Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/factor-removal
Strategy: Systematic factor removal — remove factors one at a time and observe whether the conclusion remains stable, identifying which factors are load-bearing.
Passed 17 of 19 test cases with the skill, and 9 of 19 without it.
and 9 more in the full report
12 fixed9 passed either way0 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
An evaluation plan for a Medium resource budget calls for testing 5 factor combinations. What is the maximum permitted number of combination removals for Medium budget?
| Checked | Without skill | With skill |
|---|---|---|
| Cap combination removals at 3 for a Medium resource budget. | Missed | Passed |
The instructions your model reads when the skill loads.
Ablation study approach: systematically remove each factor and observe conclusion stability.
| Parameter | S | M | L |
|---|---|---|---|
| Factors removed | 5 | 10 | 20 |
| Removal iterations | 1 | 2 | 3 |
| Combination removals | 0 | 3 | 8 |
factor-enumeration → [rank by suspected importance]
→ [for each factor]:
single-factor-removal
→ counterfactual-scenario-construction
→ fragility-measurement
→ [if budget allows, test combinations]:
single-factor-removal (multiple factors)
→ counterfactual-scenario-construction
→ load-bearing-identification (final ranking)
test cases passed, vs 9 / 19 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.