Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/falsifiability-check
SOP: check whether a hypothesis meets the falsifiability criterion
Passed 15 of 22 test cases with the skill, and 6 of 22 without it.
and 8 more in the full report
13 fixed2 passed either way3 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Analyze the statement: 'Either it will rain tomorrow in Seattle or it will not rain tomorrow in Seattle.' Evaluate whether this claim can be refuted by empirical observation, providing a JSON report with hypothesis_id, statement, positive_predictions, falsification_scenario, testability, verdict, revision_suggestion, and notes.
| Checked | Without skill | With skill |
|---|---|---|
| Response JSON sets verdict to not_falsifiable | Missed | Passed |
| Response JSON contains a non-null revision_suggestion proposing a specific testable rainfall condition | Passed | Passed |
The instructions your model reads when the skill loads.
Check hypotheses against Popper's falsifiability criterion, ensuring every hypothesis has an explicit refutation condition.
Not satisfied → stop and return an error: hypothesis statement is incomplete.
{
"hypothesis_id": "H1",
"statement": "...",
"positive_predictions": [
"If H1 is true, we should observe X in condition Y"
],
"falsification_scenario": "Specific observation that would conclusively refute H1",
"testability": "high | medium | low",
"verdict": "falsifiable | not_falsifiable | needs_revision",
"revision_suggestion": "How to make it falsifiable (null if already falsifiable)",
"notes": "Additional considerations"
}
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.