Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Select the single best candidate from a set using WSM, TOPSIS, AHP, MAUT, or VIKOR methods.
.claude/skills/yogsoth-ai-best-option-selection/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 180% | 0% |
| case-15 | ✓→✗ | ▼ Worse | -1% | 0% |
| case-18 | ✓→✗ | ▼ Worse | 75% | 0% |
Purpose: Select the single best-performing alternative from a candidate set, supporting WSM, TOPSIS, AHP, MAUT, VIKOR, and other methods.
When to use:
| Base SOP | Target | ±10% Range | |----------|--------|------------| | criterion-definition | 5-8 criteria | 4-9 | | weight-elicitation-sop | 1 weight vector | 1 | | alternative-scoring | 1 score matrix | 1 | | normalization | 1 normalized matrix | 1 | | scoring-synthesis | 1 recommendation | 1 |
yamlstrategy: best-option-selection status: pending criteria_defined: false weights_computed: false scores_computed: false normalized: false synthesized: false selected_method: null result: null
markdown## Best Option Recommendation **Recommended:** [Alternative name] **Overall Score:** [Score value] **Method Used:** [WSM/TOPSIS/AHP/MAUT/VIKOR] ### Score Ranking | Rank | Alternative | Overall Score | Key Strengths | |------|-------------|---------------|---------------| ### Sensitivity Notes [Impact of weight changes on the result]
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | convergence-scoring-matrix-construction | Build a complete scoring matrix through criterion definition, weighting, scoring, normalization, and sensitivity 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-02 | pass→pass | 16,823 | 14,820 | -12% | 1 | 1 | 0% | 3,145 | 3,546 | +13% | 0 | 0 | — |
case-11 | fail→pass | 15,146 | 13,501 | -11% | 1 | 1 | 0% | 2,218 | 2,805 | +26% | 0 | 0 | — |
case-03 | pass→pass | 15,147 | 29,712 | +96% | 1 | 1 | 0% | 2,977 | 6,639 | +123% | 0 | 0 | — |
case-04 | pass→pass | 12,655 | 13,505 | +7% | 1 | 1 | 0% | 2,381 | 3,191 | +34% | 0 | 0 | — |
case-05 | pass→pass | 8,634 | 9,892 | +15% | 1 | 1 | 0% | 1,472 | 2,182 | +48% | 0 | 0 | — |
case-01 | fail→pass | 18,245 | 24,873 | +36% | 1 | 1 | 0% | 3,417 | 5,348 | +57% | 0 | 0 | — |
case-06 | pass→pass | 7,045 | 6,661 | -5% | 1 | 1 | 0% | 1,199 | 1,703 | +42% | 0 | 0 | — |
case-07 | pass→pass | 13,932 | 15,380 | +10% | 1 | 1 | 0% | 2,283 | 3,241 | +42% | 0 | 0 | — |
case-08 | pass→pass | 13,681 | 14,961 | +9% | 1 | 1 | 0% | 2,628 | 2,901 | +10% | 0 | 0 | — |
case-09 | fail→pass | 9,695 | 22,390 | +131% | 1 | 1 | 0% | 1,519 | 4,253 | +180% | 0 | 0 | — |
case-10 | pass→pass | 15,827 | 10,026 | -37% | 1 | 1 | 0% | 2,420 | 2,027 | -16% | 0 | 0 | — |
case-12 | pass→pass | 11,274 | 8,758 | -22% | 1 | 1 | 0% | 1,887 | 2,109 | +12% | 0 | 0 | — |
case-13 | pass→pass | 9,414 | 9,345 | -1% | 1 | 1 | 0% | 1,453 | 2,068 | +42% | 0 | 0 | — |
case-14 | pass→pass | 10,809 | 10,813 | +0% | 1 | 1 | 0% | 1,696 | 2,371 | +40% | 0 | 0 | — |
case-15 | pass→fail | 13,159 | 10,208 | -22% | 1 | 1 | 0% | 2,016 | 1,986 | -1% | 0 | 0 | — |
case-16 | pass→pass | 6,876 | 3,719 | -46% | 1 | 1 | 0% | 1,054 | 1,131 | +7% | 0 | 0 | — |
case-17 | pass→pass | 17,364 | 16,222 | -7% | 1 | 1 | 0% | 2,503 | 3,675 | +47% | 0 | 0 | — |
case-18 | pass→fail | 17,090 | 26,412 | +55% | 1 | 1 | 0% | 3,037 | 5,315 | +75% | 0 | 0 | — |
case-19 | fail→fail | 8,097 | 4,392 | -46% | 1 | 1 | 0% | 1,298 | 1,291 | -1% | 0 | 0 | — |
case-20 | pass→pass | 11,507 | 7,188 | -38% | 1 | 1 | 0% | 1,750 | 1,704 | -3% | 0 | 0 | — |
case-21 | pass→pass | 14,861 | 14,037 | -6% | 1 | 1 | 0% | 2,193 | 2,730 | +24% | 0 | 0 | — |
case-22 | pass→pass | 17,203 | 14,381 | -16% | 1 | 1 | 0% | 2,667 | 2,853 | +7% | 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. 22 cases were attempted. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 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.