Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/falsifiability-audit
Tactic: hypothesis quality assurance — check falsifiability, repair failing hypotheses, complete operationalization and boundary-condition specification
Passed 19 of 25 test cases with the skill, and 8 of 25 without it.
and 13 more in the full report
12 fixed7 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our team provided 6 hypotheses regarding distributed database consensus latency under network partitions. Which tier pattern applies?
| Checked | Without skill | With skill |
|---|---|---|
| The response categorizes the workload as M tier (Standard). | Missed | Passed |
The instructions your model reads when the skill loads.
Gate a hypothesis on falsifiability, operational definition, and boundary conditions; can be entered from any hypothesis-generation path.
required: [hypothesis, operational_definition, boundary_conditions]
optional: [assumptions, prior_findings, evidence_updates]
constraints: [consume named scientific objects; preserve provenance; keep unresolved uncertainty visible]
Do not perform called SOP operations inline; each loaded SOP owns its contract and thresholds.
evaluate-falsifiability to evaluate the claim's reachable falsifiers.operationalize-construct to operationalize every construct used by the claim.specify-boundaries to state the scope and boundary conditions.
If the audit exposes an ill-formed question, consider formulate-research-question. If the claim is ready for an empirical test, consider design-experiment. If a broader falsification program is required, falsification-first-audit may be the better next tactic.Deviation: reorder only when a dependency is already satisfied or unavailable; record the reason and confidence effect.
produces: [falsifiability_verdict, operational_definition, boundary_conditions]
delta_fields: [findings, decisions]
test cases passed, vs 8 / 25 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.