Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/hypothesis-formulation
Campaign: transform insights and gaps into structured testable hypotheses
Passed 1 of 8 test cases with the skill, and 4 of 8 without it.
and 2 more in the full report
3 fixed1 passed either way8 still failing10 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are initiating a new research campaign to investigate quantum compiler optimization failures. Outline the first context action before generating hypotheses.
| Checked | Without skill | With skill |
|---|---|---|
| Triggers context initialization to establish a new campaign context store at the start of the process. | Missed | Passed |
The instructions your model reads when the skill loads.
Transform insights and gaps into structured testable hypotheses — answering "how do we turn an insight into a testable hypothesis?"
Not met → stop, recommend completing gap-prioritization or upstream work first.
Transform a vague "there's a gap here" or "this phenomenon is interesting" into a precise, falsifiable hypothesis with boundary conditions. The output is not a "solution" but a "testable proposition."
| Strategy | When to Use | Reasoning direction |
|---|---|---|
| deductive-hypothesis-generation | The domain has mature theory, and the gap is a deviation between theoretical prediction and reality | Theory → prediction |
| inductive-hypothesis-generation | The domain lacks theory but has abundant empirical observations or data patterns | Data → regularity |
| abductive-hypothesis-generation | An anomalous phenomenon that existing theory cannot explain has been observed | Anomaly → best explanation |
| competing-hypothesis-construction | Need to maintain openness and avoid confirmation bias | Multiple explanations in parallel |
| hypothesis-operationalization | A directional hypothesis exists and needs to be formalized into a testable form | Vague → precise |
CC selects autonomously based on input characteristics (whether there is theoretical support, whether there is anomalous data, hypothesis maturity). Can be combined serially.
| Tier | Hypothesis yield | Theory/mechanism | Falsifiability | Competing hypotheses |
|---|---|---|---|---|
| S | ≥2 structured hypotheses | ≥2 relevant theories | 1 falsification scenario per hypothesis | Optional |
| M | ≥3 structured hypotheses | ≥3 theories + ≥5 mechanisms | ≥1 scenario + boundary conditions per hypothesis | ≥2 competing hypotheses |
| L | ≥5 structured hypotheses | ≥5 theories + ≥8 mechanisms | Complete falsifiability audit | ≥3 competing hypotheses + discriminating predictions |
test cases passed, vs 4 / 8 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.