Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/experiment-design
Transform validated hypotheses into rigorous, executable experiment designs
Passed 5 of 11 test cases with the skill, and 3 of 11 without it.
and 8 more in the full report
7 fixed3 passed either way10 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
After finishing our comparison design strategy under a Small budget, what mandatory context recording step must be taken before moving to synthesis?
| Checked | Without skill | With skill |
|---|---|---|
| Requires executing context-checkpoint after completing the strategy. | Missed | Passed |
| Appends strategy outputs into the phase process context file. | Missed | Passed |
The instructions your model reads when the skill loads.
Positioning: What experiment to run — transform a validated hypothesis into a rigorous experiment design that maximizes information yield per compute dollar.
Before entering this campaign, the following must be satisfied:
| Gate | Requirement |
|---|---|
| Hypothesis | A falsifiable hypothesis with clearly stated IV/DV exists |
| Scope | Research question is bounded (not open-ended exploration) |
| Resources | Preliminary compute/time budget is stated |
| Prior Work | Relevant baselines and datasets have been identified |
If any gate fails, route back to hypothesis-generation or research-question refinement.
Produce a complete experiment design document that specifies:
| Signal in Hypothesis | Strategy | When to Use |
|---|---|---|
| "Factor X affects Y" | factor-level-design | Testing effects of specific variables |
| "Component C contributes to performance" | ablation-design | Understanding component contributions |
| "Method M outperforms baseline B" | comparison-design | Claiming superiority over existing work |
| "Performance scales with resource R" | scaling-design | Understanding scaling behavior |
| "Method works under condition C" | robustness-design | Testing failure boundaries |
Multiple strategies may be composed for complex hypotheses.
test cases passed, vs 3 / 11 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.