Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Assess readiness across multiple dimensions, synthesize into radar visualization, and identify bottleneck dimensions.
.claude/skills/yogsoth-ai-multi-dimensional-readiness-scan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -15% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -43% | 0% |
Systematically evaluate a candidate across all relevant feasibility dimensions, produce a composite radar view, and surface the dimensions that are limiting overall readiness.
dimension-assessment SOP for each dimension (parallelizable).radar-synthesis SOP with the collected scores.bottleneck-identification SOP on the radar data.| SOP | Stage | Purpose | |-----|-------|---------| | dimension-assessment | 1 | Score a single readiness dimension | | radar-synthesis | 2 | Combine scores into radar chart data | | bottleneck-identification | 3 | Identify limiting dimensions |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | convergence-bottleneck-identification | Identify bottleneck dimensions from radar data with severity ranking. | | dimension-assessment | Score a single readiness dimension for a candidate with evidence and gap analysis. | | radar-synthesis | Synthesize multiple dimension scores into radar chart data and compute overall readiness. |
<!-- 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→pass | 15,006 | 12,118 | -19% | 1 | 1 | 0% | 1,525 | 1,626 | +7% | 0 | 0 | — |
case-01 | pass→pass | 16,401 | 9,121 | -44% | 1 | 1 | 0% | 1,775 | 1,230 | -31% | 0 | 0 | — |
case-02 | fail→pass | 10,869 | 9,553 | -12% | 1 | 1 | 0% | 1,566 | 1,225 | -22% | 0 | 0 | — |
case-03 | fail→pass | 8,906 | 9,341 | +5% | 1 | 1 | 0% | 1,282 | 1,094 | -15% | 0 | 0 | — |
case-05 | pass→pass | 17,245 | 10,597 | -39% | 1 | 1 | 0% | 1,826 | 1,295 | -29% | 0 | 0 | — |
case-06 | fail→pass | 23,107 | 2,220 | -90% | 1 | 1 | 0% | 1,686 | 780 | -54% | 0 | 0 | — |
case-07 | fail→pass | 18,227 | 12,249 | -33% | 1 | 1 | 0% | 2,178 | 1,555 | -29% | 0 | 0 | — |
case-08 | pass→pass | 22,898 | 13,588 | -41% | 1 | 1 | 0% | 2,562 | 1,969 | -23% | 0 | 0 | — |
case-09 | pass→pass | 19,756 | 8,768 | -56% | 1 | 1 | 0% | 2,401 | 910 | -62% | 0 | 0 | — |
case-10 | fail→fail | 6,789 | 7,085 | +4% | 1 | 1 | 0% | 1,000 | 791 | -21% | 0 | 0 | — |
case-11 | fail→pass | 15,630 | 8,346 | -47% | 1 | 1 | 0% | 1,754 | 1,001 | -43% | 0 | 0 | — |
case-12 | pass→pass | 14,757 | 8,798 | -40% | 1 | 1 | 0% | 1,462 | 1,358 | -7% | 0 | 0 | — |
case-13 | fail→fail | 15,546 | 7,735 | -50% | 1 | 1 | 0% | 1,127 | 869 | -23% | 0 | 0 | — |
case-14 | pass→pass | 21,447 | 11,668 | -46% | 1 | 1 | 0% | 2,682 | 1,633 | -39% | 0 | 0 | — |
case-15 | fail→pass | 9,963 | 4,130 | -59% | 1 | 1 | 0% | 1,544 | 1,091 | -29% | 0 | 0 | — |
case-16 | fail→pass | 15,285 | 9,514 | -38% | 1 | 1 | 0% | 1,829 | 1,314 | -28% | 0 | 0 | — |
case-17 | pass→pass | 9,376 | 11,198 | +19% | 1 | 1 | 0% | 1,484 | 1,467 | -1% | 0 | 0 | — |
case-18 | fail→pass | 9,131 | 1,466 | -84% | 1 | 1 | 0% | 1,448 | 651 | -55% | 0 | 0 | — |
case-19 | pass→pass | 8,519 | 8,000 | -6% | 1 | 1 | 0% | 1,268 | 947 | -25% | 0 | 0 | — |
case-20 | pass→pass | 21,246 | 27,429 | +29% | 1 | 1 | 0% | 2,731 | 4,400 | +61% | 0 | 0 | — |
case-21 | pass→pass | 15,293 | 21,992 | +44% | 1 | 1 | 0% | 2,219 | 3,108 | +40% | 0 | 0 | — |
case-22 | pass→pass | 24,488 | 31,165 | +27% | 1 | 1 | 0% | 2,925 | 4,188 | +43% | 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, and 21 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 +36 percentage points is the difference between those two pass rates over the 21 comparable cases.
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.