Campaign Analytics

Campaign Analytics analyzes marketing campaign performance using multi-touch attribution, funnel conversion analysis, and ROI calculation. It provides three Python CLI tools that generate deterministic, repeatable analytics from JSON input, with no external dependencies.

✨ What it does

  • Implements five attribution models: first-touch, last-touch, linear, time-decay, and position-based.
  • Identifies funnel bottlenecks with stage-to-stage conversion rates and drop-off percentages.
  • Calculates ROI, ROAS, CPA, CPL, CAC, CTR, and CVR with industry benchmarking.
  • Supports text and JSON output formats for human review or pipeline integration.
  • Validates input JSON and provides descriptive errors for missing keys or type mismatches.
  • Includes reference guides for attribution models, benchmarks, and funnel optimization.

🎯 When to use it

  • When you need to attribute conversions across multiple marketing channels.
  • When you want to identify funnel drop-off points and optimize conversion paths.
  • When you need to calculate ROI, ROAS, CPA, and other campaign metrics for budget decisions.
  • When you require a simple, offline, and dependency-free analysis of campaign data.

🚀 How to use

Trigger by running the Python scripts from the command line with a JSON file. The skill expects JSON data matching the schemas for journeys, funnel stages, or campaign metrics. Example prompts:

python scripts/attribution_analyzer.py campaign_data.json --model time-decay
python scripts/funnel_analyzer.py funnel_data.json
python scripts/campaign_roi_calculator.py campaign_data.json

📄 Output: The skill produces text or JSON reports with attribution credit, funnel conversion rates, and ROI metrics.

📦 Add this skill to Claude Code

# 1. Get the skills repo
git clone --depth 1 https://github.com/alirezarezvani/claude-skills /tmp/claude-skills

# 2. Copy this skill into your project (or ~/.claude/skills for all projects)
mkdir -p .claude/skills
cp -r /tmp/claude-skills/marketing-skill/skills/campaign-analytics .claude/skills/campaign-analytics

Skill source: marketing-skill/skills/campaign-analytics/SKILL.md

⚠️ Good to know

No statistical significance testing, no real-time data connections, single-currency only, and simplified time-decay without seasonal patterns.

❓ FAQ

What attribution models are available?

The skill supports first-touch, last-touch, linear, time-decay, and position-based models.

Can I get output in JSON format?

Yes, use the --format json flag with any script to get machine-readable JSON output.

What happens if my JSON is invalid?

The scripts will exit with descriptive errors like KeyError, ValueError, or TypeError, so validate your JSON with python -m json.tool first.

🤖 Overview, features, install steps and FAQ were generated from the project's SKILL.md on Sep 4, 2026. Always check the original source before running commands.