cdo-review
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
Chinese/cs:cdo-review — CDO Forcing Questions
/cs:cdo-review — CDO核心质询问题
Command:
/cs: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.
命令:
/cs:cdo-review <plan>由决策驱动的CDO会对任何涉及数据策略的方案进行压力测试。在承诺推进数据架构搭建、AI训练任务、数据产品化或数据团队招聘之前,需先回答以下六个问题。
When to Run
适用场景
- 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"
- 在批准任何使用客户数据的新ML模型训练任务之前
- 在签署多年期数据基础设施SaaS合同(Snowflake、Databricks、Fivetran)之前
- 在将任何客户数据产品化(基准报告、嵌入端点、授权许可)之前
- 在进行重大数据团队招聘(数据主管、CDO、数据产品经理、ML工程师)之前
- 在开展并购尽职调查时(无论是我方收购还是被收购)
- 当创始人将“变现”与“数据”关联提及之时
The Six CDO Questions
六个CDO质询问题
1. What decision does this data drive?
1. 该数据将驱动哪些决策?
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.
如果没有任何决策需要依赖它推进,我们为何要收集/基于它训练/将它产品化?
- “我们以后可能需要它”不属于决策范畴。
- “它感觉像是护城河”也不属于决策范畴。
- 合理答案需明确指出一项需要该数据支撑的具体业务决策。
2. What's the consent provenance for every source?
2. 每个数据源的同意来源是什么?
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 if there's any AI use case in scope.
ai_training_data_audit.py
针对每个数据源:来源渠道、同意流程、数据类别、预期用途。
- 仅依赖第一方服务条款(TOS)的同意力度弱于第一方明确主动勾选的同意。
- 捆绑式服务条款不适用于重大新用途(比如使用个人身份信息(PII)训练基础模型)。
- 如果涉及AI用例,请运行脚本。
ai_training_data_audit.py
3. Who consumes this internally — and how many distinct functional domains?
3. 内部有哪些角色会使用它——覆盖多少个不同的职能领域?
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.
这将决定数据架构是采用集中式还是嵌入式,以及选用数据仓库还是数据网格。
- 少于5个使用者:仅使用数据仓库。
- 5-25个使用者:使用湖仓一体(lakehouse)。
- 25个以上使用者+联邦文化:使用数据网格(mesh)。
- 过早确定架构是导致数据团队倦怠的首要原因。
4. What's the M&A diligence impact?
4. 对并购尽职调查有何影响?
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 quarterly.
data_asset_valuator.py
如果收购方明天询问这个数据集的情况,我们是否准备就绪?
- 是否有文档化的匿名化流程?
- 有多大比例的客户在主服务协议(MSA)中存在例外条款?
- 训练数据来源日志是否是最新的?
- 每季度运行一次脚本。
data_asset_valuator.py
5. Can the model / decision / report be retrained / re-run / re-published without this source?
5. 如果移除该数据源,模型/决策/报告能否重新训练/重新运行/重新发布?
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.
测试你对特定数据源的依赖程度。
- 如果可以→影响范围小;后续可调整同意策略。
- 如果不可以→影响范围大;你已在结构上绑定该数据源,需更严格地审核。
6. What role unblocks this — and is it the right next hire?
6. 哪个角色能推进这件事——这是当下最适合招聘的岗位吗?
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).
当需要的是分析工程师时却招聘了数据科学家,会导致12个月的生产力损失。
- 将待推进的决策与具体岗位对应起来。
- 确认前置岗位已到位(先招聘数据工程师,再招聘ML工程师;先招聘分析师,再招聘数据科学家)。
Workflow
工作流程
bash
undefinedbash
undefined1. AI training audit (if any ML / AI use case)
1. AI训练审计(若涉及ML/AI用例)
python ../../../skills/chief-data-officer-advisor/scripts/ai_training_data_audit.py sources.json
python ../../../skills/chief-data-officer-advisor/scripts/ai_training_data_audit.py sources.json
2. Architecture decision (if changing the stack)
2. 架构决策(若变更技术栈)
python ../../../skills/chief-data-officer-advisor/scripts/data_product_strategy_picker.py profile.json
python ../../../skills/chief-data-officer-advisor/scripts/data_product_strategy_picker.py profile.json
3. Data asset valuation (if productizing or pre-M&A)
3. 数据资产估值(若产品化或筹备并购)
python ../../../skills/chief-data-officer-advisor/scripts/data_asset_valuator.py corpus.json
undefinedpython ../../../skills/chief-data-officer-advisor/scripts/data_asset_valuator.py corpus.json
undefinedOutput Format
输出格式
markdown
undefinedmarkdown
undefinedCDO Review: <plan>
CDO审查:<plan>
Date: YYYY-MM-DD
日期: YYYY-MM-DD
The Decision Being Made
待决策事项
[one sentence — which of the four CDO decisions: training | architecture | asset | hire]
[一句话说明——属于四类CDO决策中的哪一类:训练 | 架构 | 资产 | 招聘]
Training Audit (if applicable)
训练审计(若适用)
- NO-GO sources: N
- MITIGATE sources: N
- GO sources: N
- Top remediation: <one line>
- 不可用数据源:N
- 需整改数据源:N
- 可用数据源:N
- 首要整改措施:<一句话>
Architecture (if applicable)
架构方案(若适用)
- Recommended: WAREHOUSE / LAKEHOUSE / MESH
- Build-vs-buy summary: <one line>
- Kill criteria: <when to revisit>
- 推荐方案:WAREHOUSE / LAKEHOUSE / MESH
- 自研vs采购总结:<一句话>
- 终止标准:<何时重新评估>
Asset Value (if applicable)
资产价值(若适用)
- Strategic value: X/10 | Moat: STRONG / MEDIUM / WEAK
- M&A multiplier: X.Xx – X.Xx ARR
- Recommended productization path: <name>
- 战略价值:X/10 | 护城河:STRONG / MEDIUM / WEAK
- 并购乘数:X.Xx – X.Xx 年度经常性收入(ARR)
- 推荐产品化路径:<名称>
Org (if applicable)
组织架构(若适用)
- Next hire: <role>
- Why this, not that: <one line>
- Prerequisite hires in place: yes/no
- 下一个招聘岗位:<角色>
- 为何选此而非彼:<一句话>
- 前置岗位是否到位:是/否
Verdict
审查结论
🟢 SHIP | 🟡 SHARPEN | 🔴 BLOCK
🟢 推进 | 🟡 优化 | 🔴 暂缓
Next Steps
下一步行动
[3 concrete actions]
undefined[3项具体举措]
undefinedRouting
关联路由
- — for any productization or licensing path
/cs:gc-review - — for any architecture change touching customer data
/cs:ciso-review - — for build-vs-buy TCO and M&A valuation math
/cs:cfo-review - — for data team hires (comp, ladder, leveling)
/cs:chro-review - — log the verdict
/cs:decide - — on multi-year infrastructure contracts
/cs:freeze 90
- — 适用于任何产品化或授权许可路径
/cs:gc-review - — 适用于任何涉及客户数据的架构变更
/cs:ciso-review - — 适用于自研vs采购的总拥有成本(TCO)及并购估值计算
/cs:cfo-review - — 适用于数据团队招聘(薪酬、晋升体系、职级评定)
/cs:chro-review - — 记录审查结论
/cs:decide - — 针对多年期基础设施合同冻结审批
/cs:freeze 90
Related
相关资源
- Agent:
cs-cdo-advisor - Skill:
chief-data-officer-advisor - Adjacent: (contractual constraints),
../../../skills/general-counsel-advisor/(architecture capacity)../../../skills/cto-advisor/
Version: 1.0.0
- Agent:
cs-cdo-advisor - Skill:
chief-data-officer-advisor - 相关技能: (合同约束),
../../../skills/general-counsel-advisor/(架构容量)../../../skills/cto-advisor/
版本: 1.0.0