Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/hypothesis-comparison-matrix
SOP: Build a multi-dimensional comparison matrix of competing hypotheses
Passed 15 of 22 test cases with the skill, and 10 of 22 without it.
and 7 more in the full report
8 fixed7 passed either way4 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
We observed a spike in server CPU usage and suspect a memory leak in the garbage collector (Mechanism: heap fragmentation causing frequent full GC, predicting linear heap growth). Can you format this single explanation into a structured comparison matrix?
| Checked | Without skill | With skill |
|---|---|---|
| Returns an error stating that at least two hypotheses are required. | Missed | Passed |
The instructions your model reads when the skill loads.
Build a multi-dimensional comparison matrix of competing hypotheses, highlight key differences, and support informed selection.
Not met → stop and return error: at least 2 hypotheses are required to build a comparison matrix.
{
"dimensions": ["mechanism_type", "evidence_support", "testability", "parsimony", "scope", "theoretical_basis"],
"matrix": [
{
"hypothesis_id": "H1",
"label": "Primary Hypothesis",
"statement": "...",
"mechanism_type": "...",
"evidence_support": "strong | moderate | weak | none",
"testability": "high | medium | low",
"parsimony": "high | medium | low",
"scope": "broad | moderate | narrow",
"theoretical_basis": "Theory name(s)"
}
],
"key_differentiators": ["Dimension where hypotheses differ most"],
"recommendation": "Which hypothesis to prioritize and why",
"caveats": "Important limitations of the comparison"
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.