Every listing publishes its measured trigger accuracy, before and after.

See the catalogue
AI Skill Up
Browse skills

Analytics

Analytics Wiring

Sets up Tag Manager and consent so the numbers are actually trustworthy.

What it produces

is anything firing twice?
page_viewonce per route change
view_itemonce per product page
begin_checkoutfires twice on back-navigation
purchaseonce, after consent
consent_updatebefore any tag loads

Trigger accuracy

Not measured yet. This skill does not go on sale until its eval suite has been run against it and the number published here.

What we changed

  1. Installs the container and the consent gate together, because one without the other is a compliance problem.
  2. Defines events from what the business asks, not from the default recommended list.
  3. Verifies each event fires once per action, which is where most manual setups go wrong.
  4. Leaves a written map of event to meaning, so the dashboard is readable in six months.
  5. A troubleshooting table for the duplicate-fire and blocked-by-consent cases.

What it does, on real work

First-time setup

> set up Tag Manager on this site with a consent banner

Installed the container behind a consent gate, with nothing firing before a choice is made.

Defining events

> track the things that matter for a storefront

Wrote six events from the purchase path, each with the fields a report would need.

Verifying

> is anything firing twice?

Found one event double-firing on a route change and fixed the binding.

Requirements

  • Claude Code 2.0+
  • A Tag Manager container
  • macOS, Linux or Windows

Related

Writes React the way your team already agreed to write it.

Eval suite not run yet

Cuts what Claude reads before it starts, without cutting what it knows.

Eval suite not run yet