Attribution Audit
Reconciles conversion data across GA4, MMPs, AdAttributionKit and every ad platform, and refuses to add incompatible reporting windows together just to produce one clean number.
Overview
Attribution Audit is a cross-platform worker skill in the Claude Ads suite. It reconciles measurement across every browser, server, platform, analytics, MMP, offline and app attribution source instead of trusting any single platform as ground truth.
What it covers
- Inventories every attribution source with its identity, counting, deduplication and privacy rules.
- Enforces a "comparability gate": incompatible conversion windows/definitions (e.g. Meta 7-day vs. Google 30-day) are reported side by side, never summed, until reconciled.
- Explains discrepancies caused by eligibility, view-through rules, consent, modeled data or conversion lag.
- Separates measurement quality from platform-reported performance.
- Never recommends an attribution model without the operator's decision context.
Part of Claude Ads
This skill is dispatched automatically by the main ads conductor whenever attribution
or cross-platform conversion questions come up. See the full
Claude Ads entry for installation.
Installation
This worker skill installs automatically as part of the Claude Ads plugin, there's no separate step for it.
- Install the plugin once, from inside Claude Code:
/plugin marketplace add AgriciDaniel/claude-ads /plugin install claude-ads@ai-marketing-hub-claude-ads - This skill runs on its own whenever the
/adsconductor needs it; you don't call it directly. - See the Claude Ads entry for the full setup and platform list.
Related assets
Frontend Design
Generates distinctive, production-grade UI that avoids generic "AI slop," with bold typography, cohesive color, and precise motion, implemented as real code.
Graphify
Turns a codebase, plus its docs, PDFs, images, and video, into a queryable knowledge graph that a coding agent can traverse instead of grepping raw files, and never guesses silently: every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS so you know what was found versus inferred.
Caveman
Makes your coding agent answer in a stripped down, high signal style that keeps every technical fact and cuts filler, saving output tokens on chat style questions.