MCPInstall

analytics-tracking-automation

by reason-machinesProductivity & Automation

AI-powered GA4 + GTM event tracking automation — analyzes sites, designs event schemas, syncs GTM containers, runs preview verification, and publishes tracking implementations.

Installs
2K
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/reason-machines/data-skills --skill analytics-tracking-automation
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads analytics-tracking-automation automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Analytics Tracking Automation

Skill by ara.so — Data Skills collection.

This skill enables AI agents to plan, implement, and deploy GA4 + GTM tracking setups. It automates site analysis, page grouping, event schema design, GTM container synchronization, preview verification, and publishing—supporting both generic websites and Shopify storefronts.

What This Skill Does

The analytics-tracking-automation project provides a local-first workflow that:

  1. Analyzes a website by crawling pages and identifying business intent
  2. Groups pages by purpose (e.g., product, pricing, contact)
  3. Designs event schemas (GA4 events, parameters, triggers) based on site structure
  4. Syncs to GTM by creating/updating tags, triggers, variables via Google Tag Manager API
  5. Verifies in preview using automated Playwright-based checks
  6. Publishes the GTM container version when verification passes
  7. Supports Shopify with specialized tracking for cart, checkout, and purchase flows
  8. Maintains artifacts for resumable, reviewable tracking work

Installation

For Use in AI Agent Environments

The recommended installation is to clone the repository and install the skill bundle:

git clone https://github.com/jtrackingai/analytics-tracking-automation.git
cd analytics-tracking-automation
npm install
npm run install:skills

This installs the umbrella skill into your agent's skills directory and makes the event-tracking CLI available.

No-Clone Alternative

npx skills add jtrackingai/analytics-tracking-automation

Verify Installation

npx event-tracking --version

The CLI requires Node.js 18+ and will auto-install Playwright Chromium on first npm install.

Core CLI Commands

The event-tracking CLI is the primary interface. All commands accept --help for detailed options.

Start a New Tracking Setup

npx event-tracking init \
  --url https://www.example.com \
  --output ./output \
  --ga4-measurement-id G-XXXXXXXXXX

This creates a site artifact directory under ./output/ (e.g., ./output/www_example_com/) and runs:

  • Site crawl and page classification
  • Business intent page grouping
  • Event schema generation
  • Schema review checkpoint

Resume an Existing Run

npx event-tracking resume \
  --artifact-dir ./output/www_example_com \
  --continue-through sync

Resumes from the last checkpoint and continues through the specified stage (schema, sync, preview, publish).

Audit an Existing GTM Setup

npx event-tracking audit \
  --url https://www.example.com \
  --gtm-account-id 123456789 \
  --gtm-container-id 12345678 \
  --output ./output

Compares live GTM configuration against recommended tracking plan and produces a health report.

Sync Schema to GTM

npx event-tracking sync \
  --artifact-dir ./output/www_example_com \
  --gtm-account-id 123456789 \
  --gtm-container-id 12345678

Creates/updates tags, triggers, and variables in GTM based on event-schema.json. Requires Google OAuth (prompted interactively).

Verify GTM Preview

npx event-tracking verify \
  --artifact-dir ./output/www_example_com \
  --gtm-preview-url "https://tagmanager.google.com/?gtm_preview=..."

Runs automated browser checks against GTM preview mode, validates event firing, and produces a verification report.

Publish GTM Container

npx event-tracking publish \
  --artifact-dir ./output/www_example_com \
  --gtm-account-id 123456789 \
  --gtm-container-id 12345678 \
  --version-name "v1.0 - Initial tracking"

Publishes the current workspace version to live.

Shopify-Specific Setup

npx event-tracking init \
  --url https://store.example.com \
  --output ./output \
  --platform shopify \
  --ga4-measurement-id G-XXXXXXXXXX

Uses Shopify-optimized tracking (cart, checkout, purchase events).

Configuration

Environment Variables

# Google OAuth credentials (create in Google Cloud Console)
export GOOGLE_CLIENT_ID=your-client-id.apps.googleusercontent.com
export GOOGLE_CLIENT_SECRET=your-client-secret

# Optional: GA4 Measurement ID
export GA4_MEASUREMENT_ID=G-XXXXXXXXXX

# Optional: GTM Account/Container IDs
export GTM_ACCOUNT_ID=123456789
export GTM_CONTAINER_ID=12345678

OAuth Setup

To sync with GTM, you need Google OAuth credentials:

  1. Go to Google Cloud Console
  2. Create a project and enable Tag Manager API
  3. Create OAuth 2.0 credentials (Desktop app type)
  4. Set redirect URI to http://localhost:3000/oauth/callback
  5. Export GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET

First sync will open a browser for OAuth consent. Credentials are cached in the artifact directory (oauth-tokens.json).

Artifact Directory Structure

Each site run creates an artifact directory like ./output/www_example_com/:

www_example_com/
├── site-analysis.json          # Crawl results, page inventory
├── page-groups.json            # Business intent groupings
├── event-schema.json           # GA4 events, parameters, triggers
├── gtm-sync-result.json        # GTM API operation results
├── verification-report.json    # Preview verification checks
├── oauth-tokens.json           # Cached OAuth credentials
└── checkpoint.json             # Last completed stage

These files are reviewable, editable, and resumable.

TypeScript API Examples

Programmatic Site Analysis

import { analyzeSite } from 'analytics-tracking-automation';

async function analyzeSiteExample() {
  const result = await analyzeSite({
    url: 'https://www.example.com',
    outputDir: './output',
    maxPages: 100,
    includeSubdomains: false,
  });

  console.log('Pages discovered:', result.pages.length);
  console.log('Page groups:', result.pageGroups);
  console.log('Recommended events:', result.events.length);
}

Generate Event Schema

import { generateEventSchema } from 'analytics-tracking-automation';

async function generateSchemaExample() {
  const schema = await generateEventSchema({
    artifactDir: './output/www_example_com',
    pageGroups: ['home', 'product', 'pricing', 'contact'],
    businessGoals: ['signup', 'purchase', 'demo_request'],
  });

  console.log('Generated events:', schema.events);
  console.log('Event parameters:', schema.parameters);
  console.log('GTM triggers:', schema.triggers);
}

Sync to GTM

import { syncToGTM } from 'analytics-tracking-automation';

async function syncExample() {
  const syncResult = await syncToGTM({
    artifactDir: './output/www_example_com',
    gtmAccountId: process.env.GTM_ACCOUNT_ID!,
    gtmContainerId: process.env.GTM_CONTAINER_ID!,
    oauthCredentials: {
      clientId: process.env.GOOGLE_CLIENT_ID!,
      clientSecret: process.env.GOOGLE_CLIENT_SECRET!,
    },
  });

  console.log('Tags created:', syncResult.tagsCreated);
  console.log('Triggers created:', syncResult.triggersCreated);
  console.log('Variables created:', syncResult.variablesCreated);
}

Verify Preview

import { verifyPreview } from 'analytics-tracking-automation';

async function verifyExample() {
  const report = await verifyPreview({
    artifactDir: './output/www_example_com',
    gtmPreviewUrl: 'https://tagmanager.google.com/?gtm_preview=...',
    testPages: [
      { url: 'https://www.example.com/', expectedEvents: ['page_view'] },
      { url: 'https://www.example.com/pricing', expectedEvents: ['page_view', 'view_pricing'] },
      { url: 'https://www.example.com/contact', expectedEvents: ['page_view', 'contact_intent'] },
    ],
  });

  console.log('Checks passed:', report.passed);
  console.log('Checks failed:', report.failed);
  console.log('Issues:', report.issues);
}

Publish Container

import { publishContainer } from 'analytics-tracking-automation';

async function publishExample() {
  const result = await publishContainer({
    gtmAccountId: process.env.GTM_ACCOUNT_ID!,
    gtmContainerId: process.env.GTM_CONTAINER_ID!,
    versionName: 'v1.0 - Initial tracking setup',
    versionDescription: 'GA4 events for core user journeys',
    oauthCredentials: {
      clientId: process.env.GOOGLE_CLIENT_ID!,
      clientSecret: process.env.GOOGLE_CLIENT_SECRET!,
    },
  });

  console.log('Published version:', result.publishedVersion);
  console.log('Live container URL:', result.containerUrl);
}

Common Patterns

Full End-to-End Setup

import {
  analyzeSite,
  generateEventSchema,
  syncToGTM,
  verifyPreview,
  publishContainer,
} from 'analytics-tracking-automation';

async function fullSetup(url: string, outputRoot: string) {
  // 1. Analyze site
  const analysis = await analyzeSite({ url, outputDir: outputRoot });
  const artifactDir = analysis.artifactDir;

  // 2. Generate schema
  const schema = await generateEventSchema({ artifactDir });

  // 3. Review (manual checkpoint)
  console.log('Review schema before syncing:', schema);
  // User reviews and edits event-schema.json if needed

  // 4. Sync to GTM
  const syncResult = await syncToGTM({
    artifactDir,
    gtmAccountId: process.env.GTM_ACCOUNT_ID!,
    gtmContainerId: process.env.GTM_CONTAINER_ID!,
    oauthCredentials: {
      clientId: process.env.GOOGLE_CLIENT_ID!,
      clientSecret: process.env.GOOGLE_CLIENT_SECRET!,
    },
  });

  // 5. Enter GTM preview mode manually, then verify
  const previewUrl = '...'; // GTM preview URL from user
  const verifyReport = await verifyPreview({ artifactDir, gtmPreviewUrl: previewUrl });

  if (verifyReport.passed === verifyReport.total) {
    // 6. Publish
    await publishContainer({
      gtmAccountId: process.env.GTM_ACCOUNT_ID!,
      gtmContainerId: process.env.GTM_CONTAINER_ID!,
      versionName: 'v1.0 - Automated setup',
      oauthCredentials: {
        clientId: process.env.GOOGLE_CLIENT_ID!,
        clientSecret: process.env.GOOGLE_CLIENT_SECRET!,
      },
    });
    console.log('Published successfully');
  } else {
    console.error('Verification failed, fix issues before publishing');
  }
}

Shopify Tracking Setup

import { analyzeSite, generateEventSchema, syncToGTM } from 'analytics-tracking-automation';

async function shopifySetup(storeUrl: string) {
  const analysis = await analyzeSite({
    url: storeUrl,
    outputDir: './output',
    platform: 'shopify',
  });

  const schema = await generateEventSchema({
    artifactDir: analysis.artifactDir,
    platform: 'shopify',
    shopifyEvents: ['add_to_cart', 'begin_checkout', 'purchase'],
  });

  await syncToGTM({
    artifactDir: analysis.artifactDir,
    gtmAccountId: process.env.GTM_ACCOUNT_ID!,
    gtmContainerId: process.env.GTM_CONTAINER_ID!,
    platform: 'shopify',
    oauthCredentials: {
      clientId: process.env.GOOGLE_CLIENT_ID!,
      clientSecret: process.env.GOOGLE_CLIENT_SECRET!,
    },
  });

  console.log('Shopify tracking synced. Manual verification required in Shopify admin.');
}

Audit Existing Setup

import { auditGTM } from 'analytics-tracking-automation';

async function auditExample(url: string) {
  const auditReport = await auditGTM({
    url,
    gtmAccountId: process.env.GTM_ACCOUNT_ID!,
    gtmContainerId: process.env.GTM_CONTAINER_ID!,
    outputDir: './output',
    oauthCredentials: {
      clientId: process.env.GOOGLE_CLIENT_ID!,
      clientSecret: process.env.GOOGLE_CLIENT_SECRET!,
    },
  });

  console.log('Healthy tags:', auditReport.healthy);
  console.log('Drifted tags:', auditReport.drifted);
  console.log('Missing events:', auditReport.missing);
  console.log('Recommendations:', auditReport.recommendations);
}

Resume from Checkpoint

import { resumeWorkflow } from 'analytics-tracking-automation';

async function resumeExample(artifactDir: string) {
  const result = await resumeWorkflow({
    artifactDir,
    continueThrough: 'publish', // 'schema' | 'sync' | 'preview' | 'publish'
  });

  console.log('Resumed from:', result.lastCheckpoint);
  console.log('Completed through:', result.completedStage);
}

Debugging and Troubleshooting

Selector Debugging with Playwright

If preview verification reports selector mismatches or events not firing:

# Open site in headed browser for visual inspection
npm run debug:open -- https://www.example.com

# Launch codegen to capture correct selectors
npm run debug:codegen -- https://www.example.com

Then update selectors in event-schema.json:

{
  "events": [
    {
      "eventName": "click_cta",
      "trigger": {
        "type": "click",
        "selector": "button.cta-button" // Updated selector
      }
    }
  ]
}

OAuth Token Issues

If OAuth fails or tokens are stale:

# Remove cached tokens
rm ./output/www_example_com/oauth-tokens.json

# Re-run sync to trigger new OAuth flow
npx event-tracking sync --artifact-dir ./output/www_example_com

GTM API Errors

Common GTM API issues:

  • 401 Unauthorized: OAuth credentials invalid or expired
  • 403 Forbidden: User lacks GTM account/container permissions
  • 404 Not Found: GTM account or container ID incorrect
  • 429 Rate Limit: Too many API requests; add delays between operations

Check GTM permissions: User must have at least "Publish" access to the container.

Preview Verification Failures

If automated verification fails:

  1. Check GTM Preview URL: Must be active and match container
  2. Inspect browser logs: Add --verbose flag for detailed Playwright logs
  3. Test manually: Open preview URL in browser, check dataLayer in console
  4. Validate selectors: Use npm run debug:codegen to verify element targeting
  5. Network issues: Ensure site is accessible and not behind VPN/firewall

Shopify Manual Verification

Shopify tracking requires manual verification in Shopify admin:

  1. Install GTM via Shopify admin (Settings → Online Store → Preferences)
  2. Add GTM container ID
  3. Test checkout flow in preview mode
  4. Verify add_to_cart, begin_checkout, purchase events in GTM debug view

Common Event Schema Fixes

Fix missing events:

{
  "events": [
    {
      "eventName": "form_submit",
      "trigger": {
        "type": "formSubmit",
        "selector": "form#contact-form"
      },
      "parameters": {
        "form_id": "contact-form",
        "form_destination": "contact"
      }
    }
  ]
}

Fix parameter mapping:

{
  "parameters": {
    "page_type": {
      "type": "dataLayer",
      "source": "pageType"
    },
    "user_id": {
      "type": "cookie",
      "source": "user_id"
    }
  }
}

Telemetry Configuration

Anonymous startup signals are sent by default. Opt out:

npx event-tracking config telemetry --disable

Richer diagnostics (opt-in):

npx event-tracking config telemetry --enable-diagnostics

Check current preference:

npx event-tracking config telemetry --show

Advanced Configuration

Custom Crawler Settings

Edit artifact site-analysis.json before schema generation:

{
  "crawlConfig": {
    "maxPages": 200,
    "includeSubdomains": true,
    "excludePatterns": ["/blog/*", "/admin/*"],
    "followExternalLinks": false
  }
}

Custom Page Grouping

Override auto-generated page groups in page-groups.json:

{
  "groups": [
    {
      "name": "conversion",
      "intent": "purchase",
      "patterns": ["/checkout/*", "/cart", "/order-confirmation"]
    },
    {
      "name": "support",
      "intent": "help",
      "patterns": ["/help/*", "/faq", "/contact"]
    }
  ]
}

Event Schema Customization

Manually edit event-schema.json for fine-grained control:

{
  "events": [
    {
      "eventName": "custom_conversion",
      "trigger": {
        "type": "click",
        "selector": "button[data-track='conversion']"
      },
      "parameters": {
        "conversion_type": {
          "type": "element",
          "source": "data-conversion-type"
        },
        "conversion_value": {
          "type": "element",
          "source": "data-value"
        }
      },
      "conditions": {
        "pagePathContains": "/pricing"
      }
    }
  ]
}

When to Use This Skill

This skill is ideal when:

  • Setting up GA4 + GTM tracking from scratch
  • Auditing or refactoring existing tracking implementations
  • Implementing Shopify storefront tracking
  • Automating repetitive tracking tasks across multiple sites
  • Needing reviewable, resumable tracking workflows
  • Working with non-technical stakeholders who need business-friendly artifacts

This skill is NOT ideal for:

  • Real-time production debugging (use GTM Debug View instead)
  • Server-side tracking or custom measurement protocols
  • Multi-destination tracking (Adobe, Segment, etc.) without GTM
  • Sites requiring authentication or complex session flows

Key Files and Extension Points

  • src/core/analyzer.ts: Site crawl and page classification logic
  • src/core/schema-generator.ts: Event schema generation
  • src/core/gtm-sync.ts: GTM API integration
  • src/core/verifier.ts: Automated preview verification
  • src/platforms/shopify.ts: Shopify-specific tracking
  • event-schema.json: Editable event schema artifact
  • page-groups.json: Editable page grouping artifact

Extend by forking and modifying these files, or by editing artifacts between CLI stages.

Further Reading

  • Skill contract: See SKILL.md in repository for agent-facing workflow details
  • Developer guide: See DEVELOPING.md for CLI internals and maintainer workflow
  • Skill installation: See docs/README.install.md for advanced install options
  • JTracking website: https://www.jtracking.ai/skills

Support

For issues, questions, or feature requests, contact support@jtracking.ai or open an issue on GitHub.

FAQ

What does the analytics-tracking-automation skill do?

AI-powered GA4 + GTM event tracking automation — analyzes sites, designs event schemas, syncs GTM containers, runs preview verification, and publishes tracking implementations.

How do I install analytics-tracking-automation?

Run npx skills add https://github.com/reason-machines/data-skills --skill analytics-tracking-automation in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/analytics-tracking-automation/ (personal) or .claude/skills/analytics-tracking-automation/ (project).

Which AI agents can use analytics-tracking-automation?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is analytics-tracking-automation safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains analytics-tracking-automation?

It is published by reason-machines in reason-machines/data-skills. It has 2,047 recorded installs.

More from reason-machines/data-skills

View all →

apache-airflow-orchestration

reason-machines/data-skills

Expert knowledge of Apache Airflow for building, scheduling, and monitoring data pipelines and workflows

DevOps & Cloud2.4K installs

datatalks-data-engineering-zoomcamp

reason-machines/data-skills

Free 9-week data engineering course covering Docker, Terraform, Kestra, BigQuery, dbt, Spark, and Kafka with hands-on projects

Data & Databases2.4K installs

llm-public-opinion-analytics-assistant

reason-machines/data-skills

Multi-platform hot search crawler and LLM-powered public opinion analysis system with clustering, sentiment analysis, and multi-channel push notifications

AI & Agents2.4K installs

roblox-mm2-analytics-toolkit

reason-machines/data-skills

Analytics and inventory management toolkit for Roblox Murder Mystery 2 gameplay optimization

Data & Databases2.4K installs

mm2-analytics-roblox-tracker

reason-machines/data-skills

Analyze Murder Mystery 2 gameplay data, track inventory, and optimize strategy using this Roblox analytics toolkit

Data & Databases2.4K installs

mm2-roblox-analytics-toolkit

reason-machines/data-skills

Murder Mystery 2 gameplay analytics, inventory tracking, and strategy optimization toolkit for Roblox

Data & Databases2.4K installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

Productivity & Automation815.7K installs

lark-base

open.feishu.cn

飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。

Productivity & Automation815K installs

lark-drive

open.feishu.cn

飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。

Productivity & Automation815K installs

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

Productivity & Automation814.8K installs

lark-im

open.feishu.cn

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。

Productivity & Automation814.1K installs