brainstorm-experiments-new applies lean startup methodology to a new product concept. The agent first writes an XYZ hypothesis in the form “At least X% of Y will do Z”, then proposes two or three pretotype experiments to test it with minimal effort.
Options include a landing page, explainer video, email campaign, pre-order or waitlist and a concierge or manual MVP. The method follows Alberto Savoia’s The Right It, favoring skin in the game and your own data over other people’s data.
What You Get
- An XYZ hypothesis with the percentage, target market and action filled in
- Two or three pretotype experiments chosen for low effort
- A method, metric and success threshold for each experiment
- Guidance to test willingness to pay with real commitment
Common Use Cases
- Testing demand for a startup idea with a landing page and sign-up goal
- Designing a pre-order or waitlist test to check willingness to pay
- Running a concierge MVP before writing any code
- Turning a vague concept into a measurable hypothesis
What Makes It Unique
The skill is built on Alberto Savoia’s pretotyping ideas: skin in the game, which treats real commitment of time, money or reputation as the reliable signal, and Your Own Data (YODA), which prefers data you collect over market reports or analogies. The XYZ hypothesis format makes the target measurable from the start. The existing-product counterpart, brainstorm-experiments-existing, covers prototypes, fake doors and A/B tests on a live product.
Under The Hood
A single SKILL.md of instructions with no scripts. The agent reads any market research or mockup files you attach with its own file tools and writes the hypothesis and experiments in the conversation. The skill says to save substantial output as markdown, so it can write a file. It does not tell the agent to fetch web pages, call APIs or run commands. Your concept replaces $ARGUMENTS in the prompt.