Home / cabbage2000-lab / data-analysis-skills · GitHub

data-analysis-skills SKILL.md skillA

data-analysis-skills from cabbage2000-lab/data-analysis-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add cabbage2000-lab/data-analysis-skills/data-analysis-skills@v0.18.3

Pins v0.18.3 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
cabbage2000-lab/data-analysis-skills
Path
skills/data-analysis-skills/SKILL.md
Versions recorded
2
Latest version
v0.18.3, committed Sep 3, 2026
First version recorded
Aug 6, 2026
Size
15,637 bytes
Repository stars
21
License
MIT

当用户提供数据文件（CSV / Excel / JSON / TSV）或表格数据，想要做分析、找洞察或要一份报告时使用——例如「分析数据」「做数据报告」「帮我看看这份数据」「这批订单数据说明什么」，以及销售 / 经营 / 运营数据复盘、探索性分析（EDA）、A/B 实验评估、趋势预测，或要一份可交互的 HTML 数据报告。不适用于：搭建 dashboard 应用、网页爬取、连接线上数据库。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# data-analysis-skills：行业化数据分析与叙事报告

## 概述

把原始数据变成会自己讲故事的行业化数据报告——交付物不是孤立的图表和数字，而是一份有洞察、有结论、能推动业务决策的分析报告。

```
一次分析 = 五阶段流程（主线）
         × 一个行业模版 industries/（分析什么、对谁说）
         × 按需加载的方法模块 references/（怎么分析）
         → 数据 JSON 注入 assets/report_template.html → 单文件 HTML 报告
```

支持的输入：CSV、Excel（.xlsx/.xls）、JSON、TSV。**一份输入可能含多个数据集**——一个 Excel 有多个 sheet、一次给过来两个及以上文件、或 JSON 顶层是含多个数组键的 dict；这些走阶段 1 的多源接入（见 `references/data-sources.md`）。分析用 Python 执行（pandas 等；缺依赖先尝试 pip 安装，失败按降级表处理）。

## 首先：任务分流

| 用户要的是什么 | 走哪条路 |
|------|------|
| 开放式分析，想要报告/洞察（「分析这份数据」「给我一份报告」） | **完整五阶段流程**（含阶段 1 门禁），见下文 |
| 单个统计问题（「检验 B 方案是否显著」「算一下这两列的相关性」） | **轻量路径**：直接算出来，回复结果 + 注意事项；不强加行业确认，也不套完整报告流程 |

分流判据：用户点名了具体的统计计算、且没有要整体洞察或报告 → 轻量路径。**拿不准就走完整流程。统计纪律对两条路径一视同仁。**

## 五阶段流程

开工时立即用宿主的任务清单工具（Claude Code 用 TodoWrite、Codex 用 update_plan、其它宿主用各自等价的 plan/todo 工具）为每个阶段建一条 todo，逐阶段推进并更新状态。**宿主没有这类工具，就在开头列一份纯文本的五阶段清单，并在推进时逐次复述进度**——阶段追踪不因为工具缺失就丢掉。阶段 2–5 一气呵成，不再打断用户提问；每个阶段开始时打印一行进度提示。

### 阶段 1：数据接入与理解【唯一的强制门禁】

1. 读取数据并给出画像：行列数、字段类型、缺失情况、时间范围、关键字段的唯一值分布
2. **行业识别**：从字段名、数据特征和用户描述推断所属行业，并自评置信度
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add cabbage2000-lab/data-analysis-skills/data-analysis-skills@sha256:8ed71f7212a0bd1d

The line at the top of this page pins the label v0.18.3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_dq7gvon3wcngxlrl.svg)](https://markdownregistry.com/a/art_dq7gvon3wcngxlrl)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 6, 2026 and Sep 3, 2026, about one every 28 days.

versioncommittedcommitsizeaudit
v0.18.3 latest2026-09-03 d63a25f 15,637 BA view · diff
git:20260806.2d474b12026-08-06 2d474b1 17,560 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (15637 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

cabbage2000-lab/data-analysis-skills · 21 stars · license MIT · pushed 2026-10-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_dq7gvon3wcngxlrl
GET https://markdownregistry.com/api/v1/resolve?ref=cabbage2000-lab/data-analysis-skills/data-analysis-skills
GET https://markdownregistry.com/api/v1/blob/8ed71f7212a0bd1d6c95f34969ea80246480c64b02df1589e6e81dbaa5a24844

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

Browse by kind, by grade A, or by owner.