Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Compare feasibility across multiple candidates using multi-dimensional radar and weighted feasibility index.
.claude/skills/yogsoth-ai-comparative-feasibility-ranking/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 11% | 0% |
Purpose: Produce a defensible ranking of candidates by feasibility. Uses multi-dimensional radar charts to visualize relative strengths and a weighted feasibility index to collapse multiple dimensions into a single comparable score.
When to use:
| Metric | Target | |--------|--------| | Candidates compared | >= 2 | | Dimensions in radar | >= 5 | | Weight justifications | 1 per dimension |
| Key | Type | Description | |-----|------|-------------| | candidates] | array | All candidates being compared | | dimension_weights{} | map | Dimension -> weight mapping | | radar_data] | array | Per-candidate radar scores | | feasibility_index] | array | Weighted composite scores | | ranking] | array | Final ranked list |
| Tactic | When | |--------|------| | multi-dimensional-readiness-scan | To generate per-candidate radar data for comparison | | staged-gate-evaluation | To compare gate-passage likelihood across candidates |
| SOP | Purpose | |-----|---------| | radar-synthesis | Produce radar data for each candidate | | feasibility-synthesis | Produce final comparative matrix |
yamlcomparative_ranking: dimensions: [technical, market, regulatory, resource, organizational] weights: {technical: 0.3, market: 0.25, regulatory: 0.2, resource: 0.15, organizational: 0.1} candidates: - {name, scores: {...}, weighted_index: 0.X, rank: N, tier: strong|moderate|weak} radar_data: [{candidate, dimension_scores: [...]}] recommendation: <top candidate(s) with rationale> caveats: [...]
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | multi-dimensional-readiness-scan | Assess readiness across multiple dimensions, synthesize into radar visualization, and identify bottleneck dimensions. | | staged-gate-evaluation | Define gate criteria for each stage, evaluate candidates at each gate, and render go/kill/recycle decisions with evidence. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | feasibility-synthesis | Synthesize all assessments into a feasibility matrix, recommendation, and risk summary. | | 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-01 | fail→pass | 14,932 | 9,915 | -34% | 1 | 1 | 0% | 2,995 | 3,007 | +0% | 0 | 0 | — |
case-02 | fail→pass | 18,361 | 18,026 | -2% | 1 | 1 | 0% | 4,194 | 4,855 | +16% | 0 | 0 | — |
case-03 | fail→pass | 24,091 | 19,379 | -20% | 1 | 1 | 0% | 4,985 | 4,597 | -8% | 0 | 0 | — |
case-04 | fail→pass | 20,967 | 13,652 | -35% | 1 | 1 | 0% | 3,952 | 3,406 | -14% | 0 | 0 | — |
case-05 | fail→pass | 23,797 | 19,220 | -19% | 1 | 1 | 0% | 3,820 | 4,231 | +11% | 0 | 0 | — |
case-06 | pass→pass | 18,178 | 14,396 | -21% | 1 | 1 | 0% | 3,213 | 3,672 | +14% | 0 | 0 | — |
case-07 | pass→pass | 17,355 | 10,187 | -41% | 1 | 1 | 0% | 3,439 | 2,797 | -19% | 0 | 0 | — |
case-08 | fail→pass | 10,477 | 2,539 | -76% | 1 | 1 | 0% | 1,926 | 1,197 | -38% | 0 | 0 | — |
case-09 | pass→pass | 10,785 | 2,312 | -79% | 1 | 1 | 0% | 1,916 | 1,167 | -39% | 0 | 0 | — |
case-20 | pass→fail | 27,100 | 36,490 | +35% | 1 | 1 | 0% | 4,318 | 6,911 | +60% | 0 | 0 | — |
case-10 | fail→pass | 6,223 | 2,170 | -65% | 1 | 1 | 0% | 991 | 1,103 | +11% | 0 | 0 | — |
case-11 | fail→pass | 12,546 | 1,734 | -86% | 1 | 1 | 0% | 2,372 | 1,025 | -57% | 0 | 0 | — |
case-12 | pass→pass | 15,210 | 10,708 | -30% | 1 | 1 | 0% | 2,499 | 2,641 | +6% | 0 | 0 | — |
case-13 | fail→fail | 10,009 | 11,100 | +11% | 1 | 1 | 0% | 1,640 | 3,095 | +89% | 0 | 0 | — |
case-14 | pass→pass | 17,782 | 17,076 | -4% | 1 | 1 | 0% | 2,910 | 3,987 | +37% | 0 | 0 | — |
case-21 | pass→pass | 21,327 | 33,627 | +58% | 1 | 1 | 0% | 3,923 | 6,914 | +76% | 0 | 0 | — |
case-15 | fail→pass | 17,922 | 11,834 | -34% | 1 | 1 | 0% | 2,848 | 2,881 | +1% | 0 | 0 | — |
case-16 | fail→pass | 20,095 | 11,500 | -43% | 1 | 1 | 0% | 3,291 | 2,771 | -16% | 0 | 0 | — |
case-17 | pass→pass | 14,186 | 11,737 | -17% | 1 | 1 | 0% | 2,860 | 2,981 | +4% | 0 | 0 | — |
case-18 | pass→pass | 15,626 | 16,204 | +4% | 1 | 1 | 0% | 2,920 | 3,762 | +29% | 0 | 0 | — |
case-19 | pass→pass | 20,021 | 18,823 | -6% | 1 | 1 | 0% | 3,325 | 4,119 | +24% | 0 | 0 | — |
case-22 | pass→pass | 14,726 | 20,284 | +38% | 1 | 1 | 0% | 2,390 | 3,608 | +51% | 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 +41 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.