← Back to list
🛠️
attribution-reconciler ✓ Security reviewed
Use when platform-reported conversions disagree with GA4/ecommerce, when you suspect Meta and Goo…
🛠️ Developer Tools By aaron-he-zhu Version v1.0.0 Updated 2026-09-03
6.3Overall rating

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "attribution-reconciler" skill by following the instructions at https://skill123.me/install/attribution-reconciler.
⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/attribution-reconciler.sh | bash
📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 4 KB

About this skill

Overview

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-social-attributor. 付费广告归因对账/去重/增量

Source

  • Repo: https://github.com/aaron-he-zhu/aaron-marketing-skills
  • Path: ad/scale/attribution-reconciler

Evaluation

AI-evaluated 2026-09-03: Order-ID truth-set rule enforced up front, window/currency normalization before matching, matched/double-counted/unmatched kept as separate columns, and incrementality marked N/A without a holdout. Requires multiple platform exports plus an order-ID export and lives inside a larger skill chain; untrusted-export handling and never reconciling against platform-reported counts are strong safety.

Score breakdown

Quality
7.0
Usability
4.0
Security
8.0
Popularity
7.0