菜单
Use when generating data quality rules from a table schema, SQL, metric definition, or data pipeline description. Produces validation rules for freshness, row count, uniqueness, nulls, enums, ranges, referential integrity, metric fluctuation, reconciliation, and SQL checks.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when writing a concise daily report, daily worklog, standup update, shift handoff, or end-of-day summary for data analysis, data development, BI, governance, or operations work.
Use when writing or improving data documentation for warehouse tables, metrics, dashboards, SQL jobs, data products, or handover materials so other people and agents can understand data purpose, grain, fields, logic, ownership, and usage constraints.
Use when analyzing upstream and downstream impact for table changes, metric changes, field deprecation, pipeline migration, dashboard breakage, data governance review, or data asset dependency communication.
Use when planning integration with databases, BI tools, data platforms, APIs, workflow systems, storage services, or third-party tools, including connection requirements, API availability, auth strategy, configuration questions, and validation steps.
Use when planning or writing market research for a specific industry, product category, competitor set, business opportunity, user segment, or go-to-market question with structured evidence and clear assumptions.
Use when diagnosing business metric changes or anomalies such as GMV decline, conversion drop, retention loss, churn increase, revenue change, lead decline, or active user fluctuation with a structured root cause analysis plan.
| name | data-quality-rule-generator |
| description | Use when generating data quality rules from a table schema, SQL, metric definition, or data pipeline description. Produces validation rules for freshness, row count, uniqueness, nulls, enums, ranges, referential integrity, metric fluctuation, reconciliation, and SQL checks. |
根据表结构、SQL、指标定义或任务说明，生成可落地的数据质量规则。
这个 Skill 关注质量规则设计，不负责替代调度平台、质量平台或监控系统。默认输出通用 SQL 校验规则；如果用户指定 dbt、Great Expectations、DataWorks、DolphinScheduler 等平台，可以按对应形式改写。
使用这个 Skill，当用户需要：
典型输入：
请根据这张订单汇总表设计数据质量规则。
这段 SQL 每天产出渠道转化率，请帮我生成上线前校验项。
不要用这个 Skill 直接完成：
data-requirement-clarifiermetric-definition-reviewertable-design-advisorsql-reviewer如果表粒度、主键或指标口径不明确，必须先列为待确认问题，再给出基于假设的规则。
最少输入之一：
可选输入：
推荐使用 表设计上下文模板 或 SQL 审查上下文模板。
最有价值的上下文是：表粒度、主键、分区字段、更新频率、SLA、核心指标和历史波动范围。缺少历史波动时，可以给出默认监控思路，但阈值必须标记为假设。
优先从这些维度生成规则：
## 数据质量规则设计
### 1. 规则设计结论
### 2. 设计假设
### 3. 规则清单
| 规则编号 | 规则类型 | 检查对象 | 规则描述 | 严重级别 | 触发动作 |
| --- | --- | --- | --- | --- | --- |
### 4. SQL 校验示例
```sql
-- rule_xxx
```
### 5. 分层处理建议
| 严重级别 | 处理方式 |
| --- | --- |
| 阻断 | 任务失败或禁止发布 |
| 告警 | 通知负责人处理 |
| 观察 | 记录趋势，暂不拦截 |
### 6. 待确认问题
### 7. 上线前验收清单
默认用返回异常行数的方式表达：
select count(*) as invalid_count
from target_table
where dt = '${bizdate}'
and critical_field is null;
如果规则需要判断波动，默认用近 7 天或近 30 天作为参考窗口，但必须标记为可调整假设。
输出必须：
请用 data-quality-rule-generator 为下面这张表生成质量规则：
表：ads_channel_new_user_conversion_d
粒度：dt + channel_id
分区：dt
字段：dt, channel_id, register_user_cnt, first_purchase_user_cnt, conversion_rate
更新：每天 T+1 08:00 前产出