The attribution skill reviews how conversions are defined and counted across ad platforms, GA4, mobile measurement partners, server events and offline data. It lists every source with its identity, counting and deduplication rules, then reconciles comparable events and explains the gaps.
A comparability gate blocks totals until sources share the same event, window, scope and model. Until then it reports the values side by side with their definitions.
What You Get
- An inventory of attribution sources with identity, counting and deduplication rules
- Reconciliation notes that explain differences from view-through rules, consent, modeled data and conversion lag
- Side-by-side reporting where totals are not valid
- A measurement improvement plan in the common JSON contract
Common Use Cases
- Explaining why Meta and Google report different conversion counts
- Reviewing GA4 attribution against platform numbers
- Checking an MMP setup with AppsFlyer, Adjust, Branch or Singular
- Responding to a request to total conversions across platforms
What Makes It Unique
It has a written comparability gate. Aggregation is rejected until sources share the conversion event, value definition, window, click and view scope, counting method, deduplication identity, timezone, currency, model and modeled-data treatment. Its worked example refuses to add Meta seven-day and Google thirty-day conversions.
Under The Hood
This is a prompt-only skill with no scripts. It tells the agent to read the main ads contract and the normalized account snapshots, then compare the exports, analytics data and API results you provide. It does not treat any one platform as ground truth and does not recommend an attribution model without your decision context. It sends findings to the conductor in JSON and makes no account changes.