Experiment Design Planner for ChatGPT: Set Success and Decision Rules Early
Turn a product assumption into a bounded experiment with outcome measures, sample scope, duration, and a rule for what to do next.
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 skills/experiment-design/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for experiment-design 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 experiment-design 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 wants to know whether category labels help people find books. Twelve participants can attempt two fixed discovery tasks. Draft a small test, measures, and iteration rule.What to check
Specify completion, time, or wrong turns with a comparison baseline and collection method. Treat twelve participants as directional and state how inconclusive results will be handled.
Original SKILL.md on GitHub · Updated
Frequently asked question
Should the primary measure be chosen after seeing the results?
Set a primary measure and any guardrails up front. Use the preset decision rules after the run and label added analyses exploratory.