Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Score ideas on novelty dimensions — structural distance from known solutions, conceptual surprise, domain-crossing depth. Produces ranked novelty assessment.
.claude/skills/yogsoth-ai-creative-ideation-novelty-scoring/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✓→✓ | ＝ Same ✓ | 13% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | 49% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | -9% | 0% |
| case-02 | ✗→✗ | ＝ Same ✗ | -18% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | -51% | 0% |
Score ideas on multiple novelty dimensions.
Subagent — spawned via subagent-spawning/spawn-agent skill.
Novelty assessment requires comparing each idea against the known solution landscape and scoring across multiple dimensions. Benefits from focused analytical attention.
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
<!-- 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 | fail→fail | 7,483 | 5,916 | -21% | 1 | 1 | 0% | 1,274 | 1,048 | -18% | 0 | 0 | — |
case-01 | fail→fail | 6,165 | 2,864 | -54% | 1 | 1 | 0% | 1,140 | 559 | -51% | 0 | 0 | — |
case-03 | fail→fail | 7,136 | 3,651 | -49% | 1 | 1 | 0% | 1,234 | 664 | -46% | 0 | 0 | — |
case-04 | fail→fail | 8,550 | 15,177 | +78% | 1 | 1 | 0% | 1,383 | 2,658 | +92% | 0 | 0 | — |
case-05 | fail→fail | 7,130 | 3,211 | -55% | 1 | 1 | 0% | 1,123 | 623 | -45% | 0 | 0 | — |
case-06 | fail→fail | 6,762 | 20,526 | +204% | 1 | 1 | 0% | 1,061 | 3,749 | +253% | 0 | 0 | — |
case-07 | fail→fail | 8,093 | 2,927 | -64% | 1 | 1 | 0% | 1,245 | 558 | -55% | 0 | 0 | — |
case-08 | fail→fail | 5,556 | 8,377 | +51% | 1 | 1 | 0% | 853 | 1,529 | +79% | 0 | 0 | — |
case-09 | fail→fail | 7,678 | 11,162 | +45% | 1 | 1 | 0% | 1,143 | 2,020 | +77% | 0 | 0 | — |
case-10 | fail→fail | 10,420 | 13,442 | +29% | 1 | 1 | 0% | 1,531 | 2,300 | +50% | 0 | 0 | — |
case-11 | fail→fail | 9,561 | 7,617 | -20% | 1 | 1 | 0% | 1,446 | 1,250 | -14% | 0 | 0 | — |
case-12 | fail→fail | 20,249 | 20,713 | +2% | 1 | 1 | 0% | 2,984 | 3,387 | +14% | 0 | 0 | — |
case-13 | fail→fail | 20,717 | 5,126 | -75% | 1 | 1 | 0% | 3,197 | 960 | -70% | 0 | 0 | — |
case-14 | fail→fail | 20,966 | 24,595 | +17% | 1 | 1 | 0% | 3,469 | 4,318 | +24% | 0 | 0 | — |
case-15 | fail→fail | 10,739 | 8,947 | -17% | 1 | 1 | 0% | 1,605 | 1,467 | -9% | 0 | 0 | — |
case-16 | fail→fail | 17,190 | 82,842 | +382% | 1 | 1 | 0% | 2,733 | 3,636 | +33% | 0 | 0 | — |
case-17 | fail→fail | 11,252 | 10,962 | -3% | 1 | 1 | 0% | 1,879 | 817 | -57% | 0 | 0 | — |
case-18 | fail→fail | 8,400 | 11,586 | +38% | 1 | 1 | 0% | 1,275 | 2,101 | +65% | 0 | 0 | — |
case-19 | fail→fail | 7,483 | 14,734 | +97% | 1 | 1 | 0% | 1,189 | 2,613 | +120% | 0 | 0 | — |
case-20 | pass→pass | 15,168 | 16,931 | +12% | 1 | 1 | 0% | 2,292 | 2,587 | +13% | 0 | 0 | — |
case-21 | pass→pass | 20,243 | 26,798 | +32% | 1 | 1 | 0% | 3,541 | 5,259 | +49% | 0 | 0 | — |
case-22 | pass→pass | 9,228 | 8,580 | -7% | 1 | 1 | 0% | 1,919 | 1,745 | -9% | 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 0 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.
Other measured skills in the registry, with their headline benchmark lift.