Modo
Agendar llamada

analytics: armar el plan de medición de tu web con GA4, GTM y UTMs

Arma o audita el plan de medición de tu web: qué eventos medir, cómo nombrarlos, cómo instalarlos en GA4 o GTM y cómo etiquetar los enlaces con UTMs.

analytics: armar el plan de medición de tu web con GA4, GTM y UTMs

Respuesta rápida

Qué es
analytics es una skill de Corey Haines (licencia MIT) que le enseña a Claude a armar y auditar el plan de medición de una web: qué eventos medir, cómo nombrarlos, cómo instalarlos en GA4 o Google Tag Manager y cómo etiquetar los enlaces con UTMs.
Qué le das
Qué decisiones quieres tomar con los datos, qué herramientas usas hoy, qué ya se mide y quién lo va a instalar
Qué te devuelve
Un plan de medición con eventos, propiedades, conversiones y dimensiones, la convención de UTMs y una lista para validar que todo dispara bien
Licencia
MIT
En GitHub
60,6 mil estrellas · actualizada el
Revisada por Claura

Instálala en una línea para todos tus proyectos, en Claude Code, Cursor, Codex y más:

npx skills add coreyhaines31/marketingskills --skill analytics -g

Funciona en

Claude CodeEn ~/.claude/skills/
CursorEn ~/.agents/skills/
CodexEn ~/.agents/skills/
Gemini CLIEn ~/.agents/skills/

Pedidos para probarla

Con la skill instalada, copia uno y pégaselo a tu agente tal cual, o cambia los datos por los tuyos.

  • Arma el plan de medición de mi web de turnos: qué eventos medir en GA4, con qué nombres y cuáles son conversiones.

  • Dame la convención de UTMs para mis campañas de Meta, Google y newsletter, con ejemplos de cada una.

  • Revisa este listado de eventos que ya mando a GA4 [pega la lista] y dime qué sobra y qué falta.

#Qué hace

analytics es la skill de medición de Corey Haines. Antes de proponer nada pregunta tres cosas: qué decisiones van a salir de los datos y cuáles son las conversiones clave, qué se mide hoy y con qué herramientas, y en qué tecnología está hecha la web y qué requisitos de privacidad hay. Trabaja con siete principios, entre ellos medir para decidir y no por acumular datos, calcular cada total y cada tasa con una planilla o un script en lugar de sumar a ojo, y dividir siempre numerador y denominador del mismo periodo cerrado (nunca el gasto de un mes entero contra las ventas de dos semanas).

El resultado principal es el plan de medición: una tabla con cada evento, su descripción, sus propiedades y su disparador, más las dimensiones personalizadas y las conversiones con su forma de conteo. Trae la convención de nombres objeto y acción (form_submitted, cta_hero_clicked), los eventos esenciales para un sitio de marketing y para un producto, la instalación rápida de GA4 en cinco pasos, la estructura de un contenedor de Google Tag Manager y una lista de validación con DebugView y el modo de vista previa. La profundidad está en tres archivos de referencia: una biblioteca de eventos por tipo de negocio, la implementación de GA4 y la de Google Tag Manager.

La sección de UTMs es de las más completas: todo en minúsculas, guiones entre palabras, una sola forma de escribir cada fuente y nunca datos personales en un enlace. Trae una tabla de patrones por tipo de socio (newsletter, creador, podcast, afiliado, comunidad), con un enlace por cada publicación, y explica cómo crear en GA4 un grupo de canales para que esas visitas no caigan en «sin asignar», incluido uno para el tráfico que llega desde ChatGPT, Perplexity y otros asistentes.

#Cómo aplicarla a tu negocio

Caso de ejemplo: una escuela de idiomas online de Lima que vende cursos por una landing con formulario y un botón de WhatsApp, pauta en Meta y paga a dos creadoras de contenido. Hoy GA4 le muestra visitas, pero no sabe cuántas consultas trae cada canal.

  1. Preguntas primero. El pedido a la skill: «queremos saber cada semana cuántas consultas trae cada canal y qué creadora rinde más». De ahí salen tres conversiones: formulario enviado, clic en WhatsApp e inscripción pagada.
  2. Plan de medición. Sale la tabla: form_submitted con el tipo de curso, un evento propio para el clic en WhatsApp con la ubicación del botón, y el evento recomendado purchase para el pago. Cada uno con su disparador y cuál cuenta como conversión.
  3. UTMs de las creadoras. Siguiendo el patrón de la skill, utm_medium=creator, la plataforma en utm_source y el nombre de la creadora en utm_campaign, con un enlace distinto por publicación. Más el grupo de canales en GA4 para que «creator» aparezca como canal propio.
  4. Validación. Antes de dar por terminado, la lista: que cada evento dispare una sola vez, en celular y en computadora, y que ninguna propiedad lleve el correo o el teléfono de quien escribe.

Con eso, el informe semanal deja de ser «tuvimos 4.000 visitas» (cifra de ejemplo) y pasa a ser cuántas consultas trajo cada canal.

#Cómo instalarla

Es una skill que corre en cualquier agente, con tres archivos de referencia en su carpeta.

  • Con una línea, para cualquier agente: npx skills add coreyhaines31/marketingskills --skill analytics -g la deja instalada en todos tus proyectos.
  • A mano: copia la carpeta skills/analytics/ completa a ~/.claude/skills/ para Claude Code, o a ~/.agents/skills/ para Cursor, Codex y Gemini CLI.
  • App de Claude: comprime la carpeta en un ZIP y súbela desde Customize, Skills, «Upload a skill».

No necesita nada más para armar el plan. Para que lea tus datos de GA4 directamente, el repositorio documenta un conector y guías para Mixpanel, Amplitude, PostHog y Segment. Las instrucciones están en inglés: pídele la salida en español.

El SKILL.md completo (con la licencia y la fuente) está más abajo.

El SKILL.md completo

Skill original de Corey Haines (MIT). Fuente: github.com/coreyhaines31/marketingskills/tree/main/skills/analytics.

El archivo original está en inglés y va tal cual, sin traducir. Lo de arriba de esta ficha es el resumen en español: qué hace, cómo aplicarla y cómo instalarla.

Leer el archivo (377 líneas)

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

Check for product marketing context first: If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Before implementing tracking, understand:

  1. Business Context - What decisions will this data inform? What are key conversions?
  2. Current State - What tracking exists? What tools are in use?
  3. Technical Context - What's the tech stack? 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
5. Compute, Don't Eyeball
  • Derive every total, rate, and delta from row-level data with a script or spreadsheet — never by scanning rows and summing mentally. One silently dropped row corrupts every figure downstream of it.
  • Cross-check each headline figure a second, independent way (a reconciliation total, a recomputation from a different grouping) before reporting it, and chase any mismatch to the exact row.
  • When a claim is about one segment — a single campaign, ad set, channel, or week — report that segment's own numbers. Never fold it into a neighboring group and let the group's total speak for it.
6. Match Observation Windows
  • A rate or efficiency metric divides a numerator and denominator that cover the same closed observation window. Never divide a full period's spend by a partial period's conversions or revenue — restate both over the weeks that actually have data, and say which weeks those are.
  • Cohort rates use only cohorts whose observation window has ended. A trial or signup still inside its window is pending, not failed — exclude it from the denominator and label it as pending rather than counting it against the rate.
7. Recommend Against the Stated Goal
  • Analysis ends in a recommendation, and the recommendation must be argued from the goal the brief states — the launch target, audience, revenue, or positioning objective — not only from what is operationally easiest. Name which stated goal each option serves and what it trades away.

Tracking Plan Framework

Structure
Event Name | Category | Properties | Trigger | Notes
---------- | -------- | ---------- | ------- | -----
Event Types
TypeExamples
PageviewsAutomatic, enhanced with metadata
User ActionsButton clicks, form submissions, feature usage
System EventsSignup completed, purchase, subscription changed
Custom ConversionsGoal completions, funnel stages

For comprehensive event lists: See references/event-library.md


Event Naming Conventions

Recommended Format: Object-Action
signup_completed
button_clicked
form_submitted
article_read
checkout_payment_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
  • Keep provider-defined names when using automatic or recommended events (e.g. GA4 click, view_search_results, purchase). Map internal business names explicitly; naming a custom event does not make the provider collect it automatically.

Essential Events

Marketing Site
EventProperties
cta_clickedbutton_text, location
form_submittedform_type
signup_completedmethod, source
demo_requested-
Product/App
EventProperties
onboarding_step_completedstep_number, step_name
feature_usedfeature_name
purchase_completedplan, value
subscription_cancelledreason

For full event library by business type: See references/event-library.md


Event Properties

Standard Properties
CategoryProperties
Pagepage_title, page_location, page_referrer
Useruser_id, user_type, account_id, plan_type
Campaignsource, medium, campaign, content, term
Productproduct_id, product_name, category, price
Best Practices
  • Use consistent property names
  • Include relevant context
  • Don't duplicate automatic properties
  • Avoid PII in properties

GA4 Implementation

Quick Setup
  1. Create GA4 property and data stream
  2. Install gtag.js or GTM
  3. Enable enhanced measurement
  4. Configure custom events
  5. Mark conversions in Admin
Event Example
// GA4's recommended sign_up event, not a custom name, so it feeds built-in reports.
// Your tracking plan can still call this signup_completed; map the name explicitly.
gtag('event', 'sign_up', {
  'method': 'email',
  'plan': 'free'
});

For detailed GA4 implementation: See references/ga4-implementation.md


Google Tag Manager

Container Structure
ComponentPurpose
TagsCode that executes (GA4, pixels)
TriggersWhen tags fire (page view, click)
VariablesDynamic values (click text, data layer)
Data Layer Pattern
dataLayer.push({
  'event': 'form_submitted',
  'form_name': 'contact',
  'form_location': 'footer'
});

For detailed GTM implementation: See references/gtm-implementation.md


UTM Parameter Strategy

Standard Parameters
ParameterPurposeExample
utm_sourceTraffic sourcegoogle, newsletter
utm_mediumMarketing mediumcpc, email, social
utm_campaignCampaign namespring-sale
utm_contentDifferentiate versionshero-cta
utm_termPaid search keywordsrunning-shoes
Naming Conventions
  • Lowercase everything. GA4 treats LinkedIn and linkedin as two sources, and the split never merges back.
  • Hyphens between words. No spaces, underscores, or +. Pick one separator for the whole company; this skill uses hyphens.
  • One spelling per source. linkedin, never also li or linkedin.com. Keep the allowed values in a shared sheet and build links from it.
  • No personal data. Never put emails, names, phone numbers, or user IDs in a UTM. They land in analytics reports and in referrer logs, and Google's terms prohibit sending PII to GA4.
  • Specific but short: blog-footer-cta, not cta1.
  • Test the final URL. Shorteners and redirects can drop or double parameters. Click the live link and check the landing URL before the campaign ships.
UTM Patterns by Partner Type

Partner links break most often because each deal gets named on the spot. Fix the pattern per partner type once: utm_medium names the kind of deal, utm_source names who sent the traffic.

Partner typeutm_sourceutm_mediumutm_campaignutm_content
Newsletter{partner} (one per partner, across all their publications)newsletter{partner}-{publication}-{yyyy}-{mm}{placement}-{yyyy-mm-dd}
Creator (YouTube, LinkedIn, TikTok){platform}creator{creator}{post-date} or the video ID
Podcast{podcast}podcast{podcast}-{yyyy}-{mm}{spot}-{yyyy-mm-dd} (pre-roll, mid-roll)
Affiliate{partner}affiliate{partner}-affiliateplacement, if they have several
Community{community}community{community}-{program}the channel or post, if known
  • Use creator as the medium for paid creator deals, not social (which mixes them with your organic posts) or video (which mixes them with paid video ads). The platform goes in utm_source.
  • One link per placement. A newsletter that runs you on two dates gets two links, so each date's clicks stay separate. The monthly utm_campaign rolls them up.
  • Add a custom channel group in GA4. GA4's default grouping sends mediums like newsletter, creator, podcast, and community to Unassigned (only affiliate and email map to a default channel). Create a channel group with a rule per medium so partner traffic shows up as its own channels.
  • Podcast and video links often aren't clickable, so pair the UTM link with a promo code or vanity URL. See influencer-marketing for the rest of partner measurement.

The partner-type pattern is adapted from Wispr Flow's link-creator skill (MIT), published in the skills.marketing library.

Traffic From AI Assistants

You can't tag links that ChatGPT, Claude, Perplexity, Gemini, or Copilot put in their answers. Some of those visits arrive with a referrer (chatgpt.com, perplexity.ai) or an assistant-added utm_source; many arrive as direct, or come later through a branded search.

  • Add a GA4 channel group rule that matches known assistant referrers and sources into an "AI assistants" channel, and update the list as new assistants appear.
  • Treat that channel as the floor. Assistant-driven visits that show up as direct or branded search can be most of the effect, and they won't carry the referrer.
  • For measuring the full effect (exposure, delayed visits, and longer attribution windows), see ai-seo. For reconciling it with other sources, see attribution.

Debugging and Validation

Testing Tools
ToolUse For
GA4 DebugViewReal-time event monitoring
GTM Preview ModeTest triggers before publish
Browser ExtensionsTag Assistant, dataLayer Inspector
Validation Checklist
  • Events firing on correct triggers
  • Property values populating correctly
  • No duplicate events
  • Works across browsers and mobile
  • Conversions recorded correctly
  • No PII leaking
Common Issues
IssueCheck
Events not firingTrigger config, GTM loaded
Wrong valuesVariable path, data layer structure
Duplicate eventsMultiple containers, trigger firing twice

Privacy and Compliance

Considerations
  • Cookie consent required in EU/UK/CA
  • No PII in analytics properties
  • Data retention settings
  • User deletion capabilities
Implementation
  • Use consent mode (wait for consent)
  • IP anonymization
  • Only collect what you need
  • Integrate with consent management platform

Output Format

Tracking Plan Document
# [Site/Product] Tracking Plan

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

## Events

| Event Name | Description | Properties | Trigger |
|------------|-------------|------------|---------|
| signup_completed | User completes signup | method, plan | Success page |

## Custom Dimensions

| Name | Scope | Parameter |
|------|-------|-----------|
| user_type | User | user_type |

## Conversions

| Conversion | Event | Counting |
|------------|-------|----------|
| Signup | signup_completed | Once per session |

Task-Specific Questions

  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?

Tool Integrations

For implementation, see the tools registry. Key analytics tools:

ToolBest ForMCPGuide
GA4Web analytics, Google ecosystem✓ga4.md
MixpanelProduct analytics, event tracking-mixpanel.md
AmplitudeProduct analytics, cohort analysis-amplitude.md
PostHogOpen-source analytics, session replay-posthog.md
SegmentCustomer data platform, routing-segment.md

Related Skills

  • ab-testing: For experiment tracking
  • conversion-tracking: For getting conversions (including GA4 key events from forms and bookings) to ad platforms and GA4, and verifying they arrive
  • attribution: For attribution models, multi-touch/MMM/incrementality, and reconciling conflicting numbers across tools (once tracking is live)
  • seo-audit: For organic traffic analysis
  • cro: For conversion optimization (uses this data)
  • revops: For pipeline metrics, CRM tracking, and revenue attribution
Copiar el archivo tal cual
---
name: analytics
description: "When the user wants to set up or audit analytics, or asks whether a metric or number is calculated right, what to track, or how to name events: tracking plans, GA4, GTM, Mixpanel, PostHog, UTMs. Rate metrics divide matching closed windows, never full-period spend by partial-period results. For conversions in ad platforms, see conversion-tracking. For attribution or platforms that over-claim, see attribution. For tests, see ab-testing."
metadata:
  version: 2.2.5
---

<!--
Skill original: analytics, de Corey Haines (https://github.com/coreyhaines31/marketingskills/tree/main/skills/analytics)
Licencia: MIT. Reproducida con atribución según los términos de la licencia.
Copia publicada en claura-ai.com/skills.
-->

# 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

**Check for product marketing context first:**
If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Before implementing tracking, understand:

1. **Business Context** - What decisions will this data inform? What are key conversions?
2. **Current State** - What tracking exists? What tools are in use?
3. **Technical Context** - What's the tech stack? 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

### 5. Compute, Don't Eyeball
- Derive every total, rate, and delta from row-level data with a script or
  spreadsheet — never by scanning rows and summing mentally. One silently
  dropped row corrupts every figure downstream of it.
- Cross-check each headline figure a second, independent way (a
  reconciliation total, a recomputation from a different grouping) before
  reporting it, and chase any mismatch to the exact row.
- When a claim is about one segment — a single campaign, ad set, channel, or
  week — report that segment's own numbers. Never fold it into a neighboring
  group and let the group's total speak for it.

### 6. Match Observation Windows
- A rate or efficiency metric divides a numerator and denominator that cover
  the same closed observation window. Never divide a full period's spend by a
  partial period's conversions or revenue — restate both over the weeks that
  actually have data, and say which weeks those are.
- Cohort rates use only cohorts whose observation window has ended. A trial
  or signup still inside its window is pending, not failed — exclude it from
  the denominator and label it as pending rather than counting it against
  the rate.

### 7. Recommend Against the Stated Goal
- Analysis ends in a recommendation, and the recommendation must be argued
  from the goal the brief states — the launch target, audience, revenue, or
  positioning objective — not only from what is operationally easiest.
  Name which stated goal each option serves and what it trades away.

---

## Tracking Plan Framework

### Structure

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

### Event Types

| Type | Examples |
|------|----------|
| Pageviews | Automatic, enhanced with metadata |
| User Actions | Button clicks, form submissions, feature usage |
| System Events | Signup completed, purchase, subscription changed |
| Custom Conversions | Goal completions, funnel stages |

**For comprehensive event lists**: See [references/event-library.md](references/event-library.md)

---

## Event Naming Conventions

### Recommended Format: Object-Action

```
signup_completed
button_clicked
form_submitted
article_read
checkout_payment_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
- Keep provider-defined names when using automatic or recommended events (e.g. GA4 `click`, `view_search_results`, `purchase`). Map internal business names explicitly; naming a custom event does not make the provider collect it automatically.

---

## Essential Events

### Marketing Site

| Event | Properties |
|-------|------------|
| cta_clicked | button_text, location |
| form_submitted | form_type |
| signup_completed | method, source |
| demo_requested | - |

### Product/App

| Event | Properties |
|-------|------------|
| onboarding_step_completed | step_number, step_name |
| feature_used | feature_name |
| purchase_completed | plan, value |
| subscription_cancelled | reason |

**For full event library by business type**: See [references/event-library.md](references/event-library.md)

---

## Event Properties

### Standard Properties

| Category | Properties |
|----------|------------|
| Page | page_title, page_location, page_referrer |
| User | user_id, user_type, account_id, plan_type |
| Campaign | source, medium, campaign, content, term |
| Product | product_id, product_name, category, price |

### Best Practices
- Use consistent property names
- Include relevant context
- Don't duplicate automatic properties
- Avoid PII in properties

---

## GA4 Implementation

### Quick Setup

1. Create GA4 property and data stream
2. Install gtag.js or GTM
3. Enable enhanced measurement
4. Configure custom events
5. Mark conversions in Admin

### Event Example

```javascript
// GA4's recommended sign_up event, not a custom name, so it feeds built-in reports.
// Your tracking plan can still call this signup_completed; map the name explicitly.
gtag('event', 'sign_up', {
  'method': 'email',
  'plan': 'free'
});
```

**For detailed GA4 implementation**: See [references/ga4-implementation.md](references/ga4-implementation.md)

---

## Google Tag Manager

### Container Structure

| Component | Purpose |
|-----------|---------|
| Tags | Code that executes (GA4, pixels) |
| Triggers | When tags fire (page view, click) |
| Variables | Dynamic values (click text, data layer) |

### Data Layer Pattern

```javascript
dataLayer.push({
  'event': 'form_submitted',
  'form_name': 'contact',
  'form_location': 'footer'
});
```

**For detailed GTM implementation**: See [references/gtm-implementation.md](references/gtm-implementation.md)

---

## UTM Parameter Strategy

### Standard Parameters

| Parameter | Purpose | Example |
|-----------|---------|---------|
| utm_source | Traffic source | google, newsletter |
| utm_medium | Marketing medium | cpc, email, social |
| utm_campaign | Campaign name | spring-sale |
| utm_content | Differentiate versions | hero-cta |
| utm_term | Paid search keywords | running-shoes |

### Naming Conventions
- **Lowercase everything.** GA4 treats `LinkedIn` and `linkedin` as two sources, and the split never merges back.
- **Hyphens between words.** No spaces, underscores, or `+`. Pick one separator for the whole company; this skill uses hyphens.
- **One spelling per source.** `linkedin`, never also `li` or `linkedin.com`. Keep the allowed values in a shared sheet and build links from it.
- **No personal data.** Never put emails, names, phone numbers, or user IDs in a UTM. They land in analytics reports and in referrer logs, and Google's terms prohibit sending PII to GA4.
- **Specific but short:** `blog-footer-cta`, not `cta1`.
- **Test the final URL.** Shorteners and redirects can drop or double parameters. Click the live link and check the landing URL before the campaign ships.

### UTM Patterns by Partner Type

Partner links break most often because each deal gets named on the spot. Fix the pattern per partner type once: `utm_medium` names the kind of deal, `utm_source` names who sent the traffic.

| Partner type | utm_source | utm_medium | utm_campaign | utm_content |
|---|---|---|---|---|
| Newsletter | `{partner}` (one per partner, across all their publications) | `newsletter` | `{partner}-{publication}-{yyyy}-{mm}` | `{placement}-{yyyy-mm-dd}` |
| Creator (YouTube, LinkedIn, TikTok) | `{platform}` | `creator` | `{creator}` | `{post-date}` or the video ID |
| Podcast | `{podcast}` | `podcast` | `{podcast}-{yyyy}-{mm}` | `{spot}-{yyyy-mm-dd}` (pre-roll, mid-roll) |
| Affiliate | `{partner}` | `affiliate` | `{partner}-affiliate` | placement, if they have several |
| Community | `{community}` | `community` | `{community}-{program}` | the channel or post, if known |

- **Use `creator` as the medium for paid creator deals**, not `social` (which mixes them with your organic posts) or `video` (which mixes them with paid video ads). The platform goes in `utm_source`.
- **One link per placement.** A newsletter that runs you on two dates gets two links, so each date's clicks stay separate. The monthly `utm_campaign` rolls them up.
- **Add a custom channel group in GA4.** GA4's default grouping sends mediums like `newsletter`, `creator`, `podcast`, and `community` to Unassigned (only `affiliate` and `email` map to a default channel). Create a channel group with a rule per medium so partner traffic shows up as its own channels.
- Podcast and video links often aren't clickable, so pair the UTM link with a promo code or vanity URL. See **influencer-marketing** for the rest of partner measurement.

*The partner-type pattern is adapted from Wispr Flow's link-creator skill (MIT), published in the skills.marketing library.*

### Traffic From AI Assistants

You can't tag links that ChatGPT, Claude, Perplexity, Gemini, or Copilot put in their answers. Some of those visits arrive with a referrer (`chatgpt.com`, `perplexity.ai`) or an assistant-added `utm_source`; many arrive as direct, or come later through a branded search.

- Add a GA4 channel group rule that matches known assistant referrers and sources into an "AI assistants" channel, and update the list as new assistants appear.
- Treat that channel as the floor. Assistant-driven visits that show up as direct or branded search can be most of the effect, and they won't carry the referrer.
- For measuring the full effect (exposure, delayed visits, and longer attribution windows), see **ai-seo**. For reconciling it with other sources, see **attribution**.

---

## Debugging and Validation

### Testing Tools

| Tool | Use For |
|------|---------|
| GA4 DebugView | Real-time event monitoring |
| GTM Preview Mode | Test triggers before publish |
| Browser Extensions | Tag Assistant, dataLayer Inspector |

### Validation Checklist

- [ ] Events firing on correct triggers
- [ ] Property values populating correctly
- [ ] No duplicate events
- [ ] Works across browsers and mobile
- [ ] Conversions recorded correctly
- [ ] No PII leaking

### Common Issues

| Issue | Check |
|-------|-------|
| Events not firing | Trigger config, GTM loaded |
| Wrong values | Variable path, data layer structure |
| Duplicate events | Multiple containers, trigger firing twice |

---

## Privacy and Compliance

### Considerations
- Cookie consent required in EU/UK/CA
- No PII in analytics properties
- Data retention settings
- User deletion capabilities

### Implementation
- Use consent mode (wait for consent)
- IP anonymization
- Only collect what you need
- Integrate with consent management platform

---

## Output Format

### Tracking Plan Document

```markdown
# [Site/Product] Tracking Plan

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

## Events

| Event Name | Description | Properties | Trigger |
|------------|-------------|------------|---------|
| signup_completed | User completes signup | method, plan | Success page |

## Custom Dimensions

| Name | Scope | Parameter |
|------|-------|-----------|
| user_type | User | user_type |

## Conversions

| Conversion | Event | Counting |
|------------|-------|----------|
| Signup | signup_completed | Once per session |
```

---

## Task-Specific Questions

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?

---

## Tool Integrations

For implementation, see the [tools registry](https://github.com/coreyhaines31/marketingskills/blob/main/tools/REGISTRY.md). Key analytics tools:

| Tool | Best For | MCP | Guide |
|------|----------|:---:|-------|
| **GA4** | Web analytics, Google ecosystem | ✓ | [ga4.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/ga4.md) |
| **Mixpanel** | Product analytics, event tracking | - | [mixpanel.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/mixpanel.md) |
| **Amplitude** | Product analytics, cohort analysis | - | [amplitude.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/amplitude.md) |
| **PostHog** | Open-source analytics, session replay | - | [posthog.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/posthog.md) |
| **Segment** | Customer data platform, routing | - | [segment.md](https://github.com/coreyhaines31/marketingskills/blob/main/tools/integrations/segment.md) |

---

## Related Skills

- **ab-testing**: For experiment tracking
- **conversion-tracking**: For getting conversions (including GA4 key events from forms and bookings) to ad platforms and GA4, and verifying they arrive
- **attribution**: For attribution models, multi-touch/MMM/incrementality, and reconciling conflicting numbers across tools (once tracking is live)
- **seo-audit**: For organic traffic analysis
- **cro**: For conversion optimization (uses this data)
- **revops**: For pipeline metrics, CRM tracking, and revenue attribution

Preguntas frecuentes sobre la skill analytics

¿Qué es la skill analytics y para qué sirve?

analytics es una skill de Corey Haines (github.com/coreyhaines31/marketingskills, licencia MIT) para montar la medición de un sitio o producto. Parte de una idea: cada evento tiene que servir para tomar una decisión. Con eso arma el plan de medición (evento, categoría, propiedades, disparador), fija la convención de nombres objeto y acción en minúsculas, explica la instalación en GA4 y Google Tag Manager, define cómo etiquetar los enlaces con UTMs y deja una lista para validar que todo dispare bien. También revisa si un número está bien calculado, por ejemplo un costo por cliente que divide periodos que no coinciden.

¿Cómo la aplico a la web de mi negocio?

Empiezas por las preguntas, no por los eventos: qué quieres saber cada semana y qué harías distinto según la respuesta. Le pasas eso, las herramientas que usas y lo que ya se mide, y te devuelve el plan con los eventos esenciales, cuáles marcar como conversión y cómo instalarlos. Si te lo implementa un programador, el plan con el dataLayer de ejemplo es lo que le entregas. Una vez que la medición está viva, el paso siguiente es decidir qué canal se lleva el crédito de cada venta, que es el trabajo de attribution.

¿En qué se diferencia de activar GA4 con la configuración por defecto?

La configuración por defecto mide visitas y algunos clics, pero no sabe qué es una venta o un contacto para tu negocio. La skill te obliga a definirlo y a usar los eventos recomendados de Google cuando existen (sign_up, purchase) para que alimenten los informes que ya trae GA4. Además corrige errores comunes: UTMs con mayúsculas que GA4 cuenta como dos fuentes distintas, eventos duplicados por dos contenedores, datos personales metidos en una propiedad y medios como newsletter o podcast que GA4 manda a «sin asignar» si no creas un grupo de canales propio. También propone un canal aparte para el tráfico que llega desde asistentes de IA.

¿Qué tengo que tener en cuenta antes de usarla?

Tres cosas. Está en inglés: pídele el plan en español, pero deja los nombres de eventos en inglés y en minúsculas, como recomienda. La parte de privacidad nombra el consentimiento de cookies de la Unión Europea, Reino Unido y Canadá; en España aplica el RGPD, y en Latinoamérica cada país tiene su propia ley, así que confirma la tuya. Y un detalle medido en claura-ai.com: la tabla de propiedades estándar sugiere source, medium y campaign, pero si mandas parámetros con esos nombres dentro de un evento de GA4, Analytics los lee como el origen de la visita y la sesión queda como «sin asignar». Usa nombres propios, como form_source. Si prefieres que Claura lo deje funcionando, mira analítica de marketing.

Más skills de Automatización

Para seguir con este tema

Elegí qué cookies usamos