • /c-level-agents:cfo-review — for build-vs-buy TCO and M&A valuation math
  • cs-chro-advisor agent — for data team hires (comp, ladder, leveling)
  • /c-level-agents:decide — log the verdict
  • /c-level-agents:freeze 90 — on multi-year infrastructure contracts

Related

  • Agent: cs-cdo-advisor
  • Skill: chief-data-officer-advisor
  • Adjacent: ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/general-counsel-advisor/ (contractual constraints), ${CLAUDE_PLUGIN_ROOT}/vendor/c-level-advisor/cto-advisor/ (architecture capacity)

Version: 1.0.0

Files in this skill (2)
  • LICENSE
  • SKILL.md
Where it comes from

Vendored from alirezarezvani/claude-skills, commit 27cfcd0fb0a4, path c-level-agents/skills/cdo-review, licence MIT. The upstream licence file ships inside the skill.