Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Assess analogy depth (surface/structural/systemic). Determines whether an analogy warrants transfer investment.
.claude/skills/yogsoth-ai-analogy-quality-assessment/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✓→✓ | ＝ Same ✓ | -26% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 115% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | -14% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | -9% | 0% |
| case-02 | ✗→✗ | ＝ Same ✗ | 3% | 0% |
Assess analogy depth (surface/structural/systemic).
Subagent — spawned via subagent-spawning/spawn-agent skill.
Quality assessment requires rigorous, unbiased evaluation of analogy depth. Benefits from a dedicated evaluator role that is not invested in the analogy's success and can apply strict classification criteria without creative bias.
<!-- 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-01 | fail→fail | 19,878 | 16,043 | -19% | 1 | 1 | 0% | 2,759 | 2,514 | -9% | 0 | 0 | — |
case-02 | fail→fail | 19,435 | 19,331 | -1% | 1 | 1 | 0% | 2,687 | 2,775 | +3% | 0 | 0 | — |
case-03 | fail→fail | 19,658 | 24,820 | +26% | 1 | 1 | 0% | 2,612 | 3,003 | +15% | 0 | 0 | — |
case-04 | pass→pass | 17,240 | 12,240 | -29% | 1 | 1 | 0% | 2,550 | 1,897 | -26% | 0 | 0 | — |
case-05 | pass→pass | 8,199 | 21,556 | +163% | 1 | 1 | 0% | 1,197 | 2,574 | +115% | 0 | 0 | — |
case-06 | pass→pass | 4,208 | 2,756 | -35% | 1 | 1 | 0% | 669 | 578 | -14% | 0 | 0 | — |
case-07 | fail→fail | 18,180 | 18,170 | -0% | 1 | 1 | 0% | 2,534 | 2,642 | +4% | 0 | 0 | — |
case-08 | fail→fail | 15,541 | 24,994 | +61% | 1 | 1 | 0% | 2,332 | 2,657 | +14% | 0 | 0 | — |
case-09 | fail→fail | 17,975 | 18,671 | +4% | 1 | 1 | 0% | 2,643 | 2,846 | +8% | 0 | 0 | — |
case-10 | fail→fail | 18,204 | 18,993 | +4% | 1 | 1 | 0% | 2,541 | 2,889 | +14% | 0 | 0 | — |
case-11 | fail→fail | 15,400 | 21,015 | +36% | 1 | 1 | 0% | 2,219 | 3,156 | +42% | 0 | 0 | — |
case-12 | fail→fail | 15,671 | 23,098 | +47% | 1 | 1 | 0% | 2,425 | 3,216 | +33% | 0 | 0 | — |
case-13 | fail→fail | 15,218 | 15,543 | +2% | 1 | 1 | 0% | 2,168 | 2,452 | +13% | 0 | 0 | — |
case-14 | fail→fail | 17,466 | 25,283 | +45% | 1 | 1 | 0% | 2,517 | 2,875 | +14% | 0 | 0 | — |
case-15 | fail→fail | 15,091 | 20,043 | +33% | 1 | 1 | 0% | 2,261 | 3,187 | +41% | 0 | 0 | — |
case-16 | fail→fail | 16,228 | 24,972 | +54% | 1 | 1 | 0% | 2,279 | 3,890 | +71% | 0 | 0 | — |
case-17 | fail→fail | 16,615 | 18,883 | +14% | 1 | 1 | 0% | 2,277 | 2,772 | +22% | 0 | 0 | — |
case-18 | fail→fail | 15,741 | 23,554 | +50% | 1 | 1 | 0% | 2,698 | 3,578 | +33% | 0 | 0 | — |
case-19 | fail→fail | 17,191 | 16,886 | -2% | 1 | 1 | 0% | 2,474 | 2,604 | +5% | 0 | 0 | — |
case-20 | fail→fail | 17,566 | 13,213 | -25% | 1 | 1 | 0% | 2,515 | 1,912 | -24% | 0 | 0 | — |
case-21 | fail→fail | 16,586 | 14,079 | -15% | 1 | 1 | 0% | 2,489 | 764 | -69% | 0 | 0 | — |
case-22 | fail→fail | 15,886 | 28,964 | +82% | 1 | 1 | 0% | 2,329 | 2,790 | +20% | 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 21 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 0 percentage points is the difference between those two pass rates over the 21 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.