Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/counterfactual-scenario-construction
Construct precise, internally consistent counterfactual scenarios where specified factors are altered, then reason about the resulting conclusion.
Passed 8 of 15 test cases with the skill, and 4 of 15 without it.
and 6 more in the full report
7 fixed4 passed either way9 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
In the Phase III protocol for oncology drug Trial-402, evaluate a counterfactual world where the target patient dosage factor is weakened by 50%. Provide the scenario narrative, evaluate if efficacy holds, weakens, flips, or is indeterminate, trace cascading biological effects, and include a consistency check.
| Checked | Without skill | With skill |
|---|---|---|
| The output provides a consistency_check field evaluating scenario coherence. | Passed | Passed |
| The conclusion status field uses one of holds, weakened, flipped, or indeterminate. | Missed | Passed |
The instructions your model reads when the skill loads.
Builds precise counterfactual worlds where specified factors differ from actuality.
Subagent — spawned via subagent-spawning/spawn-agent.
Scenario construction requires careful reasoning about cascading effects of changes while maintaining internal consistency.
One unit = one scenario construction per factor change.
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
test cases passed, vs 4 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.