Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Find structurally similar systems in nature/technology/society. Map structural parallels to generate transferable solution principles.
.claude/skills/yogsoth-ai-direct-analogy/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-12 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -27% | 0% |
Find structurally similar systems in nature, technology, or society that share structural properties with the problem domain.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 25 | 0 | 0% | | web-research | 8 | 0 | 0% | | paper-overview | 25 | 0 | 0% | | paper-search | 15 | 0 | 0% | | paper-research | 5 | 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 structural analogies from cross-domain sources | | excursion-orchestration | Full excursion if direct search insufficient |
| SOP | Role | |-----|------| | direct-analogy-generation | Generate analogies from nature/tech/society | | analogy-chain | Deepen promising analogies through layers | | springboard-launch | Convert best analogies into concrete solutions | | synectics-synthesis | Synthesize final analogy report |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | excursion-orchestration | Orchestrate the excursion sequence — departure into unrelated domain, force-fit discoveries back to problem, launch springboard ideas. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | analogy-chain | Chain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface. | | direct-analogy-generation | Find direct analogies from nature/tech/society that share structural properties with the problem. Produces analogy list with structural mappings. | | 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-11 | pass→pass | 13,103 | 18,502 | +41% | 1 | 1 | 0% | 2,060 | 3,374 | +64% | 0 | 0 | — |
case-12 | fail→pass | 15,896 | 6,741 | -58% | 1 | 1 | 0% | 2,521 | 1,632 | -35% | 0 | 0 | — |
case-01 | fail→fail | 32,949 | 8,610 | -74% | 1 | 1 | 0% | 5,045 | 1,124 | -78% | 0 | 0 | — |
case-02 | fail→fail | 30,979 | 46,561 | +50% | 1 | 1 | 0% | 4,581 | 6,844 | +49% | 0 | 0 | — |
case-03 | pass→pass | 40,551 | 42,916 | +6% | 1 | 1 | 0% | 6,211 | 6,829 | +10% | 0 | 0 | — |
case-04 | pass→pass | 13,819 | 24,576 | +78% | 1 | 1 | 0% | 2,093 | 3,095 | +48% | 0 | 0 | — |
case-05 | fail→pass | 14,959 | 18,107 | +21% | 1 | 1 | 0% | 2,056 | 3,070 | +49% | 0 | 0 | — |
case-06 | fail→pass | 16,644 | 11,935 | -28% | 1 | 1 | 0% | 2,357 | 2,366 | +0% | 0 | 0 | — |
case-07 | pass→pass | 19,736 | 43,056 | +118% | 1 | 1 | 0% | 2,890 | 3,793 | +31% | 0 | 0 | — |
case-08 | pass→fail | 5,822 | 6,470 | +11% | 1 | 1 | 0% | 845 | 1,649 | +95% | 0 | 0 | — |
case-09 | pass→fail | 17,057 | 9,615 | -44% | 1 | 1 | 0% | 2,708 | 1,287 | -52% | 0 | 0 | — |
case-10 | fail→pass | 18,462 | 17,956 | -3% | 1 | 1 | 0% | 2,834 | 3,324 | +17% | 0 | 0 | — |
case-13 | pass→pass | 9,159 | 2,940 | -68% | 1 | 1 | 0% | 1,362 | 1,111 | -18% | 0 | 0 | — |
case-14 | pass→pass | 15,068 | 5,064 | -66% | 1 | 1 | 0% | 2,060 | 1,405 | -32% | 0 | 0 | — |
case-15 | pass→pass | 13,962 | 19,651 | +41% | 1 | 1 | 0% | 2,028 | 2,954 | +46% | 0 | 0 | — |
case-16 | fail→pass | 8,786 | 2,155 | -75% | 1 | 1 | 0% | 1,279 | 929 | -27% | 0 | 0 | — |
case-17 | pass→pass | 19,765 | 12,672 | -36% | 1 | 1 | 0% | 3,109 | 2,362 | -24% | 0 | 0 | — |
case-18 | pass→pass | 6,656 | 6,658 | +0% | 1 | 1 | 0% | 921 | 1,610 | +75% | 0 | 0 | — |
case-19 | pass→pass | 23,223 | 37,699 | +62% | 1 | 1 | 0% | 3,627 | 6,287 | +73% | 0 | 0 | — |
case-20 | pass→pass | 19,104 | 24,217 | +27% | 1 | 1 | 0% | 2,735 | 4,133 | +51% | 0 | 0 | — |
case-21 | pass→fail | 6,912 | 15,920 | +130% | 1 | 1 | 0% | 1,471 | 3,725 | +153% | 0 | 0 | — |
case-22 | pass→pass | 13,704 | 11,640 | -15% | 1 | 1 | 0% | 2,090 | 2,530 | +21% | 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 20 counted toward the lift figure. The other 2 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 +9 percentage points is the difference between those two pass rates over the 20 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.