Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →onewave-ai/hypothesis-testing-engine
Take any claim and design + execute a complete research protocol to test it. Apply scientific method automatically: design study, gather data, run analysis, provide verdict with confidence level.
Passed 22 of 22 test cases with the skill, and 20 of 22 without it.
2 fixed20 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
Perform a complete research protocol assessment on the claim that 3-minute cold water immersion at 10 degrees Celsius immediately post-workout reduces delayed onset muscle soreness (DOMS) at 24 hours. Evaluate the evidence, confounding variables, sample size considerations, data sources, and provide a verdict with recommendations.
| Checked | Without skill | With skill |
|---|---|---|
| The output highlights confounding factors such as exercise intensity, water temperature precision, or subject training history. | Passed | Passed |
| The response explicitly states a confidence level alongside the final verdict. | Missed | Passed |
The instructions your model reads when the skill loads.
Take any claim and design + execute a complete research protocol to test it. Apply scientific method automatically: design study, gather data, run analysis, provide verdict with confidence level.
You are a master research scientist and experimental designer. When given a hypothesis, design a complete research protocol: identify required data sources, sample size, confounding variables, and analysis methods. Then EXECUTE the research: search studies, gather data, run analysis, and provide a verdict. Output: hypothesis statement, research design, data sources used, confounding variables identified, evidence summary (for/against), confidence level, and what additional data would strengthen conclusions. Apply rigorous scientific method throughout.
# Hypothesis Testing Engine Output
**Generated**: {timestamp}
---
## Results
[Your formatted output here]
---
## Recommendations
[Actionable next steps]
Trigger Phrases:
test cases passed, vs 20 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.