Does this skill require external API connections?

No, the Campaign Analytics tools use the Python standard library only, ensuring deterministic and secure data processing without external dependencies or third-party API calls.

What attribution models are supported?

It supports five industry-standard models: First-Touch, Last-Touch, Linear, Time-Decay (with configurable half-life), and Position-Based (40/20/40).

What metrics does the ROI calculator provide?

It calculates ROI, ROAS, CPA, CPL, CAC, CTR, and CVR, and can flag underperforming campaigns by comparing them against included industry benchmarks.

Can I integrate this into an existing data pipeline?

Yes, all scripts support a --format json flag, making it easy to pipe results into other tools, databases, or visualization dashboards.

Campaign Analytics

Name: Campaign Analytics
Author: alirezarezvani

byalirezarezvani

•

9,958

•

Automatización de Marketing

Analyzes marketing campaign performance using multi-touch attribution, conversion funnel tracking, and comprehensive ROI metrics.

The Campaign Analytics skill provides a suite of production-ready Python tools for marketing performance evaluation without external dependencies or API overhead. It enables developers and marketers to implement deterministic attribution modeling—including first-touch, last-touch, and time-decay models—while identifying conversion bottlenecks through automated funnel analysis. By calculating essential metrics like ROAS, CPA, and CAC from standard JSON inputs, this skill facilitates data-driven budget reallocation and campaign optimization directly within the Claude Code environment.

Características Principales

01Deterministic Python-based processing with zero external dependencies or API calls

02Multi-touch attribution modeling including First-touch, Last-touch, Linear, and Time-decay

039,958 GitHub stars

04Automated funnel analysis for bottleneck identification and stage-to-stage conversion tracking

05Comprehensive ROI, ROAS, and CAC calculations with industry benchmarking

06Flexible output formats supporting both human-readable tables and machine-readable JSON

Casos de Uso

01Auditing marketing spend and profitability across multiple ad platforms and campaigns

02Identifying stage-to-stage drop-off points in e-commerce or lead generation funnels

03Calculating channel-specific credit for complex multi-touch customer journeys

Características Principales

01Deterministic Python-based processing with zero external dependencies or API calls

02Multi-touch attribution modeling including First-touch, Last-touch, Linear, and Time-decay

039,958 GitHub stars

04Automated funnel analysis for bottleneck identification and stage-to-stage conversion tracking

05Comprehensive ROI, ROAS, and CAC calculations with industry benchmarking

06Flexible output formats supporting both human-readable tables and machine-readable JSON

Casos de Uso

01Auditing marketing spend and profitability across multiple ad platforms and campaigns

02Identifying stage-to-stage drop-off points in e-commerce or lead generation funnels

03Calculating channel-specific credit for complex multi-touch customer journeys