Ads Attribution

This audits your ads attribution setup by inventorying every conversion source (GA4, Meta, Google, MMPs like AppsFlyer or Adjust, offline events) and reconciling what's actually comparable. It enforces a strict gate: won't let you add Meta seven-day conversions to Google thirty-day conversions or aggregate anything until attribution windows, conversion definitions, timezones, and counting methods align. Useful when cross-platform reports don't match, when you're evaluating an MMP, or before making budget decisions on frankly incompatible data. The core insight is treating measurement quality as separate from platform-reported performance, which is the right call when every platform has different eligibility rules and privacy models.

skills.sh installs: 3.6K
GitHub stars: 10.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agricidaniel/claude-ads --skill ads-attribution --agent claude-code

Installs into .claude/skills of the current project.

Files

Attribution Audit

Read the main ads contract and normalized account snapshots.
Declare the business conversion, value, data window, timezone, currency, and decision the attribution analysis must support.
Inventory every browser, server, platform, analytics, MMP, offline, and app attribution source with its identity, counting, deduplication, and privacy rules.
Reconcile comparable events and explain differences caused by eligibility, view-through rules, consent, modeled data, conversion lag, thresholds, or scope.
Separate measurement quality from platform-reported performance.
Return findings, contradictions, confidence, missing evidence, and a measurement improvement plan through the common JSON contract.

Do not assume one platform is ground truth, add incompatible reports together, or recommend an attribution model without the operator's decision context.