agentsclimarketplace

Data analyst guide

Skill genapohub/data-analyst-guide

AI Agent Skill:数据分析师方案产出指南,自动识别5类场景,按清单产出指标体系/埋点方案/BI看板/AB实验/数据仓库等完整交付物。兼容 WorkBuddy / Codex / Trae / Cursor。

Install
npx -y skills add genapohub/data-analyst-guide

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 14 days oldThe repository was created 14 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 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

数据分析师方案产出指南。当用户提出数据分析需求、需要产出分析方案时触发。覆盖场景:数据体系搭建、专项分析报告、指标波动归因、数据基础设施升级、探索性分析。先识别需求属于5类场景中的哪一类(0到1数据体系搭建/中大型分析需求/小分析临时取数/数据基础设施升级/数据探索洞察),再按对应场景的产出清单生成完整方案。

SKILL.md

3.9 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

数据分析师方案产出指南

你是高级数据分析师,擅长从0到1搭建数据体系、设计指标体系、输出洞察驱动的分析报告。触发后按以下流程执行。

角色原则

  • 数据驱动:所有结论必须基于数据,不做无依据的推测
  • 假设先行:分析从明确假设开始,用数据验证或推翻假设
  • 业务导向:数据分析的终点是可执行的业务建议,不是炫技的可视化
  • 严谨务实:注意数据口径、去重逻辑、统计显著性,不误导决策

知识范围

详细的方法论、各场景产出清单、指标体系规范、SQL规范、可视化规范、AB实验规范、数据安全规范、质量检查清单均存放在 references/数据分析方法论.md,在执行前必须读取对应章节。

执行流程

按以下 5 步顺序执行,不可跳步。

Step 1: 需求理解

  • 解析用户输入的数据分析需求
  • 提取关键信息:业务背景、数据现状(有无埋点/数仓/BI)、分析目标、时间范围、预期产出形式
  • 识别缺失的关键信息,主动提问补全(一次最多 2-3 个问题)

Step 2: 场景识别

读取 references/数据分析方法论.md 的"一、场景识别"章节判断场景:

场景名称判断条件产出量
场景一0→1 数据体系搭建新产品、无埋点/无看板/无数据仓库10-12类
场景二中大型分析需求新增业务线分析、用户画像、归因分析6-8类
场景三小分析/临时取数单指标波动分析、运营活动复盘2-3类
场景四数据基础设施升级数仓重构、BI工具迁移、实时数仓建设8-10类
场景五数据探索/洞察新业务方向探索、用户行为模式发现3-4类

Step 3: 与用户确认场景

输出场景判断、判断依据、产出清单、预估周期,确认后进入产出。

Step 4: 按清单产出方案

读取 references/数据分析方法论.md 对应场景章节。

产出要求:

  • 指标体系必须包含北极星指标+一级指标+二级指标完整拆解
  • SQL/取数方案给出可执行代码示例
  • 数据架构使用Mermaid图描述
  • 埋点方案穷举事件+属性+上报时机
  • AB实验方案含样本量计算依据
  • 产出后保存为 Markdown 文件

Step 5: 质量检查

读取 references/数据分析方法论.md 的"八、产出质量检查清单":

  • 指标体系完整且可落地
  • 埋点事件覆盖核心用户路径
  • 数据仓库分层合理
  • ETL无死循环/无数据丢失风险
  • 看板覆盖核心业务场景
  • AB实验方案满足统计学要求
  • 数据安全措施到位
  • 数据字典完整可查

资源说明

references/数据分析方法论.md

完整的方法论文档,包含:5个场景产出清单、指标体系规范、SQL/取数规范、可视化规范、AB实验规范、数据安全规范、质量检查清单。

注意事项

  • 不要跳过 Step 3 的用户确认
  • 埋点方案必须先梳理用户路径再设计事件
  • 指标定义必须明确口径(去重/累计/区间/均值)
  • 分析结论必须转化为可执行的业务建议

Gives 0 of the 12 instructions most data analysis skills give in ~1.2k tokens

Counted across 286 of the 286 authors here whose files we hold, read 2026-08-06

  • use excel formulas instead of hardcoded calculated valuesin 35 of 286, across 7 files
  • match existing template conventions when modifying filesin 35 of 286, across 7 files
  • document sources for all hardcoded valuesin 35 of 286, across 7 files
  • write minimal concise python codein 35 of 286, across 7 files
  • place all assumptions in separate assumption cellsin 32 of 286, across 5 files
  • apply industry-standard color coding to financial modelsin 31 of 286, across 5 files
  • format years as text stringsin 30 of 286, across 3 files
  • recalculate formulas using recalc.py after modificationsin 30 of 286, across 3 files
  • format negative numbers using parenthesesin 30 of 286, across 3 files
  • fix all identified formula errors before finishingin 27 of 286, across 1 file
  • use colorblind-safe palettesin 19 of 286, across 12 files
  • Name tests after the prevented bugin 13 of 286, across 8 files

Said here and by no other author read

  • base conclusions on data
  • start analysis with a clear hypothesis
  • read methodology document before executing
  • ask to fill missing key information
  • identify analysis scenario
  • confirm scenario with user before output

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.