Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/counterfactual-reasoning
Tactic for reasoning about what would happen if variables were different — supports causal identification and intervention analysis.
Passed 20 of 22 test cases with the skill, and 18 of 22 without it.
2 fixed18 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
Analyze the counterfactual impact on project completion if supplier alpha had delivered components on time rather than 2 weeks late. Provide a complete counterfactual assessment.
| Checked | Without skill | With skill |
|---|---|---|
| Specifies the exact critical path delay mechanism connecting supplier delivery to final project assembly. | Missed | Passed |
| Provides a distinct numerical or qualitative confidence level entry for the counterfactual trajectory. | Missed | Passed |
The instructions your model reads when the skill loads.
Reason about what would happen if a variable were different. "If X had not occurred, would Y still have happened?" This is the gold standard for causal identification.
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| causal-chain-query | SOP for tracing causal chains — follow edges from cause to effect through intermediate variables. |
| confidence-scoring | SOP for assigning calibrated confidence scores to causal claims based on evidence quality and quantity. |
| contradiction-flagging | SOP for flagging contradictions in the causal model — identify conflicting evidence or mechanism claims. |
test cases passed, vs 18 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.