Funnel Analysis Skill for ChatGPT: Calculate Drop-Off and Rank Experiments
Use stage counts to calculate conversion, drop-off volume, and total conversion. Prioritize leaks by people lost and compare follow-up experiments by impact, confidence, and ease.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download pm-data-analytics/skills/funnel-analysis/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for funnel-analysis together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that funnel-analysis appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
In a fictional onboarding funnel, 1,000 users signed up in one week, 400 created a project, and 160 sent a first invitation. Calculate stage conversion and losses and overall conversion. Give one hypothesis that support tickets or interviews could test and compare two experiments.What to check
Both transitions should be 40%, with 600 and 240 users lost and 16% overall conversion. Investigate signup to project creation first. State what evidence would support a cause and label projected experiment impact as an estimate.
Original SKILL.md on GitHub · Updated
Frequently asked question
Why should I look at both percentages and people lost?
The percentage describes relative friction. The loss volume shows how many users are affected. Start with volume to allocate investigation time, then use segments and qualitative evidence to understand the cause.