Cohort Analysis Skill for ChatGPT: Compare Mature Signup Weeks
Build a retention table from supplied cohort counts. Define the revisit event, use a consistent observation window, and mark cohorts that have yet to reach it.
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 product-manager/analytics/skills/cohort-analysis/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for cohort-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 cohort-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
A fictional reading app has 100 signups and 40 day-seven returners in week one, then 80 and 36 in week two. Week three has 120 signups and is only four days old. Produce a retention table.What to check
The first two day-seven rates are 40% and 45%. Week three is marked immature. Keep the event definition and raw counts visible and treat the difference as a lead to investigate.
Original SKILL.md on GitHub · Updated
Frequently asked question
How can cohorts of different sizes be compared?
Use eligible signups in each cohort as the denominator and keep the event and time window consistent. Show cohort sizes beside their rates.