SkillMachine
All skills

Analytics Tracking Plan Generator

Document

Builds a decision-first, GA4-ready event tracking plan from scratch.

Live output preview

Input Format: Input FormatOutputWatch the Output: Watch the Output

A plan is required to view this content

Choose a plan to access input format, sample outputs, and live previews.

View Plans →

About the skill

What it does

It turns your business context into a tracking plan document. It works from the "Track for Decisions, Not Data" principle: it asks which decisions you need to make and derives the event list backwards from those questions, keeping vanity metrics (raw pageviews, total clicks) out of the plan. The result is a taxonomy + property contract you can hand straight to a dev team or port into a GTM container, and keep as a living document.

The generated plan covers: an object-action event taxonomy (signup_completed, cta_hero_clicked), the 4 event types (Pageview / User Action / System Event / Custom Conversion), a standard property schema (Page / User / Campaign / Product axes), a custom dimension map, conversion definitions (with counting rules), a UTM parameter strategy, GA4/GTM dataLayer examples, a validation checklist (event firing, duplicate detection, PII leakage), and privacy/consent implementation (consent mode, IP anonymization).

When to use it

  • Setting up tracking from scratch for a new product or site
  • Re-taxonomizing messy, inconsistently named existing events
  • Standardizing a tracking plan before a GA4 migration or a Mixpanel/Segment rollout
  • Creating an auditable reference plan to answer "are my events firing and measuring the right thing?"
  • Delivering a clear implementation brief to a dev team

Method / frameworks

  • Object-Action naming convention (snake_case, lowercase) — aligned with GA4's official guidance; keep context in properties, not the event name.
  • Tracking Plan Framework — the Event Name · Category · Properties · Trigger · Notes structure; a living-document approach (Mixpanel Lexicon / Segment Protocols logic).
  • Questions-first (backwards design) — decision → metric → event derivation chain.
  • 4 Core Principles — decisions-not-data, start-with-questions, name-consistently, maintain-data-quality.
  • Data quality gates — de-dup (insert_id), property validation, PII scanning.
  • Consent Mode + IP anonymization — for EU/UK/CA compliance. Related skills: ab-testing, cro, revops.

How do I use this skill?

You don't "run" a skill — after installing it you just tell the agent your task (e.g. ask for the relevant job), and the skill kicks in by itself when its description matches.

Upload the analytics.zip you downloaded as-is — no packaging needed, the format is already correct (folder at root).

  1. Open Settings → Customize → Skills
  2. Upload → select the analytics.zip you downloaded
  3. Claude reads SKILL.md; the name + description appear. Ready ✅

Scripts run in Anthropic's code-execution environment (sandbox) — not on your machine.