ad-attribution-gap — Analytics, an agent skill published by mbfinotti/advertising-skills
Analyticsmbfinotti/advertising-skillsskills.sh ↗
Installs
26,680
deduplicated, at the last sync
Since we started
+482%
25 readings, about 2 days apart. Not a live curve.
Our category
Analytics
ours
Last read
Nov 22, 2026
from the directory
Our brief
oursThis skill quantifies and explains discrepancies between ad platform reporting, analytics tools, and the source-of-truth system (CRM or order system). It normalizes all sources to a common basis, computes the gap for each pair, and classifies every unit of variance as timing, definitional, or unexplained residual. It covers both B2B (CRM-anchored) and B2C/ecommerce (order-system-anchored) funnels and produces a reconciliation report with a variance table, cause attribution, and a judgment test for whether the gap is normal or a defect.
- reconciliation report
- variance table with buckets
- gap classification by cause
- MER cross-check figure
- defect vs normal judgment
- ad platform exported reports
- analytics tool exported reports
- CRM or order system data
- date range and grain
- attribution window settings
not detected
The skill description and examples show no requirement for paid APIs, subscriptions, or external services; it works from user-provided exports.
not detected
No account creation, login, or credential exchange is mentioned in the skill documentation.
The skill does not fix broken or missing tracking (tags, pixels, deduplication) — it hands off those findings to a separate skill. It does not choose attribution models; it treats model differences as causes to measure. It does not diagnose ad account performance, landing pages, or CAC/ROAS benchmarks.
Evidencestatic findingsskills/ad-attribution-gap/references/reconciliation-examples.md:1-33skills/ad-attribution-gap/SKILL.md:1-109
[{"code":"payment","match":"billing","path":"SKILL.md"}]# Worked reconciliation examples Two complete examples of the deliverable shape defined in SKILL.md. All figures are illustrative - realistic in shape and direction, not benchmarks. Do not reuse these numbers as expectations for a real account. Derive every amount from the account's own data. ## Example 1 - B2C/ecommerce, one month ### 1. Headline Anchor: order system, net revenue basis. Anchor count: **1,240 paid orders, $96,400 net revenue**. Verdicts: - Platform A vs orders: structural and explained. - Analytics vs orders: structural and explained. - Platform A + Platform B jointly claim 1,590 conversions against 1,240 orders: overlapping claims, not extra orders. Do not sum. ### 2. Normalization basis - Grain: calendar month, single reporting timezone (the order system's). - Date basis: order-event date. Platform A raw numbers (interaction-dated) re-pulled with a window wide enough to cover all interaction dates feeding this month's orders. - Conversion definition: paid order (pending and cancelled excluded), dated definition v2 (in force since the 1st of the prior month). - Counting rule: Platform A set to "every", order system counts orders - difference carried as a
--- name: ad-attribution-gap description: "Quantify and explain the discrepancy between ad platform reporting, an analytics tool, and the source of truth (CRM or order system), classifying every unit of the gap as timing, definitional, or unexplained residual. Use whenever the user says the numbers don't match, that the platform reports more conversions or revenue than the CRM or order system, or mentions cross-platform reconciliation, double-counted conversions, an attribution discrepancy, or asks whether a reporting gap is normal - even if they never say 'attribution'. Covers B2B (CRM-anchored) and B2C/ecommerce (order-system-anchored). Do NOT use to fix broken or missing tracking - use mbfinotti/advertising-skills@ad-conversion-tracking instead." license: MIT metadata: author: Maya-Beth Finotti version: "1.1.11" --- # Attribution Gap Reconciliation You are a marketing measurement analyst. Deliver a reconciliation report: a number on the gap between what each reporting system claims, with every unit of that number attributed to a named cause. The gap between an ad platform, an analytics tool, and the system that records the money is structural and expected - a report where
Read 3 of 3 text files in the skill.
Installfrom the directory
npx skills add https://github.com/mbfinotti/advertising-skillsInstalling happens there, not here. We are an index with an opinion, not a mirror.
What is inside itfrom the directory
3 files — names only. The directory does not report sizes.
What the auditors foundfrom the directory
A skill is instructions your agent will follow and scripts it may run, so who checked it matters as much as how many people installed it.
Installs, reading by readingours
Axis starts at 4.6k, not zero — the range is 4.6k to 26.7k.
Asked out loudspoken, not typed
The same skill in the words people use speaking to an assistant rather than typing into a box. Each one carries the situation it came from, and each answer says only what the skill's own files support.
No. The skill works from the CSV, spreadsheet, or warehouse exports you already have from your ad platforms, analytics tool, and CRM or order system. No paid APIs or subscriptions are mentioned.
No. The skill explicitly says fixing or installing tracking is out of scope. If the analysis finds a tag misfiring or deduplication broken, it quantifies that share of the gap and hands off to a separate tracking skill.
Yes. The skill covers both: B2B anchors on the CRM, B2C/ecommerce anchors on the order system. Blended businesses run two separate reconciliations, one per funnel.