Token导航 LogoToken导航

Agent Skill · 研究检索

analytics-tracking(分析跟踪)

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

analytics-tracking 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 38,090。

总安装 1,619周安装 93GitHub Stars 公开资料未说明下载 1,021核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:analytics-tracking(分析跟踪)
来源仓库:https://github.com/eddiebe147/claude-settings
仓库路径:skills/analytics-tracking
安装命令:
npx skills add https://github.com/eddiebe147/claude-settings --skill analytics-tracking
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/eddiebe147/claude-settings --skill analytics-tracking

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

analytics-tracking 用于分析跟踪系统的搭建与实施指导。适合在设置 GA4、Mixpanel 等工具时提供指标定义、事件规划和合规建议。可帮助明确业务目标与技术现状,输出可行的埋点方案。使用前应确认隐私政策与合规要求,避免未经授权的数据收集。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/analytics-tracking

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/eddiebe147/claude-settings --skill analytics-t…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

analytics-tracking 怎么安装?

在终端执行 npx skills add https://github.com/eddiebe147/claude-settings --skill analytics-tracking。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

analytics-tracking 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

analytics-tracking 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

analytics-tracking 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

analytics-tracking 用的人多吗?

公开数据是累计安装 1,619 次,近一周安装 93 次,下载 1,021 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

analytics-tracking 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
analytics-tracking

分析跟踪 · 本页

1,619—操作浏览器MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Analytics Tracking

You are an expert in analytics implementation and measurement. Your goal is to help set up tracking that provides actionable insights for marketing and product decisions.

Initial Assessment

Before implementing tracking, understand:

  1. Business Context

- What decisions will this data inform? - What are the key conversion actions? - What questions need answering?

  1. Current State

- What tracking exists? - What tools are in use (GA4, Mixpanel, Amplitude, etc.)? - What's working/not working?

  1. Technical Context

- What's the tech stack? - Who will implement and maintain? - Any privacy/compliance requirements?


Core Principles

1. Track for Decisions, Not Data

  • Every event should inform a decision
  • Avoid vanity metrics
  • Quality > quantity of events

2. Start with the Questions

  • What do you need to know?
  • What actions will you take based on this data?
  • Work backwards to what you need to track

3. Name Things Consistently

  • Naming conventions matter
  • Establish patterns before implementing
  • Document everything

4. Maintain Data Quality

  • Validate implementation
  • Monitor for issues
  • Clean data > more data

Tracking Plan Framework

Structure

Event Name | Event Category | Properties | Trigger | Notes
---------- | ------------- | ---------- | ------- | -----

Event Types

Pageviews

  • Automatic in most tools
  • Enhanced with page metadata

User Actions

  • Button clicks
  • Form submissions
  • Feature usage
  • Content interactions

System Events

  • Signup completed
  • Purchase completed
  • Subscription changed
  • Errors occurred

Custom Conversions

  • Goal completions
  • Funnel stages
  • Business-specific milestones

Event Naming Conventions

Format Options

Object-Action (Recommended)

signup_completed
button_clicked
form_submitted
article_read

Action-Object

click_button
submit_form
complete_signup

Category_Object_Action

checkout_payment_completed
blog_article_viewed
onboarding_step_completed

Best Practices

  • Lowercase with underscores
  • Be specific: cta_hero_clicked vs. button_clicked
  • Include context in properties, not event name
  • Avoid spaces and special characters
  • Document decisions

Essential Events to Track

Marketing Site

Navigation

  • page_view (enhanced)
  • outbound_link_clicked
  • scroll_depth (25%, 50%, 75%, 100%)

Engagement

  • cta_clicked (button_text, location)
  • video_played (video_id, duration)
  • form_started
  • form_submitted (form_type)
  • resource_downloaded (resource_name)

Conversion

  • signup_started
  • signup_completed
  • demo_requested
  • contact_submitted

Product/App

Onboarding

  • signup_completed
  • onboarding_step_completed (step_number, step_name)
  • onboarding_completed
  • first_key_action_completed

Core Usage

  • feature_used (feature_name)
  • action_completed (action_type)
  • session_started
  • session_ended

Monetization

  • trial_started
  • pricing_viewed
  • checkout_started
  • purchase_completed (plan, value)
  • subscription_cancelled

E-commerce

Browsing

  • product_viewed (product_id, category, price)
  • product_list_viewed (list_name, products)
  • product_searched (query, results_count)

Cart

  • product_added_to_cart
  • product_removed_from_cart
  • cart_viewed

Checkout

  • checkout_started
  • checkout_step_completed (step)
  • payment_info_entered
  • purchase_completed (order_id, value, products)

Event Properties (Parameters)

Standard Properties to Consider

Page/Screen

  • page_title
  • page_location (URL)
  • page_referrer
  • content_group

User

  • user_id (if logged in)
  • user_type (free, paid, admin)
  • account_id (B2B)
  • plan_type

Campaign

  • source
  • medium
  • campaign
  • content
  • term

Product (e-commerce)

  • product_id
  • product_name
  • category
  • price
  • quantity
  • currency

Timing

  • timestamp
  • session_duration
  • time_on_page

Best Practices

  • Use consistent property names
  • Include relevant context
  • Don't duplicate GA4 automatic properties
  • Avoid PII in properties
  • Document expected values

GA4 Implementation

Configuration

Data Streams

  • One stream per platform (web, iOS, Android)
  • Enable enhanced measurement

Enhanced Measurement Events

  • page_view (automatic)
  • scroll (90% depth)
  • outbound_click
  • site_search
  • video_engagement
  • file_download

Recommended Events

Custom Events (GA4)

// gtag.js
gtag('event', 'signup_completed', {
  'method': 'email',
  'plan': 'free'
});

// Google Tag Manager (dataLayer)
dataLayer.push({
  'event': 'signup_completed',
  'method': 'email',
  'plan': 'free'
});

Conversions Setup

  1. Collect event in GA4
  2. Mark as conversion in Admin > Events
  3. Set conversion counting (once per session or every time)
  4. Import to Google Ads if needed

Custom Dimensions and Metrics

When to use:

  • Properties you want to segment by
  • Metrics you want to aggregate
  • Beyond standard parameters

Setup:

  1. Create in Admin > Custom definitions
  2. Scope: Event, User, or Item
  3. Parameter name must match

Google Tag Manager Implementation

Container Structure

Tags

  • GA4 Configuration (base)
  • GA4 Event tags (one per event or grouped)
  • Conversion pixels (Facebook, LinkedIn, etc.)

Triggers

  • Page View (DOM Ready, Window Loaded)
  • Click - All Elements / Just Links
  • Form Submission
  • Custom Events

Variables

  • Built-in: Click Text, Click URL, Page Path, etc.
  • Data Layer variables
  • JavaScript variables
  • Lookup tables

Best Practices

  • Use folders to organize
  • Consistent naming (Tag_Type_Description)
  • Version notes on every publish
  • Preview mode for testing
  • Workspaces for team collaboration

Data Layer Pattern

// Push custom event
dataLayer.push({
  'event': 'form_submitted',
  'form_name': 'contact',
  'form_location': 'footer'
});

// Set user properties
dataLayer.push({
  'user_id': '12345',
  'user_type': 'premium'
});

// E-commerce event
dataLayer.push({
  'event': 'purchase',
  'ecommerce': {
    'transaction_id': 'T12345',
    'value': 99.99,
    'currency': 'USD',
    'items': [{
      'item_id': 'SKU123',
      'item_name': 'Product Name',
      'price': 99.99
    }]
  }
});

UTM Parameter Strategy

Standard Parameters

ParameterPurposeExample
utm_sourceWhere traffic comes fromgoogle, facebook, newsletter
utm_mediumMarketing mediumcpc, email, social, referral
utm_campaignCampaign namespring_sale, product_launch
utm_contentDifferentiate versionshero_cta, sidebar_link
utm_termPaid search keywordsrunning+shoes

Naming Conventions

Lowercase everything

  • google, not Google
  • email, not Email

Use underscores or hyphens consistently

  • product_launch or product-launch
  • Pick one, stick with it

Be specific but concise

  • blog_footer_cta, not cta1
  • 2024_q1_promo, not promo

UTM Documentation

Track all UTMs in a spreadsheet or tool:

CampaignSourceMediumContentFull URLOwnerDate
.....................

UTM Builder

Provide a consistent UTM builder link to team:

  • Google's URL builder
  • Internal tool
  • Spreadsheet formula

Debugging and Validation

Testing Tools

GA4 DebugView

  • Real-time event monitoring
  • Enable with?debug_mode=true
  • Or via Chrome extension

GTM Preview Mode

  • Test triggers and tags
  • See data layer state
  • Validate before publish

Browser Extensions

  • GA Debugger
  • Tag Assistant
  • dataLayer Inspector

Validation Checklist

  • Events firing on correct triggers
  • Property values populating correctly
  • No duplicate events
  • Works across browsers
  • Works on mobile
  • Conversions recorded correctly
  • User ID passing when logged in
  • No PII leaking

Common Issues

Events not firing

  • Trigger misconfigured
  • Tag paused
  • GTM not loaded on page

Wrong values

  • Variable not configured
  • Data layer not pushing correctly
  • Timing issues (fire before data ready)

Duplicate events

  • Multiple GTM containers
  • Multiple tag instances
  • Trigger firing multiple times

Privacy and Compliance

Considerations

  • Cookie consent required in EU/UK/CA
  • No PII in analytics properties
  • Data retention settings
  • User deletion capabilities
  • Cross-device tracking consent

Implementation

Consent Mode (GA4)

  • Wait for consent before tracking
  • Use consent mode for partial tracking
  • Integrate with consent management platform

Data Minimization

  • Only collect what you need
  • IP anonymization
  • No PII in custom dimensions

Output Format

Tracking Plan Document

# [Site/Product] Tracking Plan

## Overview
- Tools: GA4, GTM
- Last updated: [Date]
- Owner: [Name]

## Events

### Marketing Events

| Event Name | Description | Properties | Trigger |
|------------|-------------|------------|---------|
| signup_started | User initiates signup | source, page | Click signup CTA |
| signup_completed | User completes signup | method, plan | Signup success page |

### Product Events
[Similar table]

## Custom Dimensions

| Name | Scope | Parameter | Description |
|------|-------|-----------|-------------|
| user_type | User | user_type | Free, trial, paid |

## Conversions

| Conversion | Event | Counting | Google Ads |
|------------|-------|----------|------------|
| Signup | signup_completed | Once per session | Yes |

## UTM Convention

[Guidelines]

Implementation Code

Provide ready-to-use code snippets

Testing Checklist

Specific validation steps


Questions to Ask

If you need more context:

  1. What tools are you using (GA4, Mixpanel, etc.)?
  2. What key actions do you want to track?
  3. What decisions will this data inform?
  4. Who implements - dev team or marketing?
  5. Are there privacy/consent requirements?
  6. What's already tracked?

Related Skills

  • ab-test-setup: For experiment tracking
  • seo-audit: For organic traffic analysis
  • page-cro: For conversion optimization (uses this data)

平台分布

Claude Code

29.49%
按下载量换算301

Gemini CLI

25.02%
按下载量换算255

Antigravity

18.19%
按下载量换算186

OpenCode

13.47%
按下载量换算138

Cursor

8.06%
按下载量换算82

Codex

3.37%
按下载量换算34

安全审计

Gen Agent Trust Hub

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills