Campaign: Counterfactual reasoning to identify load-bearing factors. Core question: If key factors were different, would the conclusion still hold? Methods: Pearl SCM Three-Step, Lewis Possible Worlds, Tetlock & Belkin, PNS/PS.
NewMaintained
Automatic
◆Research pack
Last verified 8/22/2026
What it changes
Passed 7 of 14 test cases with the skill, and 7 of 14 without it.
Without skill50%
With skill50%
Checks it passed that the model alone missed
Selects closest-worlds as fallback strategy.
Constructs scenarios with minimal deviation from actuality.
Aggregates fragility measurements across all tested factors.
3 fixed8 passed either way8 still failing3 broke
Pass-rate lift
0 pp
Tokens
+27%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 8/22/2026v211 of 22 cases passed with skill · 14 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
We are evaluating a novel zero-knowledge proof compression approach. We intended to use factor removal, but our primary factor-ablation tool failed due to interconnected dependencies. Which fallback strategy should be activated specifically for an idea or approach artifact type?
What was checked, without and with the skill
Checked
Without skill
With skill
Selects closest-worlds as fallback strategy.
Missed
Passed
case-11 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md81 linessingle file
Counterfactual Probing Campaign
Core question: If key factors were different, would the conclusion still hold?
Methodology Sources
Pearl (2000) — Structural Causal Models, Three-Step counterfactual procedure
Lewis (1973) — Possible Worlds semantics for counterfactuals
Tetlock & Belkin (1996) — Counterfactual thought experiments in world politics
Fearon (1991) — Counterfactuals and hypothesis testing in political science
Williamson (2007) — The Philosophy of Philosophy, thought experiment methodology
Strategy Routing
Artifact Type
Primary Strategy
Fallback Strategy
hypothesis, claim
structural-counterfactual
necessity-sufficiency
research-question
thought-experiment
closest-worlds
idea, approach
factor-removal
closest-worlds
experiment-design
necessity-sufficiency
structural-counterfactual
gap
closest-worlds
factor-removal
Budget Table
Parameter
S (Quick)
M (Standard)
L (Deep)
Factors examined
5
10
20
Counterfactual scenarios
3
8
15
Necessity tests
3
6
12
Flip-point search depth
2
4
8
Tactics
systematic-factor-ablation — Remove factors one at a time, observe conclusion stability
minimal-change-search — Find smallest change that flips the conclusion
causal-necessity-testing — Evaluate necessity and sufficiency of each causal claim
Context Management
Each subagent operates in isolated context. Factor enumeration precedes all counterfactual reasoning. Scenarios are constructed with minimal deviation from actuality. Fragility measurements aggregate across all tested factors.