- Home
- Skills
- Data & Databases
- Funnel Analysis Playbook
Funnel Analysis Playbook
Find where users drop off in a multi-step funnel, compare segments and rank fixes by users lost and impact.
$12
Works with the AI tools you already use
Funnel Analysis Playbook
Example session with this skill installed
Analyze our signup funnel from events.csv: landing_view → signup → onboarding_complete → first_project → upgrade_paid, 7-day window. Split by device. Where should we focus?
- Read your context and instructions
- Compiled the funnel analysis playbook
- Generated the document
Illustrative example on synthetic data. It follows this skill's funnel_report_template.md.
Funnel Analysis Report: Signup to paid, 7-day window
Summary
Overall conversion is
2.08% (416 of 20,000). The largest absolute loss is at landing → signup, but the most
fixable leak is onboarding on mobile.
Funnel table
| Step | Users | Step conv. | Dropped |
|---|---|---|---|
| landing_view | 20,000 | – | – |
| signup | 6,400 | 32.0% | 13,600 |
| onboarding_complete | 4,160 | 65.0% | 2,240 |
| first_project | 2,080 | 50.0% | 2,080 |
| upgrade_paid | 416 | 20.0% | 1,664 |
Drop-off analysis by step
onboarding_complete (the biggest gap between segments)
- Desktop 78% vs mobile 49%.
- Median time to complete is 6 min on desktop and 19 min on mobile (P95 is 2.1 hours), which suggests friction rather than lack of intent.
Segment breakdown
| Device | Landing → paid |
|---|---|
| Desktop | 2.9% |
| Mobile | 1.3% |
Recommendations
Fix mobile onboarding. If mobile onboarding closed half the gap to desktop, that would recover about 400 users per 20,000 visitors, or about
40 extra paid users at current downstream rates.
2. Test a shorter signup form (the largest volume loss, but lower intent).
3. Re-run the funnel after the fix and compare period over period.
funnel-analysis-playbook.pdf
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
Funnel Analysis Playbook gives your agent a disciplined way to analyze conversion funnels. It defines the ordered steps and the completion window, builds a user-level funnel from an event log (with a bundled script), and computes step-to-step and overall conversion. It adds time-to-convert percentiles and segment comparisons, then ranks drop-off points by users lost and revenue impact.
Use it when
- Conversion is low and you need to know where people leave
- A product change may have hurt one step
- You are comparing conversion across channels, devices or plans
- You need a baseline before designing an A/B test
What's inside (installs as one folder, funnel-analysis/):
funnel-analysis/LICENSEfunnel-analysis/SKILL.mdfunnel-analysis/assets/funnel_report_template.mdfunnel-analysis/references/funnel_design_guide.mdfunnel-analysis/scripts/funnel_analyzer.py
Please read before buying: this is packaged from my free, MIT-licensed open-source library (https://github.com/nimrodfisher/data-analytics-skills). The same content is available there for free. You are paying for a ready-to-install package. It is a one-time purchase, sold as-is, with no support, updates or maintenance included. The MIT license is included.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 day ago
- Passed all security checks, Safe to install