Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build a complete scoring matrix through criterion definition, weighting, scoring, normalization, and sensitivity testing.
.claude/skills/yogsoth-ai-convergence-scoring-matrix-construction/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 136% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-13 | ✓→✗ | ▼ Worse | -18% | 0% |
Standard MCDA workflow of define criteria → assign weights → score → aggregate → sensitivity check, producing a complete scoring matrix and ranking results.
Complete scoring matrix + weight vector + ranking results
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | alternative-scoring | Score each candidate alternative against all criteria to produce a score matrix. | | criterion-definition | Extract evaluation criteria from research goals and candidate alternatives. | | normalization | Normalize a score matrix using a specified method to make scores comparable across criteria. | | scoring-synthesis | Synthesize score matrix, rankings, and sensitivity analysis into a final recommendation. | | weight-elicitation-sop | Compute criteria weights using a specified elicitation method (AHP, Swing, BWM, MACBETH, or Simos). |
<!-- 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-01 | fail→fail | 27,757 | 28,454 | +3% | 1 | 1 | 0% | 6,240 | 6,694 | +7% | 0 | 0 | — |
case-02 | fail→fail | 23,187 | 6,704 | -71% | 1 | 1 | 0% | 4,831 | 870 | -82% | 0 | 0 | — |
case-03 | fail→fail | 28,005 | 27,248 | -3% | 1 | 1 | 0% | 6,246 | 6,700 | +7% | 0 | 0 | — |
case-04 | fail→pass | 16,079 | 12,596 | -22% | 1 | 1 | 0% | 2,920 | 2,674 | -8% | 0 | 0 | — |
case-05 | fail→pass | 13,312 | 9,693 | -27% | 1 | 1 | 0% | 2,285 | 1,561 | -32% | 0 | 0 | — |
case-06 | pass→pass | 14,908 | 9,853 | -34% | 1 | 1 | 0% | 2,352 | 2,038 | -13% | 0 | 0 | — |
case-07 | pass→pass | 10,818 | 4,721 | -56% | 1 | 1 | 0% | 1,658 | 1,204 | -27% | 0 | 0 | — |
case-08 | pass→pass | 10,855 | 6,854 | -37% | 1 | 1 | 0% | 1,837 | 1,612 | -12% | 0 | 0 | — |
case-09 | pass→pass | 8,027 | 2,685 | -67% | 1 | 1 | 0% | 1,348 | 835 | -38% | 0 | 0 | — |
case-10 | pass→pass | 9,676 | 5,177 | -46% | 1 | 1 | 0% | 1,450 | 1,302 | -10% | 0 | 0 | — |
case-11 | fail→fail | 10,024 | 4,156 | -59% | 1 | 1 | 0% | 1,597 | 1,170 | -27% | 0 | 0 | — |
case-12 | fail→pass | 15,437 | 26,017 | +69% | 1 | 1 | 0% | 2,648 | 6,250 | +136% | 0 | 0 | — |
case-13 | pass→fail | 16,062 | 11,026 | -31% | 1 | 1 | 0% | 3,148 | 2,574 | -18% | 0 | 0 | — |
case-14 | fail→pass | 11,330 | 5,994 | -47% | 1 | 1 | 0% | 1,794 | 1,313 | -27% | 0 | 0 | — |
case-15 | pass→pass | 14,322 | 10,290 | -28% | 1 | 1 | 0% | 2,420 | 2,215 | -8% | 0 | 0 | — |
case-16 | pass→pass | 12,204 | 9,050 | -26% | 1 | 1 | 0% | 1,996 | 1,953 | -2% | 0 | 0 | — |
case-17 | pass→pass | 14,403 | 12,340 | -14% | 1 | 1 | 0% | 2,663 | 2,880 | +8% | 0 | 0 | — |
case-18 | pass→pass | 6,475 | 3,501 | -46% | 1 | 1 | 0% | 1,041 | 964 | -7% | 0 | 0 | — |
case-19 | fail→fail | 9,149 | 4,145 | -55% | 1 | 1 | 0% | 1,472 | 1,021 | -31% | 0 | 0 | — |
case-20 | pass→pass | 13,375 | 8,381 | -37% | 1 | 1 | 0% | 2,105 | 1,818 | -14% | 0 | 0 | — |
case-21 | pass→pass | 14,366 | 3,646 | -75% | 1 | 1 | 0% | 2,446 | 1,002 | -59% | 0 | 0 | — |
case-22 | pass→pass | 20,049 | 25,795 | +29% | 1 | 1 | 0% | 4,333 | 5,825 | +34% | 0 | 0 | — |
case-23 | pass→pass | 13,445 | 15,476 | +15% | 1 | 1 | 0% | 2,211 | 2,754 | +25% | 0 | 0 | — |
case-24 | pass→pass | 15,782 | 15,263 | -3% | 1 | 1 | 0% | 2,981 | 3,483 | +17% | 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. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +13 percentage points is the difference between those two pass rates over the 23 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.