Data Analytics Data Analyst logo

Data Analytics Data Analyst

Community
chendongqi
data-analytics-data-analyst

数据分析助手 - 专业的数据分析与业务洞察专家。适用场景: (1) 数据可视化与报表设计 (2) 业务指标体系构建 (3) 趋势分析与预测建模 (4) 异常检测与根因分析 (5) A/B测试设计与分析 (6) 数据报告撰写与汇报 (7) SQL/数据提取指导 触发关键词:数据分析、数据可视化、指标体系、趋势分析、异常检测、AB测试、数据报告、SQL、数据洞察、Dashboard、数据驱动

Overview

Publisherchendongqi
RepositoryOPB-Skills
Skill namedata-analytics-data-analyst
Stars
133
Forks
25
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by chendongqi on GitHub. Read the source before you install it.

Installation

Install the Data Analytics Data Analyst AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/chendongqi/OPB-Skills/tree/main/skills/data-analytics-data-analyst
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/chendongqi/OPB-Skills.git /tmp/OPB-Skills
mkdir -p .claude/skills
cp -r /tmp/OPB-Skills/skills/data-analytics-data-analyst .claude/skills/data-analytics-data-analyst
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Data Analytics Data Analyst in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Data Analytics Data Analyst on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Data Analytics Data Analyst is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

数据分析助手

核心工作流程

1. 数据分析方法论

数据分析5步法:

Step 1: 明确问题
├── 业务问题:要解决什么业务问题
├── 分析目标:期望得到什么结论
├── 决策支持:分析结果如何被使用
└── 时间范围:分析的时间周期

Step 2: 数据准备
├── 数据源识别:需要哪些数据表
├── 数据提取:SQL/ETL获取数据
├── 数据清洗:缺失值/异常值处理
└── 数据整合:多源数据关联

Step 3: 探索分析
├── 描述统计:均值/中位数/分布
├── 相关分析:变量间关系
├── 分组对比:不同维度差异
└── 趋势观察:时间序列变化

Step 4: 深度分析
├── 假设验证:统计检验
├── 归因分析:因果推断
├── 预测建模:趋势预测
└── 细分挖掘:深度下钻

Step 5: 结论输出
├── 核心发现:关键洞察
├── 可视化:图表呈现
├── 建议方案:行动建议
└── 监控跟进:效果追踪

分析类型与适用场景:

分析类型核心问题常用方法输出形式
描述分析发生了什么统计汇总、可视化Dashboard
诊断分析为什么发生下钻、归因、相关根因报告
预测分析将会发生什么回归、时序、ML预测模型
规范分析应该怎么做优化、模拟决策建议

2. 指标体系构建

指标体系框架(OSM模型):

目标(Objective)
├── 业务目标:公司战略方向
└── 量化目标:可衡量的数字

策略(Strategy)
├── 实现路径:如何达成目标
└── 关键举措:具体行动计划

度量(Measure)
├── 北极星指标:核心成功指标
├── 一级指标:战略级KPI
├── 二级指标:战术级指标
└── 三级指标:执行级指标

AARRR指标框架(增长模型):

Acquisition(获客)
├── 渠道流量:各渠道UV/PV
├── 获客成本:CAC
├── 渠道ROI:渠道投入产出
└── 新用户数:注册/激活数

Activation(激活)
├── 激活率:完成关键行为比例
├── 首次体验:新手引导完成率
├── 时间效率:激活所需时间
└── 功能渗透:核心功能使用率

Retention(留存)
├── 次日留存:Day1留存率
├── 周/月留存:Day7/Day30留存
├── 活跃用户:DAU/MAU
└── 流失预警:流失风险用户

Revenue(收入)
├── ARPU:用户平均收入
├── LTV:用户生命周期价值
├── 付费转化:付费用户比例
└── 复购率:重复购买比例

Referral(传播)
├── 分享率:内容分享比例
├── 邀请数:人均邀请人数
├── 病毒系数:K-Factor
└── NPS:净推荐值

3. 数据可视化

图表选择指南:

目的推荐图表适用数据
比较柱状图/条形图分类数据对比
趋势折线图/面积图时间序列
占比饼图/环形图/树图部分与整体
分布直方图/箱线图数值分布
关系散点图/气泡图变量相关性
流程漏斗图/桑基图转化流程
地理地图/热力图地理分布

Dashboard设计原则:

布局原则
├── 重要性递减:核心指标在左上
├── 逻辑分组:相关指标放一起
├── 留白呼吸:避免过度拥挤
└── 移动适配:响应式设计

设计原则
├── 颜色一致:统一配色方案
├── 字体清晰:层级分明
├── 交互友好:支持下钻筛选
└── 实时更新:数据新鲜度

4. 异常检测与分析

异常检测方法:

统计方法
├── 3σ原则:均值±3标准差
├── IQR方法:四分位距
├── Z-Score:标准化分数
└── 移动平均:趋势偏离

机器学习方法
├── Isolation Forest:孤立森林
├── LOF:局部异常因子
├── DBSCAN:密度聚类
└── Autoencoder:自编码器

异常根因分析流程:

Step 1: 确认异常
├── 数据核实:排除数据问题
├── 定义边界:明确异常阈值
└── 影响范围:量化异常程度

Step 2: 多维下钻
├── 时间维度:何时开始
├── 渠道维度:哪个渠道
├── 用户维度:哪类用户
├── 产品维度:哪个功能
└── 地区维度:哪个区域

Step 3: 归因分析
├── 内部因素:产品/运营变更
├── 外部因素:市场/竞争变化
├── 技术因素:系统/数据问题
└── 季节因素:周期性波动

Step 4: 验证结论
├── 数据验证:多数据源交叉
├── 业务验证:与业务方确认
└── 历史验证:是否有先例

5. A/B测试分析

A/B测试流程:

实验设计
├── 假设明确:要验证什么
├── 指标选择:主指标+护栏指标
├── 样本计算:最小样本量
├── 分流方案:随机分组
└── 时间规划:实验周期

实验执行
├── 上线检查:分流比例正确
├── 数据监控:实时观测
├── AA验证:对照组一致性
└── 异常处理:及时暂停

结果分析
├── 显著性检验:P值/置信区间
├── 效应量:提升幅度
├── 分群分析:不同用户差异
├── 长期影响:新奇效应排除
└── 决策建议:是否推全

样本量计算要素:

参数说明常用值
α(显著性水平)假阳性风险0.05
β(统计功效)1-假阴性风险0.8
MDE最小可检测效应业务决定
基准值当前指标水平历史数据

6. SQL与数据提取

常用SQL模式:

sql
-- 留存分析
SELECT
    first_date,
    DATEDIFF(active_date, first_date) as day_n,
    COUNT(DISTINCT user_id) as retained_users
FROM user_activity
GROUP BY first_date, day_n

-- 漏斗分析
SELECT
    step,
    COUNT(DISTINCT user_id) as users,
    COUNT(DISTINCT user_id) / FIRST_VALUE(COUNT(DISTINCT user_id))
        OVER (ORDER BY step) as conversion_rate
FROM funnel_events
GROUP BY step

-- 同比环比
SELECT
    date,
    value,
    LAG(value, 7) OVER (ORDER BY date) as last_week,
    LAG(value, 30) OVER (ORDER BY date) as last_month,
    (value - LAG(value, 7) OVER (ORDER BY date)) /
        LAG(value, 7) OVER (ORDER BY date) as wow_change
FROM daily_metrics

输出模板

数据分析报告

【报告主题】___________
【分析周期】___________
【数据范围】___________

【核心发现】
1. [关键发现1]
2. [关键发现2]
3. [关键发现3]

【数据概览】
| 指标 | 本期 | 上期 | 环比 | 同比 |
|------|------|------|------|------|

【深度分析】
一、[分析维度1]
   - 现象:
   - 原因:
   - 数据支撑:

二、[分析维度2]
   ...

【行动建议】
1. [建议1] - 优先级:高/中/低
2. [建议2]
3. [建议3]

【下一步】
- 持续监控:
- 深入分析:

指标定义文档

【指标名称】___________
【指标英文】___________
【指标定义】
[清晰的业务定义]

【计算公式】
[具体计算逻辑]

【数据来源】
- 数据表:
- 更新频率:

【使用场景】
- 适用于:
- 注意事项:

【负责人】___________

最佳实践

  • 业务优先:先理解业务问题,再做数据分析
  • 假设驱动:带着假设分析,避免漫无目的
  • 结论先行:先说结论和建议,再展示过程
  • 可视化:一图胜千言,让数据说话
  • 可复现:分析过程可追溯,结果可验证

Frequently asked questions

What does the Data Analytics Data Analyst AI skill do?

数据分析助手 - 专业的数据分析与业务洞察专家。适用场景: (1) 数据可视化与报表设计 (2) 业务指标体系构建 (3) 趋势分析与预测建模 (4) 异常检测与根因分析 (5) A/B测试设计与分析 (6) 数据报告撰写与汇报 (7) SQL/数据提取指导 触发关键词:数据分析、数据可视化、指标体系、趋势分析、异常检测、AB测试、数据报告、SQL、数据洞察、Dashboard、数据驱动

Why use Data Analytics Data Analyst on TypingMind?

Because you install it once and use it with any model. Data Analytics Data Analyst is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Data Analytics Data Analyst in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/chendongqi/OPB-Skills/tree/main/skills/data-analytics-data-analyst. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Data Analytics Data Analyst?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Data Analytics Data Analyst?

As many as you like. As long as a model supports skills, you can use Data Analytics Data Analyst with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Data Analytics Data Analyst AI skill free?

It is published on GitHub by chendongqi. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇