Agent skill · Testing & QA

attribution-reconciler

Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution models, and reads incrementality from a geo/holdout test. Not for the point-in-time R2 veto or RQS gate — use ad-account-auditor; not for the ROI/ROAS ratio math itself — use roi-calculator; not for organic dark-social share attribution or GA4 direct-traffic decomposition — use dark-so

aaron-he-zhugithub.com/aaron-he-zhuGitHub ↗
claude-codeApache-2.0
Install
npx skills add aaron-he-zhu/aaron-marketing-skills --skill attribution-reconciler --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 11 KB
Bundled scripts: none
Version: 19.1.0
Requires: Claude Code and compatible agent-skill hosts
Path: ad/scale/attribution-reconciler/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 2,508
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Attribution Reconciler > Based on the ROAS dimension **R** (attribution integrity) in the [ROAS Benchmark](../../../references/roas-benchmark.md). This is the **standing de-dup / incrementality workbook**: it reconciles platform-reported conversions against the GA4/ecommerce order-ID truth set on a recurring cadence. It delegates **all** ratio/ROAS math to [roi-calculator](../../../influencer/report/roi-calculator/SKILL.md) and does **not** re-run the R2 veto — [ad-account-auditor](../../activate/ad-account-auditor/SKILL.md) judges R2 once, point-in-time. This workbook just keeps the truth set clean between audits. Upstream, [conversion-signal-qa](../../activate/conversion-signal-qa/SKILL.md) is the **pre-launch** instrumentation pass that makes the signal trustworthy and only *gates* that a dedup rule exists; this skill is the recurring reconciliation that runs **on** that signal — match, de-dup, quantify, read incrementality. The single rule: the truth set is the **order IDs** from GA4/ecommerce, **never** any platform's reported-conversion count. This workbook reconciles **paid** channels only — decomposing GA4 direct traffic and estimating organic dark-social share attributio

What's inside
Steps it walks through
  1. Quick Start
  2. Skill Contract
  3. Handoff Summary
  4. Data Sources
  5. Instructions
  6. Save Results
  7. Reference Materials
  8. Next Best Skill
More from aaron-marketing-skills
All skills →
About this skill
What does the attribution-reconciler skill do?

Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Google are double-counting the same sales, or for a standing (monthly) reconciliation workbook that de-dups stacked credit against an order-ID truth set, normalizes attribution windows and currency, compares attribution models, and reads incrementality from a geo/holdout test. Not for the point-in-time R2 veto or RQS gate — use ad-account-auditor; not for the ROI/ROAS ratio math itself — use roi-calculator; not for organic dark-social share attribution or GA4 direct-traffic decomposition — use dark-so

How do I install it?

Run `npx skills add aaron-he-zhu/aaron-marketing-skills --skill attribution-reconciler --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From aaron-he-zhu/aaron-marketing-skills, a repository with 2,508 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going