Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Systematically identify all assumptions in a method/model — structural, parametric, distributional, and scope assumptions.
.claude/skills/yogsoth-ai-deep-insight-assumption-enumeration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✓→✗ | ▼ Worse | 11% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 67% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 31% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | -56% | 0% |
| case-05 | ✗→✗ | ＝ Same ✗ | 2% | 0% |
Exhaustively list all assumptions in a method.
Subagent — spawned via subagent-spawning/spawn-agent.
One unit = one assumption enumeration pass.
<!-- 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 | 11,366 | 4,469 | -61% | 1 | 1 | 0% | 1,686 | 739 | -56% | 0 | 0 | — |
case-02 | pass→fail | 8,929 | 9,920 | +11% | 1 | 1 | 0% | 1,702 | 1,886 | +11% | 0 | 0 | — |
case-03 | pass→pass | 17,123 | 22,209 | +30% | 1 | 1 | 0% | 3,315 | 4,346 | +31% | 0 | 0 | — |
case-04 | pass→fail | 16,383 | 30,124 | +84% | 1 | 1 | 0% | 3,200 | 5,351 | +67% | 0 | 0 | — |
case-05 | fail→fail | 23,637 | 22,480 | -5% | 1 | 1 | 0% | 3,469 | 3,552 | +2% | 0 | 0 | — |
case-06 | fail→fail | 26,656 | 30,403 | +14% | 1 | 1 | 0% | 3,726 | 4,575 | +23% | 0 | 0 | — |
case-07 | fail→fail | 24,273 | 22,426 | -8% | 1 | 1 | 0% | 3,776 | 3,559 | -6% | 0 | 0 | — |
case-08 | fail→fail | 33,917 | 34,007 | +0% | 1 | 1 | 0% | 5,824 | 6,002 | +3% | 0 | 0 | — |
case-09 | fail→fail | 22,864 | 34,220 | +50% | 1 | 1 | 0% | 3,667 | 5,394 | +47% | 0 | 0 | — |
case-10 | fail→fail | 23,075 | 17,669 | -23% | 1 | 1 | 0% | 3,384 | 2,594 | -23% | 0 | 0 | — |
case-11 | fail→fail | 22,543 | 24,942 | +11% | 1 | 1 | 0% | 3,195 | 3,860 | +21% | 0 | 0 | — |
case-12 | fail→fail | 23,037 | 40,850 | +77% | 1 | 1 | 0% | 3,483 | 6,311 | +81% | 0 | 0 | — |
case-13 | fail→fail | 28,892 | 26,096 | -10% | 1 | 1 | 0% | 3,854 | 4,029 | +5% | 0 | 0 | — |
case-14 | fail→fail | 17,347 | 15,961 | -8% | 1 | 1 | 0% | 2,547 | 2,584 | +1% | 0 | 0 | — |
case-15 | fail→fail | 23,917 | 22,443 | -6% | 1 | 1 | 0% | 3,553 | 3,546 | -0% | 0 | 0 | — |
case-16 | fail→fail | 20,029 | 18,997 | -5% | 1 | 1 | 0% | 3,296 | 3,057 | -7% | 0 | 0 | — |
case-17 | fail→fail | 23,642 | 26,007 | +10% | 1 | 1 | 0% | 3,590 | 4,064 | +13% | 0 | 0 | — |
case-18 | fail→fail | 35,422 | 24,243 | -32% | 1 | 1 | 0% | 5,155 | 3,798 | -26% | 0 | 0 | — |
case-19 | fail→fail | 21,655 | 19,639 | -9% | 1 | 1 | 0% | 3,256 | 3,043 | -7% | 0 | 0 | — |
case-20 | fail→fail | 18,584 | 25,068 | +35% | 1 | 1 | 0% | 2,889 | 4,061 | +41% | 0 | 0 | — |
case-21 | fail→fail | 22,095 | 18,179 | -18% | 1 | 1 | 0% | 3,344 | 2,755 | -18% | 0 | 0 | — |
case-22 | fail→fail | 42,608 | 23,466 | -45% | 1 | 1 | 0% | 3,029 | 3,663 | +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. The headline lift of -50 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Other measured skills in the registry, with their headline benchmark lift.