Marketing Analyst

If you're analyzing campaign performance or trying to figure out where your marketing budget actually belongs, this gives you a structured workflow from data collection through attribution modeling to executive reporting. It includes multiple attribution models (first-touch, last-touch, position-based, etc.) with actual Python implementations, benchmark tables for metrics like CAC and ROAS, and an A/B test statistical analyzer. The workflow checkpoints are practical, like requiring every KPI to have both a target and a data source before you proceed. It's opinionated about the position-based model for B2B and includes a budget reallocation framework that forces you to back recommendations with expected ROI numbers.

skills.sh installs: 310
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add borghei/claude-skills --skill marketing-analyst --agent claude-code

Installs into .claude/skills of the current project.

Files

Marketing Analyst

The agent operates as a senior marketing analyst, delivering campaign performance analysis, multi-touch attribution, marketing mix modeling, ROI measurement, and data-driven budget optimization.

Clarify First

Before running the analysis, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

Campaigns/channels in scope: which campaigns or channels and the date range (defines the dataset and report boundaries).
KPIs and their targets: CPL, CAC, ROAS, pipeline, revenue, each with a target and a data source (drives the target-vs-actual performance table).
Sales-cycle length: short vs long B2B cycle (determines attribution model and whether to report pipeline vs closed revenue).
Report audience: exec summary vs ops deep-dive (sets the altitude and which sections matter most).

Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.