Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Identify dominant paradigms constraining the field and use de Bono lateral thinking provocations to escape them.
.claude/skills/yogsoth-ai-dominant-idea-escape/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 71% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 60% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 160% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 116% | 0% |
Break free from paradigm lock-in through lateral thinking.
| Base SOP | Target | ±10% Range | |----------|--------|------------| | web-search | 30 | 27–33 | | web-research | 10 | 9–11 | | paper-overview | 30 | 27–33 | | paper-search | 20 | 18–22 | | paper-research | 10 | 9–11 |
<HARD-GATE>
| SOP | Done | Target | % |
|-----|------|--------|---|
| web-search | ? | 30 | ? |
| web-research | ? | 10 | ? |
| paper-overview | ? | 30 | ? |
| paper-search | ? | 20 | ? |
| paper-research | ? | 10 | ? |
Budget Gate: OPEN/CLOSED (>=80% required to exit)
</HARD-GATE>Import: web-search, web-research, paper-overview, paper-search, paper-research Subagent: dominant-idea-identification, provocation-generation, consequence-following
Identify the dominant paradigm/assumption constraining the field, generate de Bono provocations (escape, reversal, exaggeration, distortion), follow consequences of each provocation to extract viable new framings.
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | lateral-escape | de Bono lateral escape sequence — identify dominant idea, generate provocations (escape/reversal/exaggeration/distortion), follow consequences to extract new framings. Breaks paradigm lock-in. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | consequence-following | Follow a provocation's logical consequences step by step to extract viable insights and new research directions. | | deep-insight-provocation-generation | Generate de Bono lateral thinking provocations to challenge dominant ideas using escape, reversal, exaggeration, and distortion. | | dominant-idea-identification | Identify dominant paradigms and assumptions constraining thinking in a research field. |
<!-- 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 | 22,281 | 12,478 | -44% | 1 | 1 | 0% | 3,237 | 1,764 | -46% | 0 | 0 | — |
case-02 | fail→fail | 20,856 | 32,999 | +58% | 1 | 1 | 0% | 3,038 | 6,774 | +123% | 0 | 0 | — |
case-03 | fail→fail | 28,235 | 39,163 | +39% | 1 | 1 | 0% | 4,102 | 6,764 | +65% | 0 | 0 | — |
case-04 | pass→fail | 23,950 | 44,863 | +87% | 1 | 1 | 0% | 3,843 | 6,741 | +75% | 0 | 0 | — |
case-05 | pass→fail | 23,283 | 6,413 | -72% | 1 | 1 | 0% | 3,774 | 1,524 | -60% | 0 | 0 | — |
case-06 | pass→fail | 19,105 | 32,337 | +69% | 1 | 1 | 0% | 3,019 | 5,930 | +96% | 0 | 0 | — |
case-07 | fail→pass | 27,676 | 17,868 | -35% | 1 | 1 | 0% | 4,136 | 1,638 | -60% | 0 | 0 | — |
case-08 | fail→fail | 18,394 | 10,292 | -44% | 1 | 1 | 0% | 2,686 | 1,360 | -49% | 0 | 0 | — |
case-09 | fail→pass | 25,727 | 37,372 | +45% | 1 | 1 | 0% | 3,944 | 6,737 | +71% | 0 | 0 | — |
case-10 | fail→fail | 23,676 | 6,494 | -73% | 1 | 1 | 0% | 3,511 | 1,626 | -54% | 0 | 0 | — |
case-11 | fail→fail | 22,302 | 5,354 | -76% | 1 | 1 | 0% | 3,329 | 1,388 | -58% | 0 | 0 | — |
case-12 | fail→fail | 20,830 | 17,355 | -17% | 1 | 1 | 0% | 1,764 | 1,472 | -17% | 0 | 0 | — |
case-13 | fail→pass | 29,799 | 39,028 | +31% | 1 | 1 | 0% | 4,204 | 6,734 | +60% | 0 | 0 | — |
case-14 | fail→pass | 18,393 | 36,921 | +101% | 1 | 1 | 0% | 2,596 | 6,737 | +160% | 0 | 0 | — |
case-15 | fail→fail | 15,913 | 5,275 | -67% | 1 | 1 | 0% | 2,414 | 1,290 | -47% | 0 | 0 | — |
case-16 | fail→fail | 19,924 | 43,096 | +116% | 1 | 1 | 0% | 2,952 | 6,735 | +128% | 0 | 0 | — |
case-17 | fail→pass | 22,152 | 39,236 | +77% | 1 | 1 | 0% | 3,123 | 6,738 | +116% | 0 | 0 | — |
case-18 | fail→pass | 14,700 | 32,669 | +122% | 1 | 1 | 0% | 2,253 | 5,494 | +144% | 0 | 0 | — |
case-19 | fail→pass | 18,160 | 6,571 | -64% | 1 | 1 | 0% | 2,564 | 1,478 | -42% | 0 | 0 | — |
case-20 | fail→pass | 19,039 | 39,066 | +105% | 1 | 1 | 0% | 2,730 | 6,731 | +147% | 0 | 0 | — |
case-21 | fail→pass | 22,902 | 39,485 | +72% | 1 | 1 | 0% | 3,441 | 6,728 | +96% | 0 | 0 | — |
case-22 | fail→fail | 27,624 | 14,496 | -48% | 1 | 1 | 0% | 3,234 | 2,069 | -36% | 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 19 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 +27 percentage points is the difference between those two pass rates over the 19 comparable cases. 4 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.