Client reporting for Google Ads
Give your AI tool the campaign report for the period. It writes the client report as a Word document under your agency’s name, traces every number in it to the data, and fact checks any draft you already have.
npx skills add parallel-ai-inc/google-ads-skills -gInstalls all 13 skills in Claude Code, Codex, Cursor and other tools. Steps for each tool
Northside Plumbing: Google Ads, October 2026
Monthly business review, prepared by Harbor Search Partners on November 13, 2026.
Reporting period: October 1, 2026 to October 31, 2026. Compared with September 1, 2026 to September 30, 2026 and with October 1, 2025 to October 31, 2025.
Month‑over‑month snapshot
October brought 413.49 conversions at a cost of 14,423.32, against 407.22 conversions in September. Conversions rose 1.5% while cost fell 3.8%.
Without Brand, cost per conversion was 50.24, which is 25.6% above the 40.00 target. Brand searches convert cheaply by nature, so the whole account’s figure of 34.88 looks better than the rest of the account performs.
- Against October last year, conversions rose 17.5%.
- Spend came in 9.9% below the spend target of 16,000.00, mostly because Drain Cleaning | Search was paused.
What to give it
The campaign report by day. In Google Ads, open Campaigns, then Segment, Time and Day, with Campaign, Campaign status, Campaign type, Impr., Clicks, Cost, Conversions and Conv. value. Cover the period and the one before it, and start a year earlier to compare with last year.
The change history for the period is worth adding. With it, the report lists what was changed and who changed it, the team or Google’s systems.
The skill also asks for the report type and period, the client’s and agency’s names as they should appear, the targets, the brand campaigns, what a conversion is for this client, and any work done outside Google Ads.
What you get back
client-report.docxThe report in Word, under your agency’s name, with every number traced to the data.client-report-tables.xlsxThe tables behind it, for your own charts.fact-check.md and fact-check.xlsxWhen you give it a draft, every number in it checked against the data, with a verdict.
Before the report is written, a fact check traces each number in its text to the data, and the report is written only when every one passes.
A draft is fact checked against the data
Give it a report someone already wrote, and it matches every number to the data, reading the words around it too: the measure, the campaign, the comparison and whether it rose or fell.
Fact check: draft‑report‑to‑check.md
Checked against the numbers for 2026‑10‑01 to 2026‑10‑31, compared with 2026‑09‑01 to 2026‑09‑30 and the same period last year.
- 9 numbers found, dates not counted.
- Verified: 4.
- Contradicted by the data: 3.
- Unclear or overclaimed: 1.
- Needs data: 1.
- Dates, counted apart: 4 found, 4 match the period and the data.
Contradicted by the data
- Contradicted by the data: wrong direction: “5.2%” in: Cost per conversion rose 5.2% to 34.88, under the 40.00 target. Account: Cost / conv., change vs previous period is −5.2%, so it went down, but the sentence says it went up. (Line 4)
- Contradicted by the data: “18%” in: Drain Cleaning | Search declined sharply, with cost down 18% on September. The data says Drain Cleaning | Search: Cost, change vs previous period is −37.8%. (Line 7)
- Contradicted by the data: “9.4x” in: Return on ad spend reached 9.4x for the month. The data says Account: Conv. value / cost, current period is 9.09. (Line 8)
How it decides
Scripts compute every number, and the report states no figure they did not print. Each rule it applies is labelled Official, from Google’s documentation, or Practitioner rule, from Parallel AI’s operating knowledge.
- When brand is an outlier, the figures without brand come first, because brand searches convert cheaply by nature and flatter the blended figure.Practitioner rule
- A campaign paused during the period is reported as paused, with the cost that removed, never as a decline.Practitioner rule
- When the periods differ in length, every total sits beside its per day figure, because a total can fall only because the month is shorter.Practitioner rule
- Conversions follow the account’s attribution settings, and Google Ads conversions are not the client’s sales or CRM leads.OfficialGoogle Ads Help, About attribution models
What it does not cover
- Conversions reported late. The last days of a period can still rise.
- The client’s sales or CRM leads, unless you give it that number to carry.
- Reasoning. The fact check traces numbers, and a cause or recommendation stays your judgment.
- Every change in the account. The change history can miss some account level and Google representative changes.
- More than one client at a time. Each client is its own run.
When you want it on live accounts
The skill writes one client’s report from one export. Parallel AI drafts client reports from your live Google Ads accounts, across every client, as documents you can edit.
The page for this job in Parallel AI is Spend 15 minutes reviewing a client report, not 90 minutes building it.
The guides behind this job are The Google Ads client report template and Why do Google Ads reports take so long?.
Install
In Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, OpenCode and other tools that read Agent Skills, the open skills CLI installs every skill in the pack.
npx skills add parallel-ai-inc/google-ads-skills -gIn Claude Code, add the pack as a plugin from a session.
/plugin marketplace add parallel-ai-inc/google-ads-skills/plugin install parallel-ai-for-google-ads@parallel-ai
To install this skill alone, name it.
npx skills add parallel-ai-inc/google-ads-skills --skill client-reporting-for-google-ads -gAdd -a with a tool’s id, such as codex or cursor, to install for that tool alone. Without -g, the skills install into the current project.
Questions and answers
Does the skill cost anything?
No. The skills are free to use for any Google Ads work, for yourself or for clients. They may not be republished as your own skills. Parallel AI is a separate product, with a 5‑day free trial.
Does Parallel AI’s name appear in the report?
No. The report carries your agency’s name. The files the skill writes are your own work, and no vendor name goes in them.
Where does my data go?
The skill’s scripts make no network calls, and nothing goes to Parallel AI. Your AI tool sees the files you give it, as it would any file, under that tool’s own terms. If the export is a client’s, check your agreement with that client before you give it to an AI tool.
Does it change my Google Ads account?
No. It never connects to an account on anyone’s behalf and never changes one. It reads the reports you give it and writes files. Where a job ends in a change, it writes a Google Ads Editor file, and you check it there before posting.
Which AI tools can run it?
Tools that read Agent Skills and can run Python, such as Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and OpenCode. The scripts use Python 3’s standard library only.
Is Northside Plumbing a real business?
No. Northside Plumbing is the pack’s made up sample account, with problems planted for each skill to find. Run the skill on the sample files and you get the same figures as this page.
Google Ads is a trademark of Google LLC. Parallel AI is not affiliated with or endorsed by Google.
Report on every client in one request
Parallel AI drafts each client’s report from your live Google Ads accounts, with every number from the account, as Docs you can edit before they go out.
Starter $20, Pro $60 and Max $200 a month
You connect Google Ads first, then add a card to start the trial.