Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Random word/concept as thinking entry point (de Bono Random Entry)
.claude/skills/yogsoth-ai-random-entry/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 156% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -41% | 0% |
Use a random word or concept as an unrelated entry point to force new thinking connections (de Bono Random Entry technique).
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 15 | 0 | 0% | | web-research | 5 | 0 | 0% | | paper-overview | 15 | 0 | 0% | | paper-search | 10 | 0 | 0% | | paper-research | 3 | 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 provocations from random word connections (shared) |
| SOP | Role | |-----|------| | movement-operation | Extract directions from random-word connections | | stepping-stone | Bridge from random associations to practical ideas | | alternatives-generation | Generate alternatives from random entry connections | | lateral-synthesis | Synthesize random entry outputs |
<!-- BEGIN available-tables (generated) -->
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. | | lateral-synthesis | Synthesize all lateral thinking intermediate outputs into a structured idea report. | | stepping-stone | Use impractical ideas as stepping stones to reach practical solutions (de Bono Stepping Stone technique). |
<!-- 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 | 16,866 | 20,052 | +19% | 1 | 1 | 0% | 1,822 | 2,992 | +64% | 0 | 0 | — |
case-02 | pass→pass | 16,937 | 25,380 | +50% | 1 | 1 | 0% | 1,821 | 3,797 | +109% | 0 | 0 | — |
case-03 | pass→pass | 14,214 | 7,107 | -50% | 1 | 1 | 0% | 1,125 | 1,516 | +35% | 0 | 0 | — |
case-04 | pass→pass | 18,794 | 28,383 | +51% | 1 | 1 | 0% | 2,171 | 4,213 | +94% | 0 | 0 | — |
case-05 | pass→pass | 25,451 | 25,998 | +2% | 1 | 1 | 0% | 2,570 | 2,951 | +15% | 0 | 0 | — |
case-06 | pass→fail | 23,505 | 8,458 | -64% | 1 | 1 | 0% | 2,990 | 931 | -69% | 0 | 0 | — |
case-07 | fail→pass | 40,113 | 8,288 | -79% | 1 | 1 | 0% | 1,063 | 1,689 | +59% | 0 | 0 | — |
case-08 | pass→pass | 9,649 | 7,859 | -19% | 1 | 1 | 0% | 637 | 951 | +49% | 0 | 0 | — |
case-09 | fail→pass | 10,722 | 7,450 | -31% | 1 | 1 | 0% | 328 | 841 | +156% | 0 | 0 | — |
case-10 | pass→pass | 15,613 | 7,354 | -53% | 1 | 1 | 0% | 1,465 | 859 | -41% | 0 | 0 | — |
case-11 | fail→fail | 17,534 | 8,799 | -50% | 1 | 1 | 0% | 1,587 | 1,029 | -35% | 0 | 0 | — |
case-12 | fail→pass | 7,037 | 8,191 | +16% | 1 | 1 | 0% | 961 | 746 | -22% | 0 | 0 | — |
case-13 | fail→pass | 8,889 | 9,141 | +3% | 1 | 1 | 0% | 1,267 | 753 | -41% | 0 | 0 | — |
case-14 | fail→pass | 6,618 | 1,962 | -70% | 1 | 1 | 0% | 627 | 764 | +22% | 0 | 0 | — |
case-15 | pass→pass | 15,412 | 9,405 | -39% | 1 | 1 | 0% | 1,699 | 1,034 | -39% | 0 | 0 | — |
case-16 | pass→pass | 18,064 | 10,191 | -44% | 1 | 1 | 0% | 2,046 | 1,287 | -37% | 0 | 0 | — |
case-17 | fail→pass | 12,673 | 8,328 | -34% | 1 | 1 | 0% | 1,850 | 1,065 | -42% | 0 | 0 | — |
case-18 | pass→pass | 27,802 | 6,236 | -78% | 1 | 1 | 0% | 2,763 | 953 | -66% | 0 | 0 | — |
case-19 | fail→fail | 19,606 | 18,304 | -7% | 1 | 1 | 0% | 1,970 | 2,314 | +17% | 0 | 0 | — |
case-20 | pass→fail | 21,018 | 48,012 | +128% | 1 | 1 | 0% | 3,570 | 7,087 | +99% | 0 | 0 | — |
case-21 | pass→fail | 22,256 | 43,818 | +97% | 1 | 1 | 0% | 2,518 | 5,458 | +117% | 0 | 0 | — |
case-22 | pass→pass | 17,727 | 32,958 | +86% | 1 | 1 | 0% | 2,600 | 5,325 | +105% | 0 | 0 | — |
case-23 | pass→fail | 20,630 | 60,387 | +193% | 1 | 1 | 0% | 2,785 | 8,701 | +212% | 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 +11 percentage points is the difference between those two pass rates over the 21 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.