Marketing Campaign KPI Auditor

What it does

The Marketing Campaign KPI Auditor is an AI workflow skill that ingests raw campaign exports from advertising platforms and returns a formatted performance report. Instead of merging CSVs and building pivot tables on Sunday night, you drop your data into the skill and get back a clean executive summary, platform-wise KPIs, gap analysis against targets, and a list of optimization actions sorted by potential impact.

Quick scan:

• Best for: Marketing Managers, Performance Marketers, Agency Leads
• Output: Markdown report with executive summary, gap analysis, trends, and optimization bullets
• Inputs: Campaign data CSV (impressions, clicks, cost, conversions, revenue optional) and optional targets
• Time saved: Replaces 45–90 minutes of weekly spreadsheet work
• Main caveat: Does not pull live data; you must export CSVs manually

When to use it (and when not to)

Use this skill when you regularly report on campaigns across multiple channels and need a consistent, automated analysis that you can review before sharing with stakeholders. It shines during weekly stand-ups, monthly reviews, and mid-campaign optimization checks.

Skip it if you’re only looking at one campaign or already have a tightly integrated BI dashboard. The skill is a data cruncher, not a data puller.

How to install and use

1. Download the skill ZIP from this page.
2. Unzip into your AI workflow skills folder.
3. Export your campaign data from each ad platform for the same date range. Combine into one CSV. Include columns: platform, campaign, date, impressions, clicks, cost, and optionally conversions, conversion value, ad group.
4. Add your target KPIs in a separate small table or embed them in the prompt.
5. Run Claude with the skill loaded and say: “Audit my campaign KPIs for this week.” Attach the CSV.
6. Review the generated report. Add context, adjust recommendations, and use it directly.

A concrete example

A mid-size ecommerce brand runs Google Search, Meta Advantage+, and LinkedIn Sponsored Content campaigns. The marketing manager exports each platform’s weekly performance (about 50 rows total), saves a CSV, and runs the auditor.

Input snippet:

platform,campaign,impressions,clicks,cost,conversions,revenue
Google,Shoes-Search,15,200,380,1,200,45,9,500
Meta,Retargeting,22,100,1,100,610,30,7,200
...

Targets: CPA ≤ $40, ROAS ≥ 3x.

Output excerpt:

## Campaign Performance Report — Week 15

Executive Summary

Total Spend: $2,340 | Conversions: 52 | Overall CPA: $45.00 | ROAS: 3.1x

Top performer – Retargeting (ROAS 6.2, CPA $23.00)

Gap Analysis alert – Shoes-Search (CPA $52, 30% over target)

Optimization Suggestion – Lower bids on broad match keywords in Shoes-Search, shift budget to Retargeting.

The manager pastes the report into the weekly deck, adds qualitative notes, and saves 40 minutes.

Limitations

• Data import only: The skill doesn’t connect to API endpoints; you must manually fetch exports. A future version could integrate with data connectors.
• Statistical noise: Campaigns with very low volume (e.g., <500 impressions) are flagged as unreliable and the report will caveat their metrics.
• Platform-specific nuances: The skill treats all conversions as equal; it doesn’t account for differences like Facebook’s view-through conversions unless you clean the data beforehand.
• Human override required: Automated optimization suggestions are rule-based. Strategic decisions (e.g., brand vs. performance balance) still need a human.

[Download the skill] → link handled by the platform

Related skills

Skills that pair well, or that you'd reach for instead:

Install

Start with the ZIP package, then choose the AI tool workflow that fits your setup.

1. Download marketing-campaign-kpi-auditor.zip (6.5 KB).
2. Open the package and read SKILL.md, plus any included references, templates, or scripts.
3. Use the instructions directly in any AI tool that supports reusable instructions, project knowledge, custom agents, or uploaded reference files.

For Claude Code, unzip into ~/.claude/skills/ so the folder lands at ~/.claude/skills/marketing-campaign-kpi-auditor/, then reload Claude Code. For Claude.ai, upload the same ZIP from Customize → Skills.

Use with other AI tools

This package is not locked to one vendor. If your AI tool does not support Claude-style skills, copy the core instructions from SKILL.md into the tool's custom instructions, project prompt, agent setup, or reusable prompt library.

• Upload or paste any included reference files as project knowledge where your tool supports it.
• Keep the output format from SKILL.md intact so results stay predictable.
• Run a small test with your own data before using the workflow in production.

Compatibility depends on the features your AI tool provides. Treat scripts as optional local helpers unless your environment can run them safely.

Claude installation reference

Review this skill