What data format does Funnel Analyzer require?

A structured CSV with defined stages and a header; the example uses visit, signup, trial, paid.

Can it replace analytics expertise or business decisions?

It computes metrics and visualizations but does not replace statistical expertise or strategic business decisions.

Does it access or upload data automatically?

No, it runs locally with user-provided CSVs; it relies on local dependencies like pandas and click.

funnel-analyzer

npx machina-cli add skill guia-matthieu/clawfu-skills/funnel-analyzer --openclaw

Files (1)

SKILL.md

1.5 KB

Funnel Analyzer

Analyze conversion funnels to identify drop-off points and optimization opportunities.

What Claude Does vs What You Decide

Claude Does	You Decide
Structures analysis frameworks	Metric definitions
Identifies patterns in data	Business interpretation
Creates visualization templates	Dashboard design
Suggests optimization areas	Action priorities
Calculates statistical measures	Decision thresholds

Dependencies

pip install pandas click

Commands

python scripts/main.py analyze data.csv --stages "visit,signup,trial,paid"
python scripts/main.py dropoff funnel.csv
python scripts/main.py visualize funnel.csv --output funnel-chart.html

Skill Boundaries

What This Skill Does Well

Structuring data analysis
Identifying patterns and trends
Creating visualization frameworks
Calculating statistical measures

What This Skill Cannot Do

Access your actual data
Replace statistical expertise
Make business decisions
Guarantee prediction accuracy

Skill Metadata

Mode: centaur

category: analytics
dependencies: [pandas]
difficulty: intermediate

Source

git clone https://github.com/guia-matthieu/clawfu-skills/blob/main/skills/analytics/funnel-analyzer/SKILL.mdView on GitHub

Overview

Funnel Analyzer helps you pinpoint where users drop off in conversion funnels and identify optimization opportunities. It supports analyzing checkout funnels, signup flows, and tracking funnel performance through visualizations. By structuring data analyses and highlighting drop-offs, it guides practical improvements.

How This Skill Works

It structures raw funnel data into stages, computes drop-off and conversion metrics with pandas, and generates visualization templates. The CLI exposes analyze, dropoff, and visualize commands to process CSVs and produce actionable reports.

When to Use It

Analyzing a checkout funnel to spot where users abandon the purchase
Tracking a signup flow to understand where new users drop off
Identifying conversion blockers in the user journey
Optimizing the overall user journey based on data-driven insights
Visualizing funnel performance to compare campaigns or time periods

Quick Start

Step 1: Prepare your data.csv with defined funnel stages (visit, signup, trial, paid)
Step 2: Run analysis: python scripts/main.py analyze data.csv --stages "visit,signup,trial,paid"
Step 3: Visualize results: python scripts/main.py visualize funnel.csv --output funnel-chart.html (Optional: python scripts/main.py dropoff funnel.csv for a drop-off report)

Best Practices

Define a consistent set of funnel stages (e.g., visit, signup, trial, paid) and ensure your data aligns with them
Use pandas-based processing to compute stage-by-stage drop-off and conversion rates
Create visualization templates to compare funnels across segments and timeframes
Calculate statistical measures (confidence intervals, significance) to avoid overinterpreting small changes
Validate findings with business context and prioritize actionable optimizations

Example Use Cases

Ecommerce checkout funnel analysis to reduce cart abandonment
SaaS onboarding funnel to improve signup-to-trial conversion
Mobile app funnel comparison across iOS and Android platforms
A/B test funnel results to determine which variant lowers drop-offs
Subscription site funnel optimization from visit to paid signup

Frequently Asked Questions

Add this skill to your agents