Exploratory Data Analysis

Use when exploring a dataset before formal analysis, modeling, reporting, or dashboarding. Runs a bundled zero-dependency data health check on CSV files that infers field types, detects encoding, pseudo-nulls, numbers stored as text, leading-zero IDs, duplicate keys, partition-vs-event-time drift, missing dates, and orphan join keys, ranks issues P0/P1/P2, and renders an HTML report; then interprets grain, usability, and next analysis directions. 中文触发词:数据探索、EDA、数据体检、数据摸底、拿到一份新数据。

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add shisuidata/ss-data-skills --skill exploratory-data-analysis
Manual install
git clone --depth 1 https://github.com/shisuidata/ss-data-skills.git /tmp/ss-data-skills
mkdir -p ~/.claude/skills
cp -r /tmp/ss-data-skills/skills/exploratory-data-analysis ~/.claude/skills/exploratory-data-analysis

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Exploratory Data Analysis

## 目标

拿到一份新数据,先回答三个问题:

1. **一行代表什么?**(粒度、主键、时间范围)
2. **能不能直接用?**哪些问题会让结果算错,哪些需要在口径里处理?
3. **值得往哪个方向继续分析?**

核心原则:**数据长什么样由脚本说,数据意味着什么由人判断**。`scripts/eda.py` 负责体检和问题分级;模型负责推断字段含义、确认粒度、区分数据问题和真实业务现象、规划下一步。

## 使用场景

- 拿到一张新表、一份 CSV 或 Excel 导出,先摸底
- 判断数据能否支撑某个分析、看板或模型
- 接手别人的数据,快速发现坑
- 多张表要关联之前,检查键是否对得上
- 分析结果“看起来不对”,回头排查数据本身

典型输入:

```text
请帮我对这份订单数据做 EDA,看哪些字段有质量问题,能不能用来做渠道分析。
```

## 不适用场景

- 漏斗、留存、实验等专项分析:体检完成后分别使用 `funnel-analysis`、`retention-cohort-analysis`、`ab-test-analysis`
- 为一张表设计长期运行的质量监控规则:使用 `data-quality-rule-generator`(可以把体检发现的问题作为输入)
- SQL 逻辑审查:使用 `sql-reviewer`
- 写完整分析报告:使用 `data-analysis-report-writer`

只有业务问题、没有任何数据或字段时,先列出需要的数据,不要假装已经完成 EDA。

## 输入信息

最少输入:

- 数据文件(CSV、TSV 或 xlsx,UTF-8 和 GBK 都可以),或字段列表 + 样例

推荐输入:

- 分析目标:这份数据接下来要用来做什么
- 主键:一行应该由哪些字段唯一确定
- 多表时的关联关系
- 时间字段、分区字段
- 已知问题

## 上下文建议

推荐使用 [数据分析上下文模板](../../context/templates/analysis-context.md);表结构信息可参考 [数据表上下文模板](../../context/templates/table-context.md)。

最有价值的上下文是:分析目标、预期粒度和主键、多表关联关系。没有真实数据时,只能输出检查清单,不能声称发现了具体的缺失率或分布。

## 工作流程

1. **运行体检**(有数据文件且能执行代码时必须运行):

   ```bash
   python3 scripts/eda.py profile \
     --table orders=orders.csv --table users=users.csv \
     --key orders=order_id --key users=user_id \
     --join orders.user_id=users.user_id \
     --html eda_report.html
   ```

   - 组合主键:`--key events=user_id+event_time+event_name`
   - 指定时间字段:`--time-col orders=pay_time`(默认自动选择非分区的时间列)
   - 大文件:`--max-rows 500000` 在全表上随机抽样,报告会标注;主键和关联检查建议全量运行
Read the full skill on GitHub

Details

Skill name
exploratory-data-analysis
Path
skills/exploratory-data-analysis/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Exploratory Data Analysis skill do?

Use when exploring a dataset before formal analysis, modeling, reporting, or dashboarding. Runs a bundled zero-dependency data health check on CSV files that infers field types, detects encoding, pseudo-nulls, numbers stored as text, leading-zero IDs, duplicate keys, partition-vs-event-time drift, missing dates, and orphan join keys, ranks issues P0/P1/P2, and renders an HTML report; then interprets grain, usability, and next analysis directions. 中文触发词:数据探索、EDA、数据体检、数据摸底、拿到一份新数据。

How do I install the Exploratory Data Analysis skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add shisuidata/ss-data-skills --skill exploratory-data-analysis. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Exploratory Data Analysis popular?

It lives in shisuidata/ss-data-skills, which has 9 GitHub stars and 0 forks.

Related skills

Ab Test Analysis

9

shisuidata/ss-data-skills

Use when designing, checking, or interpreting A/B tests and experiments. Computes significance, confidence intervals, sample ratio mismatch, power, CUPED, and sample size with a bundled zero-dependency script, then judges validity risks, guardrails, and ship/iterate/rollback decisions and renders an HTML experiment report. 中文触发词:A/B 实验、AB 测试、实验解读、显著性、样本量计算、能不能全量。

Testing & QA

Business Root Cause Analysis

9

shisuidata/ss-data-skills

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. 中文触发词:指标归因、为什么下降、异常排查、GMV 下滑、指标波动原因。

Marketing, Sales & Business

Daily Report Writer

9

shisuidata/ss-data-skills

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. 中文触发词:日报、日终同步、站会发言、值班交接。

Writing & Content

Stream Pipeline Designer

9

shisuidata/ss-data-skills

Use when designing or reviewing a real-time data pipeline with Flink, Spark Structured Streaming, Kafka, or CDC. Advises on time semantics, watermarks, state management, exactly-once guarantees, throughput, backpressure, and real-time to batch alignment. 中文触发词:实时数仓、Flink、Kafka、实时管道、背压、Watermark、CDC。

Data & Analytics

Data Viz Kit

9

shisuidata/ss-data-skills

Use when producing any chart, data report page, KPI tile, or visual data deliverable for Chinese business audiences. Provides chart-choice rules, Chinese number and period conventions (万/亿, 同比/环比, 涨跌色), a validated light/dark palette, and a zero-dependency Python kit that renders self-contained HTML reports. 中文触发词:图表规范、选图、配色、数据可视化、HTML 数据报告。

Data & Analytics

Public Dashboard Design

5

nekoai-lab/claude-skills

公共ダッシュボードや説明責任が求められる資料に対して、誤解防止・比較しやすさ・信頼性確保を優先した設計ルールを適用する

Data & Analytics

Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.