Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Wish-fulfillment thinking — ignore physical laws for ideal solution. Use unconstrained imagination to reveal what the problem truly needs.
.claude/skills/yogsoth-ai-fantasy-analogy/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -46% | 0% |
Wish-fulfillment thinking — ignore physical laws to imagine the ideal solution, then work backward to feasible approximations.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 15 | 0 | 0% | | web-research | 5 | 0 | 0% | | paper-overview | 15 | 0 | 0% | | paper-search | 10 | 0 | 0% | | paper-research | 3 | 0 | 0% |
Cannot exit strategy until ≥80% of each budget line is consumed OR yield targets are met with justification for remaining budget.
| Tactic | Role | |--------|------| | analogy-extraction | Extract principles from fantasy solutions |
| SOP | Role | |-----|------| | fantasy-wish | Generate unconstrained ideal solutions | | springboard-launch | Convert fantasy insights into feasible solutions | | synectics-synthesis | Synthesize fantasy analogy outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | fantasy-wish | Unconstrained wish-fulfillment ideation. Ignore all physical laws to imagine the ideal solution, then identify realization directions. | | springboard-launch | Convert analogy insights into concrete feasible solutions. Transform abstract connections into actionable mechanisms. | | synectics-synthesis | Synthesize all synectics outputs into a structured idea report. Combines results from all analogy types and excursion processes. |
<!-- 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 | pass→pass | 15,354 | 13,393 | -13% | 1 | 1 | 0% | 1,222 | 1,364 | +12% | 0 | 0 | — |
case-02 | fail→pass | 17,518 | 20,388 | +16% | 1 | 1 | 0% | 2,493 | 3,251 | +30% | 0 | 0 | — |
case-03 | pass→pass | 8,596 | 2,350 | -73% | 1 | 1 | 0% | 1,282 | 869 | -32% | 0 | 0 | — |
case-04 | pass→pass | 13,224 | 14,811 | +12% | 1 | 1 | 0% | 2,108 | 2,781 | +32% | 0 | 0 | — |
case-05 | pass→pass | 17,813 | 23,735 | +33% | 1 | 1 | 0% | 2,651 | 3,571 | +35% | 0 | 0 | — |
case-06 | pass→pass | 7,812 | 3,531 | -55% | 1 | 1 | 0% | 1,181 | 1,127 | -5% | 0 | 0 | — |
case-07 | fail→pass | 7,816 | 4,050 | -48% | 1 | 1 | 0% | 1,130 | 1,186 | +5% | 0 | 0 | — |
case-08 | pass→pass | 12,591 | 3,771 | -70% | 1 | 1 | 0% | 1,863 | 1,147 | -38% | 0 | 0 | — |
case-09 | fail→pass | 11,967 | 2,076 | -83% | 1 | 1 | 0% | 1,876 | 843 | -55% | 0 | 0 | — |
case-10 | fail→pass | 10,030 | 1,763 | -82% | 1 | 1 | 0% | 1,568 | 764 | -51% | 0 | 0 | — |
case-11 | fail→pass | 9,113 | 1,407 | -85% | 1 | 1 | 0% | 1,304 | 707 | -46% | 0 | 0 | — |
case-12 | pass→pass | 10,976 | 7,514 | -32% | 1 | 1 | 0% | 1,787 | 1,663 | -7% | 0 | 0 | — |
case-13 | pass→pass | 2,311 | 2,335 | +1% | 1 | 1 | 0% | 402 | 872 | +117% | 0 | 0 | — |
case-14 | pass→pass | 3,302 | 1,598 | -52% | 1 | 1 | 0% | 525 | 746 | +42% | 0 | 0 | — |
case-15 | pass→pass | 10,058 | 9,506 | -5% | 1 | 1 | 0% | 1,496 | 1,909 | +28% | 0 | 0 | — |
case-16 | fail→pass | 11,333 | 6,540 | -42% | 1 | 1 | 0% | 1,642 | 1,501 | -9% | 0 | 0 | — |
case-17 | pass→pass | 18,066 | 21,143 | +17% | 1 | 1 | 0% | 2,633 | 2,758 | +5% | 0 | 0 | — |
case-18 | pass→pass | 1,794 | 1,593 | -11% | 1 | 1 | 0% | 262 | 734 | +180% | 0 | 0 | — |
case-19 | fail→pass | 10,620 | 14,328 | +35% | 1 | 1 | 0% | 1,685 | 2,194 | +30% | 0 | 0 | — |
case-20 | pass→fail | 17,258 | 28,714 | +66% | 1 | 1 | 0% | 2,854 | 5,297 | +86% | 0 | 0 | — |
case-21 | pass→fail | 19,920 | 25,650 | +29% | 1 | 1 | 0% | 3,363 | 4,891 | +45% | 0 | 0 | — |
case-22 | pass→fail | 30,453 | 9,673 | -68% | 1 | 1 | 0% | 6,067 | 1,071 | -82% | 0 | 0 | — |
case-23 | pass→pass | 2,925 | 1,919 | -34% | 1 | 1 | 0% | 532 | 761 | +43% | 0 | 0 | — |
case-24 | pass→pass | 12,584 | 9,448 | -25% | 1 | 1 | 0% | 1,844 | 1,928 | +5% | 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 +17 percentage points is the difference between those two pass rates over the 23 comparable cases. 3 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.