Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →refoundai/growth-experimentation
Help users build and scale a high-velocity growth experimentation engine that prioritizes impact and fosters a culture of rapid learning.
Passed 19 of 22 test cases with the skill, and 16 of 22 without it.
and 3 more in the full report
5 fixed14 passed either way1 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am leading product growth for a digital platform and trying to evaluate when we should run formal lift tests versus deploying changes directly. Help me build a structured decision workflow that outlines evaluation criteria, messaging optimization approaches, and guidelines for measuring baseline counterfactuals.
| Checked | Without skill | With skill |
|---|---|---|
| Evaluates whether to run an A/B test versus shipping directly based on data volume, traffic reach, and testing friction. | Passed | Passed |
| Recommends Conversion Lift Studies or randomized holdout tests to measure true counterfactual performance. | Passed | Passed |
| Recommends shifting generic CTA microcopy like 'Continue' to goal-oriented commitment copy. | Missed | Passed |
The instructions your model reads when the skill loads.
Build a high-output engine to compound small wins into massive growth.
Help the user with growth experimentation velocity using insights from 10 guests and posts across Lenny's Podcast and Newsletter.
Timothy Davis: "You can always do a very, very small test. You can just put a little money into a platform, see if there's a sign of life. If there is, then you can pull back and say, 'Okay, we have signs of life. Now let's build a campaign around that.'"
Validate new channels or ideas using low-budget tests and narrow match thresholds before committing significant resources.
From "How today’s top consumer brands measure marketing’s impact": "Testing/conversion lift studies (CLS): regularly run by marketers to validate what performance would look like if you switched a channel off, or scaled spend up or down."
Use randomized testing and lift studies as the gold standard to observe what would happen without your intervention.
From "The secret to Duolingo’s exponential growth": "To get the best long-term gains, you should always have a sense of urgency. The quicker you launch winning experiments, the quicker those changes impact your growth. Not only that, but these improvements compound!"
Focus on high experiment velocity because early small wins multiply over time into significant competitive advantages.
Jackson Shuttleworth: "We've actually set up really good infrastructure for copy testing. We used to say continue, our standard CTA is continue, and we changed that to commit to my goal, and it was a massive win."
Shift from generic microcopy to intentional language that reinforces the user's specific goals and psychological state.
From "Fostering a culture of experimentation": "When systems are still in flux, you don't want to overinvest in tooling that will become outdated immediately when your data schema gets updated or some other piece of infrastructure changes. However, it is essential to have a way to rapidly iterate, and that means quick access to experiment results data. So if you need to in the early days, build something simple and scrappy at first, and over time evolve it to support the team's needs."
Prioritize rapid iteration over perfect infrastructure by starting with simple internal tools to prove the value of testing.
test cases passed, vs 16 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.