More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Analytics Setup and Tracking Plan

    1

    Build a tracking plan that starts from your decisions: events, naming, conversions, UTM rules, and a validation checklist.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Analytics Setup and Tracking Plan

    Analytics Setup and Tracking Plan

    Example session with this skill installed

    We sell a meal-prep subscription box direct to consumers. The site is on Shopify, GA4 only records pageviews, and we run Meta ads plus a weekly email. About 900 people a month create an account, but we cannot tell which channel produces subscribers who stay past the first box, and checkout abandonment is a guess. Give us a tracking plan.

    • Read your context and instructions
    • Compiled the analytics setup

    Decisions first, per the protocol. Two decisions drive this plan: (1) shift budget between Meta ads and email based on who becomes a subscriber, not who clicks; (2) find the checkout step losing subscribers. Every event below serves one of them.

    Core events (object-action naming, context in properties):

    • account_created (method, source) on account creation. Conversion, once per session.
    • plan_selected (plan_type: weekly/flex, meals_count) when a plan is picked. Not a conversion.
    • checkout_started (plan_type, value) when checkout opens. Not a conversion.
    • purchase_completed (plan_type, value, currency, is_first_order) on payment confirmation, sent server-side so a closed thank-you page cannot lose it. Conversion, once per event.
    • box_skipped and subscription_cancelled (reason_code) in the account area. These two answer the retention half of decision 1.

    UTM rules applied: Meta gets utm_source=meta, utm_medium=paid_social, utm_campaign per campaign theme; email gets utm_source=newsletter, utm_medium=email, utm_campaign per issue. All lowercase, logged in one shared sheet, and never placed on internal site links.

    Validation before reporting: fire each event in GA4 DebugView on desktop and mobile, confirm purchase_completed fires once per order against 10 test orders in Shopify, and confirm no email address appears in any property. Until that passes, the plan stays marked draft and no channel budget moves on its data.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Most analytics setups collect a lot and answer little. This skill reverses that: it starts with the 3 to 5 decisions your data has to inform, then defines the smallest event set that supports them, with one naming pattern, clear property rules, and a counting rule for every conversion.

    It covers GA4 and Google Tag Manager implementation patterns, product analytics tools such as Mixpanel and PostHog, UTM rules with a shared log, and the privacy defaults that keep personal data out of your properties. Every plan ends with a validation checklist and a tracking health score, so you know whether the numbers can be trusted before a dashboard gets built on them.

    You get a tracking plan document you can hand to a developer, an audit path for setups that already exist but do not match your order or CRM records, and honest notes on what analytics cannot see, including consent losses and ad blockers.

    This skill produces the plan, the naming and UTM rules, and the validation checks; it does not log into your analytics account, install tags, or change a live container. It also cannot recover history: events defined today only collect data from today, and consent refusals and ad blockers mean analytics will always undercount real orders by some margin. Attribution choices and A/B test analysis are separate work and are not covered.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 25 days ago

    Permissions

    No special permissions declared or detected

    Listed25 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    Build a tracking plan that starts from your decisions: events, naming, conversions, UTM rules, and a validation checklist.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use Analytics Setup and Tracking Plan on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Marketing & SEO