Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Find direct analogies from nature/tech/society that share structural properties with the problem. Produces analogy list with structural mappings.
.claude/skills/yogsoth-ai-direct-analogy-generation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✓→✓ | ＝ Same ✓ | 40% | 0% |
| case-07 | ✓→✓ | ＝ Same ✓ | 15% | 0% |
| case-08 | ✓→✓ | ＝ Same ✓ | -2% | 0% |
| case-02 | ✗→✗ | ＝ Same ✗ | 26% | 0% |
| case-03 | ✗→✗ | ＝ Same ✗ | 28% | 0% |
Find direct analogies from nature, technology, and society.
Subagent — spawned via subagent-spawning/spawn-agent skill.
Direct analogy generation requires broad cross-domain knowledge search and careful structural mapping. Benefits from dedicated focus on finding non-obvious parallels without premature solution generation.
<!-- 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 | 18,289 | 23,198 | +27% | 1 | 1 | 0% | 3,017 | 3,789 | +26% | 0 | 0 | — |
case-03 | fail→fail | 19,530 | 22,987 | +18% | 1 | 1 | 0% | 3,026 | 3,880 | +28% | 0 | 0 | — |
case-01 | fail→fail | 20,446 | 25,801 | +26% | 1 | 1 | 0% | 2,891 | 4,184 | +45% | 0 | 0 | — |
case-04 | fail→fail | 14,763 | 14,355 | -3% | 1 | 1 | 0% | 2,328 | 2,307 | -1% | 0 | 0 | — |
case-05 | fail→fail | 19,448 | 18,097 | -7% | 1 | 1 | 0% | 3,135 | 2,734 | -13% | 0 | 0 | — |
case-06 | pass→pass | 16,939 | 21,258 | +25% | 1 | 1 | 0% | 3,473 | 4,865 | +40% | 0 | 0 | — |
case-07 | pass→pass | 19,968 | 22,313 | +12% | 1 | 1 | 0% | 3,536 | 4,064 | +15% | 0 | 0 | — |
case-08 | pass→pass | 18,654 | 16,923 | -9% | 1 | 1 | 0% | 2,933 | 2,864 | -2% | 0 | 0 | — |
case-09 | fail→fail | 21,237 | 17,476 | -18% | 1 | 1 | 0% | 3,248 | 2,821 | -13% | 0 | 0 | — |
case-10 | fail→fail | 18,981 | 14,525 | -23% | 1 | 1 | 0% | 2,942 | 2,398 | -18% | 0 | 0 | — |
case-11 | fail→fail | 22,967 | 17,586 | -23% | 1 | 1 | 0% | 3,327 | 2,542 | -24% | 0 | 0 | — |
case-12 | fail→fail | 16,887 | 21,608 | +28% | 1 | 1 | 0% | 2,701 | 3,563 | +32% | 0 | 0 | — |
case-13 | fail→fail | 17,015 | 19,107 | +12% | 1 | 1 | 0% | 2,908 | 3,340 | +15% | 0 | 0 | — |
case-14 | fail→fail | 12,838 | 9,157 | -29% | 1 | 1 | 0% | 2,033 | 1,664 | -18% | 0 | 0 | — |
case-15 | fail→fail | 13,317 | 14,121 | +6% | 1 | 1 | 0% | 2,160 | 2,442 | +13% | 0 | 0 | — |
case-16 | fail→fail | 17,274 | 15,062 | -13% | 1 | 1 | 0% | 2,804 | 2,520 | -10% | 0 | 0 | — |
case-17 | fail→fail | 15,170 | 16,085 | +6% | 1 | 1 | 0% | 2,423 | 2,511 | +4% | 0 | 0 | — |
case-18 | fail→fail | 14,515 | 20,901 | +44% | 1 | 1 | 0% | 2,336 | 3,380 | +45% | 0 | 0 | — |
case-19 | fail→fail | 20,063 | 19,896 | -1% | 1 | 1 | 0% | 3,095 | 3,074 | -1% | 0 | 0 | — |
case-20 | fail→fail | 18,484 | 18,494 | +0% | 1 | 1 | 0% | 2,991 | 3,042 | +2% | 0 | 0 | — |
case-21 | fail→fail | 16,211 | 15,428 | -5% | 1 | 1 | 0% | 2,536 | 2,663 | +5% | 0 | 0 | — |
case-22 | fail→fail | 14,216 | 15,819 | +11% | 1 | 1 | 0% | 2,418 | 2,873 | +19% | 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.
Other measured skills in the registry, with their headline benchmark lift.