---
name: Attribution Audit
slug: attribution-audit
category: Data
description: Attribution Audit audits cross-platform attribution, conversion definitions, reporting windows, GA4, AdServices and AdAttributionKit, MMPs, browser and server events, offline conversions, and platform reconciliation. Use it for attribution audits, comparing conversion windows, reconciling Meta and Google conversions, reviewing MMPs like AppsFlyer, Adjust, Branch, Singular, or diagnosing
github: "https://github.com/AgriciDaniel/claude-ads/tree/main/skills/ads-attribution"
language: Python
stars: 8064
forks: 1200
install: "npx degit https://github.com/AgriciDaniel/claude-ads/tree/main/skills/ads-attribution ~/.claude/skills/ads-attribution"
installs_to: ~/.claude/skills/ads-attribution
source_path: skills/ads-attribution/SKILL.md
collection_size: 25
category_size: 668
collection_url: "https://dirskills.com/collections/AgriciDaniel/claude-ads"
added: 2026-08-15T06:51:05.899Z
last_synced: 2026-08-15T06:51:05.899Z
canonical_url: "https://dirskills.com/skills/attribution-audit"
---

# Attribution Audit

Attribution Audit audits cross-platform attribution, conversion definitions, reporting windows, GA4, AdServices and AdAttributionKit, MMPs, browser and server events, offline conversions, and platform reconciliation. Use it for attribution audits, comparing conversion windows, reconciling Meta and Google conversions, reviewing MMPs like AppsFlyer, Adjust, Branch, Singular, or diagnosing

**Install:**

```bash
npx degit https://github.com/AgriciDaniel/claude-ads/tree/main/skills/ads-attribution ~/.claude/skills/ads-attribution
```

## README

# Attribution Audit

1. Read the main `ads` contract and normalized account snapshots.
2. Declare the business conversion, value, data window, timezone, currency, and
   decision the attribution analysis must support.
3. Inventory every browser, server, platform, analytics, MMP, offline, and app
   attribution source with its identity, counting, deduplication, and privacy rules.
4. Reconcile comparable events and explain differences caused by eligibility,
   view-through rules, consent, modeled data, conversion lag, thresholds, or scope.
5. Separate measurement quality from platform-reported performance.
6. 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.

## Comparability gate

Reject aggregation until the sources share, or are explicitly normalized to, the
same conversion event and value definition, attribution window, click/view scope,
counting method, deduplication identity, timezone, currency, attribution model,
and modeled-data treatment. Until then, report the values side by side with their
definitions; do not compute a total.

Example: Meta seven-day conversions and Google thirty-day conversions are
incompatible. Refuse to add them, reconcile windows and definitions first, and
only aggregate a newly comparable dataset.