Dw data comparison
Skill pugyy/dw-harness/template/.claude/skills/dw-data-comparison
A Claude Code engineering template for reliable data warehouse AI development./面向数仓 AI 开发的 Claude Code 工程化模板：hooks、skills、subagents 与八步标准流程。
npx -y skills add pugyy/dw-harness --skill dw-data-comparisonAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
数仓数据比对流程，适用于新旧表、上下游表、核心金额字段和指标口径差异分析。直接调用命令：/dw-data-comparison。
SKILL.md
1.0 KB, as published. Nobody here has run it
Step 5: 数据比对
执行流程
- 调用
data-comparatorsubagent 进行新旧表数据对比 - subagent 在独立 context 运行，只返回差异超过容差的字段
- 主对话只接收差异摘要
推荐提示词
用 data-comparator subagent 对比数据：
- 新表: [表名], partition_dt = '[日期]'
- 参考表: [表名], partition_dt = '[日期]'
- 比对字段: [核心金额字段列表]
- 容差: ≤ 0.01%（金额类）
只返回差异超过容差的字段列表及差值。
比对参数
| 字段类型 | 容差 |
|---|---|
| 金额类 | ≤ 0.01% |
| 数量类 | ≤ 0.1% |
| 字符串类 | 精确匹配 |
输出
由 data-comparator subagent 返回：
- 字段级差异列表
- 差异率
- 差值说明
- 结论（通过/需关注）