Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Construct distinct future scenarios, evaluate portfolio performance under each, and identify vulnerabilities and robustness characteristics.
.claude/skills/yogsoth-ai-scenario-stress-testing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -66% | 0% |
Evaluate how a portfolio performs across multiple plausible future scenarios to identify vulnerabilities, assess robustness, and inform portfolio adjustments.
| Stage | SOP | Purpose | |-------|-----|---------| | 1 | scenario-construction | Construct >=3 distinct future scenarios | | 2 | portfolio-evaluation-per-scenario | Evaluate portfolio under each scenario | | 3 | portfolio-synthesis | Synthesize findings into robustness verdict |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | portfolio-evaluation-per-scenario | Evaluate a specific portfolio's performance metrics and vulnerabilities under a given scenario. | | portfolio-synthesis | Synthesize all per-scenario evaluations into a final portfolio recommendation with robustness score and actionable guidance. | | scenario-construction | Construct distinct future scenarios spanning key uncertainties for portfolio stress testing. |
<!-- END available-tables (generated) -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→fail | 20,488 | 30,353 | +48% | 1 | 1 | 0% | 2,357 | 4,802 | +104% | 0 | 0 | — |
case-05 | fail→pass | 25,705 | 15,810 | -38% | 1 | 1 | 0% | 3,305 | 2,056 | -38% | 0 | 0 | — |
case-01 | fail→pass | 49,615 | 35,492 | -28% | 1 | 1 | 0% | 8,281 | 5,335 | -36% | 0 | 0 | — |
case-02 | pass→fail | 20,111 | 17,756 | -12% | 1 | 1 | 0% | 2,904 | 2,299 | -21% | 0 | 0 | — |
case-03 | fail→pass | 19,297 | 27,945 | +45% | 1 | 1 | 0% | 2,729 | 4,865 | +78% | 0 | 0 | — |
case-06 | fail→fail | 30,252 | 12,887 | -57% | 1 | 1 | 0% | 3,718 | 1,527 | -59% | 0 | 0 | — |
case-07 | fail→fail | 19,458 | 29,347 | +51% | 1 | 1 | 0% | 3,016 | 4,713 | +56% | 0 | 0 | — |
case-08 | fail→fail | 23,336 | 22,820 | -2% | 1 | 1 | 0% | 2,830 | 3,984 | +41% | 0 | 0 | — |
case-09 | fail→fail | 19,985 | 12,083 | -40% | 1 | 1 | 0% | 2,210 | 2,299 | +4% | 0 | 0 | — |
case-10 | fail→pass | 11,012 | 20,688 | +88% | 1 | 1 | 0% | 1,481 | 2,893 | +95% | 0 | 0 | — |
case-11 | fail→pass | 25,256 | 12,245 | -52% | 1 | 1 | 0% | 4,464 | 1,533 | -66% | 0 | 0 | — |
case-12 | fail→fail | 20,790 | 30,131 | +45% | 1 | 1 | 0% | 2,267 | 4,516 | +99% | 0 | 0 | — |
case-13 | fail→fail | 22,314 | 23,321 | +5% | 1 | 1 | 0% | 2,472 | 4,009 | +62% | 0 | 0 | — |
case-14 | fail→pass | 29,368 | 21,567 | -27% | 1 | 1 | 0% | 3,606 | 3,241 | -10% | 0 | 0 | — |
case-15 | fail→pass | 33,337 | 36,602 | +10% | 1 | 1 | 0% | 4,162 | 5,556 | +33% | 0 | 0 | — |
case-16 | pass→pass | 32,745 | 22,848 | -30% | 1 | 1 | 0% | 3,472 | 3,929 | +13% | 0 | 0 | — |
case-17 | fail→pass | 31,929 | 33,907 | +6% | 1 | 1 | 0% | 4,550 | 5,290 | +16% | 0 | 0 | — |
case-18 | fail→fail | 29,370 | 15,658 | -47% | 1 | 1 | 0% | 3,599 | 2,024 | -44% | 0 | 0 | — |
case-19 | fail→pass | 32,937 | 30,243 | -8% | 1 | 1 | 0% | 4,805 | 6,112 | +27% | 0 | 0 | — |
case-20 | pass→pass | 49,151 | 27,961 | -43% | 1 | 1 | 0% | 8,233 | 3,759 | -54% | 0 | 0 | — |
case-21 | fail→pass | 56,335 | 31,721 | -44% | 1 | 1 | 0% | 7,183 | 5,732 | -20% | 0 | 0 | — |
case-22 | fail→pass | 49,210 | 28,442 | -42% | 1 | 1 | 0% | 7,003 | 3,762 | -46% | 0 | 0 | — |
case-23 | pass→fail | 30,754 | 22,603 | -27% | 1 | 1 | 0% | 4,108 | 4,133 | +1% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.