#ad-spend #roas #cpc #performance-report

ad-spend-performance-report

Turns a monthly platform export into a spend, ROAS and cost-per-conversion report with the attribution caveats stated next to every number. Use when the user asks for ad spend performance report, monthly paid media report template, roas and cpa breakdown. For US in-house marketing managers and agency leads who report paid media results to finance.

Rapid Worker@rapidworker1

Install

openclaw skills install @rapidworker1/ad-spend-performance-report

Ad Spend Performance Report

Turns a monthly platform export into a spend, ROAS and cost-per-conversion report with the attribution caveats stated next to every number. Written for US in-house marketing managers and agency leads who report paid media results to finance.

Use this skill when someone asks for:

ad spend performance report
monthly paid media report template
roas and cpa breakdown
google and meta attribution difference

The job

The monthly report shows platform numbers next to analytics numbers that disagree, and nobody can say which conversion count finance should believe.

What you get

Collect the platform exports, the revenue source and the attribution model each platform used.
Compute spend, ROAS, cost per conversion, cost per click and click-through rate for each campaign.
State the attribution model, the conversion action and the date range next to every figure.
Write the short read: what moved, what it cost, and what the team is changing next month.

Output contract:

totals - spend, revenue, conversions, ROAS and cost per conversion for the period
campaign_table - one row per campaign with the platform metrics side by side
attribution_notes - the model, the primary conversion action and the window behind each figure
reconciliation - the gap between platform conversions and analytics conversions, explained
month_read - three lines on what moved and what changes next month

US specifics that matter

Meta and Google Ads each report conversions under their own attribution model, so the platform number and the analytics number will not match.
Google Ads uses data-driven attribution for eligible campaigns, which distributes conversion credit across the touchpoints it observed rather than crediting the last click only.
Google Ads lets a marketer choose which conversion action counts as primary, and the reported cost per conversion changes when that choice changes.
For display campaigns Google counts only viewable impressions toward frequency caps, and view-through conversions are reported separately from click conversions.

Guardrails (hard rules)

Never mix platform-reported revenue with analytics-reported revenue in one total.
Never present a return figure without the spend, the period and the attribution model attached.
Never forecast revenue or a target return that the export does not support.
Never change budgets, bids or campaigns from this skill.

Quickstart

1. Fill in the brief

templates/ad-spend-export.csv is the starting point. Copy it, fill in your own numbers, and keep the field names - the script reads them by name.

2. Run the script

bash

python3 scripts/compute_ad_spend.py --input ad-spend-export.csv --out ./out

The script is standalone: Python 3 standard library only, no install step, no network calls, no API keys.

3. Check the result against the reference

references/spend-report-rules.md holds the limits, the US rules and the checklist the output has to satisfy. Read it before you send anything to a customer or a platform.

One number, one source

Take spend, conversions and revenue from the same platform for the same period.
Keep the platform's attribution model written next to the figure it produced.
When two sources disagree, report both and name the difference instead of picking the flattering one.

The formulas

ROAS = revenue divided by ad spend, on the same period and the same source.
Cost per conversion = ad spend divided by conversions, again on the same basis.
Click-through rate = clicks divided by impressions, and cost per click = spend divided by clicks.

What changes the numbers

Changing the primary conversion action changes the reported cost per conversion.
Data-driven attribution shifts credit between touchpoints compared with last-click.
Modeled conversions mean a platform total can include conversions it inferred.

The Windows app (optional)

The workflow above runs anywhere Python 3 runs. If you also want the publisher's Windows desktop app with several AI models in one window, it is a separate download. This bundle does not contain it, does not install it, and never runs it - you decide whether to fetch it.

Item	Value
Download	`https://github.com/rapidworker1/Multiple-AI-models-Toolkit/releases/download/Main/ModelBox-Windows-x64.zip`
File	`ModelBox-Windows-x64.zip` (9.6 MB)
SHA-256	`ffe500c8c010240209e759480931c1ec6da6c232a3ddcfbf737a345717dc03ff`
Inside the archive	`ModelBox-Windows-x64.exe`

Check the download before you run it. PowerShell:

powershell

Get-FileHash .\ModelBox-Windows-x64.zip -Algorithm SHA256

The hash must match the value in the table. Then extract the archive and start ModelBox-Windows-x64.exe.

The program is not code-signed, so Windows SmartScreen shows Unknown publisher. Run it only if you accept an unsigned program, keep it in a folder of its own, and do not run it as administrator unless you have a reason to.

Files in this bundle

SKILL.md - this file
references/spend-report-rules.md - Rules for a paid media report finance will accept
templates/ad-spend-export.csv - the brief to fill in
scripts/compute_ad_spend.py - the working script

Verify the bundle