Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Non-threatening 'Why?' questioning of current practices (de Bono Challenge)
.claude/skills/yogsoth-ai-challenge-operation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 80% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 96% | 0% |
Apply de Bono's Challenge technique: non-threatening questioning of why things are done the way they are. Not criticism — genuine curiosity about whether current approaches are the only way.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 20 | 0 | 0% | | web-research | 8 | 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 | |--------|------| | concept-hierarchy | Organize challenged practices into concept levels |
| SOP | Role | |-----|------| | challenge-questioning | Apply non-threatening 'Why?' to current practices | | escape-technique | Escape from dominant patterns revealed by challenge | | alternatives-generation | Generate alternatives to challenged practices | | lateral-synthesis | Synthesize challenge operation outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | concept-hierarchy | Build concept levels from purpose through concepts to ideas, with escape and fractionation at each level. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | alternatives-generation | Generate alternatives for every known approach — ensure no approach goes unchallenged. | | challenge-questioning | Non-threatening 'Why?' questioning of current practices to reveal historical accidents vs. genuine constraints. | | escape-technique | Identify dominant thinking pattern and escape it via deliberate pattern-breaking. | | lateral-synthesis | Synthesize all lateral thinking intermediate outputs into a structured idea report. |
<!-- 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 | 8,254 | 2,032 | -75% | 1 | 1 | 0% | 461 | 886 | +92% | 0 | 0 | — |
case-15 | fail→pass | 11,901 | 6,292 | -47% | 1 | 1 | 0% | 2,015 | 1,565 | -22% | 0 | 0 | — |
case-16 | fail→fail | 16,642 | 28,833 | +73% | 1 | 1 | 0% | 2,685 | 4,661 | +74% | 0 | 0 | — |
case-02 | pass→pass | 13,369 | 11,657 | -13% | 1 | 1 | 0% | 2,067 | 2,444 | +18% | 0 | 0 | — |
case-03 | pass→pass | 12,250 | 10,951 | -11% | 1 | 1 | 0% | 1,942 | 2,381 | +23% | 0 | 0 | — |
case-04 | pass→pass | 9,821 | 14,077 | +43% | 1 | 1 | 0% | 1,539 | 2,813 | +83% | 0 | 0 | — |
case-05 | pass→pass | 12,794 | 18,899 | +48% | 1 | 1 | 0% | 1,879 | 3,485 | +85% | 0 | 0 | — |
case-06 | pass→pass | 14,094 | 10,464 | -26% | 1 | 1 | 0% | 2,173 | 2,167 | -0% | 0 | 0 | — |
case-07 | pass→pass | 14,728 | 15,480 | +5% | 1 | 1 | 0% | 2,356 | 3,103 | +32% | 0 | 0 | — |
case-08 | fail→pass | 15,289 | 2,488 | -84% | 1 | 1 | 0% | 955 | 907 | -5% | 0 | 0 | — |
case-09 | fail→pass | 8,981 | 2,192 | -76% | 1 | 1 | 0% | 458 | 826 | +80% | 0 | 0 | — |
case-10 | fail→pass | 2,881 | 1,767 | -39% | 1 | 1 | 0% | 427 | 836 | +96% | 0 | 0 | — |
case-11 | fail→pass | 3,314 | 1,363 | -59% | 1 | 1 | 0% | 415 | 759 | +83% | 0 | 0 | — |
case-12 | fail→pass | 2,759 | 1,647 | -40% | 1 | 1 | 0% | 336 | 834 | +148% | 0 | 0 | — |
case-13 | fail→pass | 9,086 | 5,327 | -41% | 1 | 1 | 0% | 1,381 | 1,464 | +6% | 0 | 0 | — |
case-14 | fail→pass | 8,373 | 12,975 | +55% | 1 | 1 | 0% | 1,328 | 2,558 | +93% | 0 | 0 | — |
case-17 | pass→fail | 15,238 | 26,983 | +77% | 1 | 1 | 0% | 2,189 | 1,046 | -52% | 0 | 0 | — |
case-18 | pass→pass | 15,162 | 8,519 | -44% | 1 | 1 | 0% | 2,197 | 1,950 | -11% | 0 | 0 | — |
case-19 | fail→pass | 14,316 | 3,043 | -79% | 1 | 1 | 0% | 2,238 | 1,092 | -51% | 0 | 0 | — |
case-20 | pass→pass | 7,510 | 14,419 | +92% | 1 | 1 | 0% | 1,135 | 2,683 | +136% | 0 | 0 | — |
case-21 | pass→fail | 12,580 | 17,917 | +42% | 1 | 1 | 0% | 1,677 | 2,221 | +32% | 0 | 0 | — |
case-22 | pass→pass | 10,199 | 30,590 | +200% | 1 | 1 | 0% | 1,732 | 5,529 | +219% | 0 | 0 | — |
case-23 | pass→pass | 14,958 | 29,528 | +97% | 1 | 1 | 0% | 2,867 | 6,034 | +110% | 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 20 counted toward the lift figure. The other 3 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 +35 percentage points is the difference between those two pass rates over the 20 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.