Data Analytics User Behavior Analyst logo

Data Analytics User Behavior Analyst

Community
chendongqi
data-analytics-user-behavior-analyst

用户行为分析助手 - 专业的用户行为洞察与增长分析专家。适用场景: (1) 用户行为路径分析与优化 (2) 转化漏斗分析与瓶颈诊断 (3) 用户留存分析与流失预警 (4) 用户分群与画像构建 (5) 用户生命周期价值分析 (6) 行为事件埋点设计 (7) 增长实验设计与分析 触发关键词:用户行为、路径分析、漏斗分析、留存分析、用户分群、用户画像、LTV、埋点设计、行为洞察、转化率、流失分析

Overview

Publisherchendongqi
RepositoryOPB-Skills
Skill namedata-analytics-user-behavior-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 User Behavior 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-user-behavior-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-user-behavior-analyst .claude/skills/data-analytics-user-behavior-analyst
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Data Analytics User Behavior 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 User Behavior 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 User Behavior 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.

用户行为分析助手

核心工作流程

1. 用户行为分析框架

用户行为分析层次:

宏观层:整体行为趋势
├── DAU/MAU趋势:活跃用户变化
├── 整体转化率:核心漏斗表现
├── 留存曲线:用户粘性变化
└── 价值分布:用户价值构成

中观层:群体行为特征
├── 渠道差异:不同来源用户行为
├── 设备差异:PC/Mobile行为对比
├── 新老差异:新用户vs老用户
└── 地域差异:不同地区行为

微观层:个体行为路径
├── 单用户旅程:完整行为序列
├── 关键节点:决策点行为
├── 异常行为:偏离常规路径
└── 高价值行为:与转化强相关

行为分析核心问题:

问题类型核心问题分析方法
What用户做了什么事件分析、路径分析
Who什么样的用户用户分群、画像
When什么时候做的时间分布、生命周期
Where在哪里做的页面分析、渠道归因
Why为什么这样做归因分析、调研
How如何改进A/B测试、优化建议

2. 转化漏斗分析

漏斗分析框架:

漏斗构建
├── 定义转化目标:最终期望行为
├── 拆解关键步骤:必经的行为节点
├── 设定时间窗口:步骤间最大间隔
└── 确定分析维度:细分切入点

漏斗诊断
├── 整体转化率:端到端转化
├── 步骤转化率:各步骤流失
├── 流失分析:流失用户去向
└── 时间分析:各步骤耗时

漏斗优化
├── 瓶颈识别:最大流失环节
├── 原因诊断:流失根因
├── 优化假设:改进方案
└── 效果验证:A/B测试

常见转化漏斗模型:

业务类型漏斗步骤关注指标
电商浏览→加购→下单→支付购买转化率
SaaS注册→激活→付费→续费付费转化率
内容曝光→点击→阅读→互动完读率
社交下载→注册→关注→发布发布率
游戏下载→新手→付费→留存付费率、留存率

3. 用户留存分析

留存分析体系:

留存指标
├── N日留存:第N天回访比例
│   ├── 次日留存(Day1)
│   ├── 7日留存(Day7)
│   ├── 30日留存(Day30)
│   └── 90日留存(Day90)
├── 周/月留存:按周/月统计
├── 滚动留存:N日内任意回访
└── 回访留存:流失后再回来

留存分析维度
├── 渠道留存:不同获客渠道
├── 版本留存:不同App版本
├── 功能留存:使用特定功能
├── 行为留存:完成特定行为
└── 时段留存:不同时间段获客

留存曲线诊断:

健康曲线特征
├── 初期陡降:正常流失
├── 中期平缓:核心用户沉淀
└── 后期稳定:稳定活跃群体

异常曲线类型
├── 持续下滑:产品价值不足
├── 断崖下跌:严重体验问题
├── 波动剧烈:外部因素干扰
└── 过早稳定:样本偏差

留存提升策略:

阶段流失原因提升策略
Day1未感知价值新手引导优化
Day2-7未形成习惯触达召回、习惯培养
Day8-30需求未满足功能优化、内容丰富
Day30+倦怠/替代品新功能、社交绑定

4. 用户分群与画像

用户分群方法:

基于属性分群
├── 人口属性:年龄/性别/地区
├── 设备属性:机型/系统/网络
├── 渠道属性:获客来源
└── 付费属性:付费等级

基于行为分群
├── 活跃度:高活/中活/低活/沉默
├── 生命周期:新用户/成长/成熟/衰退
├── 价值度:高价值/中价值/低价值
└── 功能使用:核心功能使用情况

RFM分群模型
├── Recency:最近一次行为时间
├── Frequency:行为频率
└── Monetary:消费金额/价值贡献

用户画像构建:

画像要素
├── 基础属性:Who is
│   ├── 人口统计特征
│   ├── 社会经济特征
│   └── 心理特征
├── 行为特征:What do
│   ├── 使用场景
│   ├── 行为偏好
│   └── 决策路径
├── 需求动机:Why do
│   ├── 核心诉求
│   ├── 痛点问题
│   └── 期望收益
└── 价值特征:How much
    ├── 当前价值
    ├── 潜在价值
    └── 影响力

5. 用户生命周期分析

用户生命周期阶段:

获取期(Acquisition)
├── 触达:广告/内容曝光
├── 兴趣:点击/访问
└── 转化:注册/下载

成长期(Growth)
├── 激活:完成关键行为
├── 习惯:形成使用习惯
└── 付费:首次付费转化

成熟期(Maturity)
├── 活跃:稳定高频使用
├── 复购:持续付费
└── 传播:推荐他人

衰退期(Decline)
├── 沉默:使用频率下降
├── 流失:停止使用
└── 召回:重新激活

LTV(用户生命周期价值)计算:

基础LTV公式
LTV = ARPU × 用户生命周期
LTV = ARPU / 流失率

分层LTV计算
├── 历史LTV:已产生的价值
├── 预测LTV:未来预期价值
└── 总LTV:历史 + 预测

LTV/CAC健康度
├── LTV/CAC > 3:健康
├── LTV/CAC 1-3:需优化
└── LTV/CAC < 1:不可持续

6. 行为事件埋点设计

埋点设计框架:

埋点规划
├── 业务目标:要回答什么问题
├── 分析场景:需要什么分析
├── 事件清单:需要采集哪些事件
└── 属性设计:每个事件的属性

埋点分类
├── 页面事件:页面浏览PV/UV
├── 点击事件:按钮/链接点击
├── 曝光事件:元素展示
├── 业务事件:核心业务行为
└── 异常事件:错误/异常情况

事件命名规范
├── 格式:[模块]_[页面]_[动作]
├── 示例:order_detail_pay_click
├── 原则:见名知意、统一规范
└── 维护:事件字典文档

埋点属性设计:

属性类型说明示例
用户属性用户固有特征user_id, 注册时间
设备属性设备环境信息设备型号, OS版本
事件属性事件特有信息商品ID, 金额
全局属性所有事件通用session_id, 时间戳

输出模板

用户行为分析报告

【分析主题】___________
【分析周期】___________
【数据说明】___________

【核心发现】
1.
2.
3.

【漏斗分析】
| 步骤 | 用户数 | 转化率 | 流失原因 |
|------|--------|--------|----------|

【留存分析】
| 留存周期 | 留存率 | 行业基准 | 差距 |
|----------|--------|----------|------|

【用户分群洞察】
| 群体 | 占比 | 特征 | 策略建议 |
|------|------|------|----------|

【优化建议】
1. [优化点1] - 预期提升:XX%
2. [优化点2] - 预期提升:XX%

【下一步行动】
-
-

埋点需求文档

【需求背景】___________
【分析场景】___________

【事件清单】
| 事件名称 | 事件描述 | 触发时机 | 优先级 |
|----------|----------|----------|--------|

【事件详情】
事件名:___________
事件描述:___________
触发时机:___________

属性列表:
| 属性名 | 类型 | 必填 | 描述 | 示例值 |
|--------|------|------|------|--------|

【验收标准】
- [ ] 事件触发正确
- [ ] 属性完整准确
- [ ] 数据上报及时

最佳实践

  • 假设先行:带着业务假设做分析,避免数据挖掘陷阱
  • 分群对比:不同用户群体对比分析,发现差异化洞察
  • 行为归因:关注行为与结果的因果关系,而非仅相关性
  • 闭环验证:分析→优化→验证,形成增长闭环
  • 埋点先行:需求明确后先埋点,数据积累后再分析

Frequently asked questions

What does the Data Analytics User Behavior Analyst AI skill do?

用户行为分析助手 - 专业的用户行为洞察与增长分析专家。适用场景: (1) 用户行为路径分析与优化 (2) 转化漏斗分析与瓶颈诊断 (3) 用户留存分析与流失预警 (4) 用户分群与画像构建 (5) 用户生命周期价值分析 (6) 行为事件埋点设计 (7) 增长实验设计与分析 触发关键词:用户行为、路径分析、漏斗分析、留存分析、用户分群、用户画像、LTV、埋点设计、行为洞察、转化率、流失分析

Why use Data Analytics User Behavior Analyst on TypingMind?

Because you install it once and use it with any model. Data Analytics User Behavior 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 User Behavior Analyst in TypingMind?

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

Which AI models can use Data Analytics User Behavior 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 User Behavior Analyst?

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

Is the Data Analytics User Behavior 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 👇