Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Identify and suspend fundamental assumptions via de Bono PO. Systematically negate axioms to reveal hidden solution spaces.
.claude/skills/yogsoth-ai-axiom-negation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 36% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 22% | 0% |
Identify and suspend fundamental assumptions via de Bono PO.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 20 | 0 | 0% | | web-research | 5 | 0 | 0% | | paper-overview | 20 | 0 | 0% | | paper-search | 12 | 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 | |--------|------| | provocation-generation | Generate PO provocations from negated axioms | | assumption-enumeration | Surface assumptions to negate |
| SOP | Role | |-----|------| | assumption-perturbation | Perturb each axiom and observe consequences | | reversal-generation | Generate formal negations of axioms | | constructive-rebellion | Build alternatives from negated axioms | | destruction-synthesis | Synthesize negation outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | creative-ideation-assumption-enumeration | Surface, perturb, and prioritize assumptions by disruption potential. Orchestrates assumption surfacing → perturbation → sacred cow identification → prioritization. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | constructive-rebellion | Build constructive alternatives from destructive negation. Transform violated assumptions into viable innovation directions. | | creative-ideation-assumption-perturbation | Perturb each assumption, observe system response. Systematic stress-testing of assumptions to reveal fragility and opportunity. | | destruction-synthesis | Synthesize all assumption destruction outputs into structured destructive innovation report. | | reversal-generation | Systematically reverse positive statements to generate creative inversions. Produces reversed statements with initial associations. |
<!-- 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→pass | 14,372 | 7,323 | -49% | 1 | 1 | 0% | 2,187 | 1,907 | -13% | 0 | 0 | — |
case-02 | fail→pass | 10,695 | 9,066 | -15% | 1 | 1 | 0% | 1,658 | 2,099 | +27% | 0 | 0 | — |
case-03 | fail→pass | 11,425 | 10,236 | -10% | 1 | 1 | 0% | 1,690 | 2,299 | +36% | 0 | 0 | — |
case-04 | pass→pass | 5,842 | 12,109 | +107% | 1 | 1 | 0% | 1,046 | 2,513 | +140% | 0 | 0 | — |
case-05 | pass→pass | 12,410 | 12,958 | +4% | 1 | 1 | 0% | 1,917 | 2,427 | +27% | 0 | 0 | — |
case-06 | pass→pass | 9,167 | 4,555 | -50% | 1 | 1 | 0% | 1,404 | 1,408 | +0% | 0 | 0 | — |
case-07 | pass→pass | 13,172 | 13,484 | +2% | 1 | 1 | 0% | 2,058 | 2,681 | +30% | 0 | 0 | — |
case-08 | pass→pass | 19,212 | 19,544 | +2% | 1 | 1 | 0% | 2,914 | 3,702 | +27% | 0 | 0 | — |
case-09 | fail→fail | 17,201 | 4,717 | -73% | 1 | 1 | 0% | 2,698 | 1,308 | -52% | 0 | 0 | — |
case-10 | fail→pass | 21,962 | 6,962 | -68% | 1 | 1 | 0% | 1,252 | 1,716 | +37% | 0 | 0 | — |
case-11 | fail→pass | 12,855 | 11,114 | -14% | 1 | 1 | 0% | 1,956 | 2,385 | +22% | 0 | 0 | — |
case-12 | pass→pass | 14,646 | 16,192 | +11% | 1 | 1 | 0% | 2,187 | 3,025 | +38% | 0 | 0 | — |
case-13 | fail→pass | 13,713 | 4,219 | -69% | 1 | 1 | 0% | 2,100 | 1,301 | -38% | 0 | 0 | — |
case-14 | fail→pass | 10,352 | 1,581 | -85% | 1 | 1 | 0% | 1,702 | 868 | -49% | 0 | 0 | — |
case-15 | fail→pass | 11,013 | 1,915 | -83% | 1 | 1 | 0% | 1,766 | 911 | -48% | 0 | 0 | — |
case-16 | fail→pass | 9,406 | 2,159 | -77% | 1 | 1 | 0% | 1,401 | 969 | -31% | 0 | 0 | — |
case-17 | fail→pass | 7,732 | 1,867 | -76% | 1 | 1 | 0% | 1,174 | 898 | -24% | 0 | 0 | — |
case-18 | fail→pass | 17,710 | 2,052 | -88% | 1 | 1 | 0% | 783 | 891 | +14% | 0 | 0 | — |
case-19 | pass→pass | 10,479 | 13,181 | +26% | 1 | 1 | 0% | 1,532 | 2,656 | +73% | 0 | 0 | — |
case-20 | pass→pass | 8,553 | 11,659 | +36% | 1 | 1 | 0% | 1,486 | 2,452 | +65% | 0 | 0 | — |
case-21 | pass→pass | 9,419 | 21,118 | +124% | 1 | 1 | 0% | 1,455 | 3,693 | +154% | 0 | 0 | — |
case-22 | pass→pass | 19,109 | 35,059 | +83% | 1 | 1 | 0% | 2,886 | 5,567 | +93% | 0 | 0 | — |
case-23 | fail→pass | 10,306 | 4,698 | -54% | 1 | 1 | 0% | 1,572 | 1,364 | -13% | 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, and 21 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 +52 percentage points is the difference between those two pass rates over the 21 comparable cases.
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.