Product Experiment Skill for ChatGPT: Test Existing Product Assumptions at Low Cost
Break a feature idea into testable assumptions. Compare prototypes, usability sessions, controlled trials, or technical spikes with success criteria and a decision rule.
中文Install in ChatGPT
Requires a ChatGPT workspace where you can create skills. This is a text adaptation of the pinned GitHub source.
- Review the inputs and outputs in the pinned pm-product-discovery/skills/brainstorm-experiments-existing/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide the current product, target users, assumption, resource limits, and available measures.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional calendar app wants to learn whether search filters reduce time to find an event. Six testers are available and traffic is too low for an A/B test. Propose two methods.What to check
Start with a short prototype task and include a comparator, completion time, and errors. Keep population-level impact for later testing.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can 'improve conversion' be the acceptance criterion?
Turn it into an observable metric with a baseline, window, and decision threshold. Confirm a proposed threshold when it is absent.