Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Surface, perturb, and prioritize assumptions by disruption potential. Orchestrates assumption surfacing → perturbation → sacred cow identification → prioritization.
.claude/skills/yogsoth-ai-creative-ideation-assumption-enumeration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 74% | 0% |
Surface, perturb, and prioritize assumptions by disruption potential.
Use assumption-surfacing SOP to enumerate all implicit assumptions in the target. Cover all 8 categories (physical, temporal, spatial, economic, technical, social, logical, paradigmatic).
For each surfaced assumption, use assumption-perturbation SOP to systematically perturb it. Observe what breaks, what new spaces open, and what remains stable.
From the perturbation results, use sacred-cow-identification SOP to flag assumptions that are deeply held but poorly justified — the true sacred cows with highest disruption potential.
Rank all assumptions by disruption potential × challengeability. Select top candidates for downstream negation and inversion work.
| Metric | Floor | |--------|-------| | Assumptions surfaced | ≥8 | | Categories covered | ≥5/8 | | Assumptions perturbed | ≥6 | | High-disruption identified | ≥3 | | Sacred cows flagged | ≥2 |
| SOP | Role | |-----|------| | assumption-surfacing | Stage 1 — enumerate assumptions (shared, existing) | | assumption-perturbation | Stage 2 — perturb and observe | | sacred-cow-identification | Stage 3 — flag unquestioned beliefs | | novelty-scoring | Stage 4 — score disruption potential | | saturation-detection | Pre — check if more surfacing needed |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | creative-ideation-assumption-perturbation | Perturb each assumption, observe system response. Systematic stress-testing of assumptions to reveal fragility and opportunity. | | sacred-cow-identification | Find domain's unquestioned beliefs. Systematic identification of dogma that constrains innovation. |
<!-- 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-16 | pass→pass | 16,294 | 16,462 | +1% | 1 | 1 | 0% | 2,394 | 3,087 | +29% | 0 | 0 | — |
case-09 | fail→pass | 26,381 | 24,222 | -8% | 1 | 1 | 0% | 3,808 | 4,239 | +11% | 0 | 0 | — |
case-02 | fail→pass | 38,534 | 30,288 | -21% | 1 | 1 | 0% | 6,212 | 5,045 | -19% | 0 | 0 | — |
case-01 | pass→pass | 33,669 | 35,411 | +5% | 1 | 1 | 0% | 5,187 | 6,076 | +17% | 0 | 0 | — |
case-03 | fail→pass | 25,462 | 28,360 | +11% | 1 | 1 | 0% | 4,593 | 5,620 | +22% | 0 | 0 | — |
case-04 | pass→pass | 15,110 | 24,753 | +64% | 1 | 1 | 0% | 2,481 | 4,376 | +76% | 0 | 0 | — |
case-05 | pass→fail | 14,673 | 24,152 | +65% | 1 | 1 | 0% | 2,461 | 4,486 | +82% | 0 | 0 | — |
case-06 | pass→fail | 15,464 | 30,672 | +98% | 1 | 1 | 0% | 2,450 | 5,343 | +118% | 0 | 0 | — |
case-07 | fail→pass | 21,397 | 31,162 | +46% | 1 | 1 | 0% | 3,079 | 5,283 | +72% | 0 | 0 | — |
case-08 | fail→pass | 22,563 | 29,472 | +31% | 1 | 1 | 0% | 3,287 | 5,728 | +74% | 0 | 0 | — |
case-10 | pass→pass | 22,643 | 33,139 | +46% | 1 | 1 | 0% | 3,340 | 5,485 | +64% | 0 | 0 | — |
case-11 | fail→pass | 21,855 | 26,482 | +21% | 1 | 1 | 0% | 3,407 | 4,803 | +41% | 0 | 0 | — |
case-12 | fail→pass | 20,924 | 32,464 | +55% | 1 | 1 | 0% | 3,150 | 5,784 | +84% | 0 | 0 | — |
case-13 | pass→pass | 19,188 | 28,902 | +51% | 1 | 1 | 0% | 2,626 | 5,069 | +93% | 0 | 0 | — |
case-14 | pass→pass | 21,468 | 25,563 | +19% | 1 | 1 | 0% | 3,190 | 4,472 | +40% | 0 | 0 | — |
case-15 | fail→pass | 17,810 | 11,095 | -38% | 1 | 1 | 0% | 2,587 | 2,032 | -21% | 0 | 0 | — |
case-17 | fail→pass | 54,629 | 24,101 | -56% | 1 | 1 | 0% | 3,189 | 4,055 | +27% | 0 | 0 | — |
case-18 | fail→pass | 20,731 | 39,701 | +92% | 1 | 1 | 0% | 3,351 | 4,916 | +47% | 0 | 0 | — |
case-19 | fail→pass | 26,042 | 30,485 | +17% | 1 | 1 | 0% | 4,155 | 5,089 | +22% | 0 | 0 | — |
case-20 | pass→pass | 26,122 | 37,305 | +43% | 1 | 1 | 0% | 4,087 | 6,614 | +62% | 0 | 0 | — |
case-21 | pass→pass | 21,698 | 25,790 | +19% | 1 | 1 | 0% | 3,169 | 4,618 | +46% | 0 | 0 | — |
case-22 | pass→pass | 24,593 | 25,234 | +3% | 1 | 1 | 0% | 3,273 | 4,393 | +34% | 0 | 0 | — |
case-23 | fail→pass | 20,721 | 23,112 | +12% | 1 | 1 | 0% | 3,122 | 3,977 | +27% | 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. 23 cases were attempted. The headline lift of +43 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 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.