agentleFS
kastriasanikastriasani/google-ads-skills/skills/google-ads-reporting/SKILL.md

google-ads-reporting

Skill1 starsChanged 5 months agoMITView on GitHub

Produce client performance reports and QBRs from Google Ads data. Use whenever someone needs a weekly, monthly, or quarterly Google Ads report, a client recap, a QBR or quarterly business review deck content, a KPI dashboard, a campaign ROI or ROAS breakdown, an attribution comparison across channels, or a period-over-period summary with prioritized recommendations. Trigger phrases include build a report, monthly report, QBR, client report, performance recap, how did the account do, ROAS by campaign, attribution model comparison, budget reallocation, winners and losers, and turn this campaign data into a report.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Compute campaign and portfolio ROI: Run python3 scripts/campaign_roi_calculator.py --demo to see the format, then feed real data.

    line 34
  2. Very specific:

    Run attribution if there are multi-touch journeys: Run python3 scripts/attribution_analyzer.py --demo then your journey data.

    line 41
  3. Very specific:

    Find the funnel bottleneck: Run python3 scripts/funnel_analyzer.py --demo then real impression-to- conversion counts (optionally by …

    line 47
  4. Very specific:

    Assemble the report: Run python3 scripts/report_builder.py --demo to see the output, then feed the real campaign data (this period plus a …

    line 52
  5. Distinctive:

    Search Impression Share, CvR, ROAS, CPA, CPC, Quality Score, and how to read them together.

    line 96

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Google Ads Reporting

Turn raw Google Ads numbers into a report a client can act on. This skill computes the metrics, ranks winners and losers, compares period-over-period, runs attribution across channels, and assembles the whole thing into a structured report with a prioritized recommendation list. The goal is a recap that drives a decision, not a screenshot of the platform.

When to use

Reach for this skill when someone asks for a Google Ads report at any cadence (weekly, monthly, quarterly/QBR), a client performance recap, a KPI dashboard, a campaign ROI/ROAS breakdown, a budget-reallocation recommendation, an attribution comparison, or a period-over-period summary. If the request is to diagnose account health and produce a fix list, use google-ads-audit; if the request is to render the report as a slide deck, hand the output to google-ads-presentation.

Workflow

  1. Set the scope. Confirm report type (campaign, channel, account, QBR), the period, the comparison period, and the audience. Pull targets (ROAS, CPA, conversions, spend) so the dashboard can show status, not just numbers.
  2. Compute campaign and portfolio ROI. Run python3 scripts/campaign_roi_calculator.py --demo to see the format, then feed real data. It returns per-campaign ROI, ROAS, CPA, CPL, CTR, CVR plus a portfolio summary, benchmark flags, and budget-reallocation recommendations (scale winners, cut losers). See references/metrics-glossary.md for every metric definition.
  3. Run attribution if there are multi-touch journeys. Run python3 scripts/attribution_analyzer.py --demo then your journey data. It runs all five models (first-touch, last-touch, linear, time-decay, position-based) so you can show how much credit Google Ads earns under each lens and stop a last-click default from undervaluing upper-funnel search.
  4. Find the funnel bottleneck. Run python3 scripts/funnel_analyzer.py --demo then real impression-to- conversion counts (optionally by segment: device, network, campaign type). It pinpoints the biggest absolute and relative drop-off.
  5. Assemble the report. Run python3 scripts/report_builder.py --demo to see the output, then feed the real campaign data (this period plus a "prior" block per campaign). It emits Markdown (and --json) with the KPI dashboard (This / Prior / Change / Target / Status), winners and losers, and a 2x2 impact/effort recommendation list. Use references/report-templates.md to pick the cadence template and references/qbr-structure.md for the 4-act QBR narrative.
  6. Frame the narrative. For a QBR, structure it as the 4 acts: where we said we'd be, where we are, why the gap, what next. Lead with the headline metric, never bury a miss, and make every recommendation specific and dated.

Inputs and data sources

The skill runs standalone on pasted numbers or a CSV/JSON you assemble: per campaign give spend, impressions, clicks, conversions, conversion value, and a prior-period block. No live connection is required.

Optional sources that enrich the report:

  • Google Ads API / UI for campaign metrics, Search Impression Share, and Quality Score.
  • GA4 for funnel steps, engagement, and assisted conversions.
  • Google Sheets / BigQuery as the data warehouse you export from.
  • Search Console for the organic context that frames paid performance.

Outputs

  • A per-campaign and portfolio ROI/ROAS/CPA table with benchmark flags and budget-reallocation moves.
  • A cross-model attribution comparison showing Google Ads' credit under each lens.
  • A funnel bottleneck analysis (absolute and relative drop-off).
  • A complete report in Markdown and JSON: KPI dashboard with status, winners and losers, period-over-period deltas, and a 2x2 prioritized recommendation list, ready to hand to google-ads-presentation.

References

  • references/report-templates.md - the eight-section structure and the weekly / monthly / QBR cadence templates plus dashboard design principles.
  • references/qbr-structure.md - the 4-act QBR narrative, the Headline-Data-Narrative-Ask per-section formula, the QBR slide order, and how to deliver bad news.
  • references/metrics-glossary.md - Google Ads metric definitions including Search Impression Share, CvR, ROAS, CPA, CPC, Quality Score, and how to read them together.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.