campaign-analytics

Distribute conversion credit across marketing touchpoints using five attribution models.

Updated Mar 21, 2026
One-click install
npx skills add https://github.com/AgLyx3/My-Note-App-Not-Just-a-Note-App --skill campaign-analytics-aglyx3
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: campaign-analytics
Source: https://github.com/AgLyx3/My-Note-App-Not-Just-a-Note-App/tree/main/.cursor/skills/marketing-skill/campaign-analytics
Command: npx skills add https://github.com/AgLyx3/My-Note-App-Not-Just-a-Note-App --skill campaign-analytics-aglyx3

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Analyzes marketing campaign performance by distributing revenue credit across multiple channels through multi-touch attribution, revealing true channel value and ROI.

Core Features & Use Cases

  • Multi-Touch Attribution: five models (first-touch, last-touch, linear, time-decay, position-based) with per-model credits.
  • Funnel & ROI Insights: analyses funnel progression and computes ROI/ROAS, with A/B test templates and cross-channel comparisons.
  • Reproducible CLI Tools: deterministic Python CLI tools that operate on JSON data, no external API calls, suitable for offline analysis.
  • Use Case: Run analytics on a dataset of journeys to identify which channels drive conversions across the full funnel, and generate executive-ready reports.

Quick Start

Use the skill by running the attribution analyzer on a data file to produce multi-model results.

Frequently Asked Questions about campaign-analytics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I calculate multi-touch attribution to compare channel value across my marketing campaigns?▼

Multi-touch attribution distributes conversion credit across marketing touchpoints to reveal true channel value. You apply five attribution models—first-touch, last-touch, linear, time-decay, and position-based—to journey datasets and compare per-channel credits side by side.

What's the difference between first-touch, last-touch, linear, time-decay, and position-based attribution models?▼

First-touch credits the initial interaction; last-touch credits the final one; linear spreads credit evenly; time-decay weights later touchpoints more heavily; position-based splits credit between first, middle, and last interactions. The analyzer outputs a cross-model comparison to highlight these differences.

How do I run campaign attribution analysis on my customer journey data without external API calls?▼

You run deterministic Python CLI tools on JSON data files containing journeys, touchpoints, conversions, and revenue. The tools operate fully offline with no external API calls, producing per-channel credits, model summaries, and cross-model comparison outputs.

Can I use this multi-touch attribution tool to compute ROI and funnel progression for multiple marketing channels?▼

Yes, multi-touch attribution analyzes funnel progression and computes ROI and ROAS across channels. It applies five attribution models to your journey data and generates per-channel credits alongside funnel insights and cross-channel comparisons.

What data format do I need for multi-touch attribution analysis of campaign performance?▼

Multi-touch attribution requires JSON datasets containing marketing journeys with touchpoints, conversions, and revenue. The deterministic CLI tools read these JSON files directly and output per-model credits, model summaries, and cross-model comparison reports.

Why does last-touch attribution hide the true value of earlier marketing channels in my funnel?▼

Last-touch attribution assigns all conversion credit to the final interaction, ignoring upstream touchpoints. Multi-touch attribution solves this by distributing credit across the entire journey, revealing which earlier channels actually contribute to ROI and funnel progression.