Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expand from purpose to concepts to directions to ideas (de Bono Concept Fan)
.claude/skills/yogsoth-ai-concept-fan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-03 | ✓→✗ | ▼ Worse | -46% | 0% |
Expand thinking from purpose through concepts to directions to ideas using de Bono's Concept Fan technique. Move between levels of abstraction to find new approaches.
| 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 | Build concept levels from purpose through concepts to ideas |
| SOP | Role | |-----|------| | concept-fan-expansion | Expand fan from purpose → concepts → directions → ideas | | escape-technique | Escape dominant concept to find alternative concepts | | fractionation | Split broad concepts into finer units | | alternatives-generation | Generate alternative ideas at each level | | lateral-synthesis | Synthesize concept fan 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. | | concept-fan-expansion | Expand concept fan from purpose through concepts to directions to ideas (de Bono Concept Fan). | | escape-technique | Identify dominant thinking pattern and escape it via deliberate pattern-breaking. | | fractionation | Split concepts into smaller units and recombine them differently to produce novel structures. | | 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 | pass→pass | 11,175 | 25,676 | +130% | 1 | 1 | 0% | 2,438 | 6,188 | +154% | 0 | 0 | — |
case-02 | pass→pass | 15,148 | 28,339 | +87% | 1 | 1 | 0% | 2,493 | 4,976 | +100% | 0 | 0 | — |
case-03 | pass→fail | 16,299 | 10,782 | -34% | 1 | 1 | 0% | 2,507 | 1,342 | -46% | 0 | 0 | — |
case-04 | fail→pass | 9,692 | 13,183 | +36% | 1 | 1 | 0% | 1,779 | 2,833 | +59% | 0 | 0 | — |
case-05 | pass→pass | 12,278 | 11,539 | -6% | 1 | 1 | 0% | 1,844 | 2,433 | +32% | 0 | 0 | — |
case-06 | fail→pass | 7,881 | 10,631 | +35% | 1 | 1 | 0% | 1,300 | 2,191 | +69% | 0 | 0 | — |
case-07 | fail→pass | 14,123 | 12,815 | -9% | 1 | 1 | 0% | 2,189 | 1,958 | -11% | 0 | 0 | — |
case-08 | pass→pass | 16,490 | 23,570 | +43% | 1 | 1 | 0% | 2,387 | 4,221 | +77% | 0 | 0 | — |
case-09 | pass→pass | 14,284 | 17,030 | +19% | 1 | 1 | 0% | 2,105 | 3,022 | +44% | 0 | 0 | — |
case-10 | pass→pass | 9,122 | 10,706 | +17% | 1 | 1 | 0% | 1,337 | 2,203 | +65% | 0 | 0 | — |
case-11 | pass→pass | 12,449 | 11,300 | -9% | 1 | 1 | 0% | 1,851 | 2,386 | +29% | 0 | 0 | — |
case-12 | pass→pass | 9,173 | 9,712 | +6% | 1 | 1 | 0% | 1,302 | 1,924 | +48% | 0 | 0 | — |
case-13 | fail→pass | 9,201 | 7,351 | -20% | 1 | 1 | 0% | 1,542 | 1,722 | +12% | 0 | 0 | — |
case-14 | pass→pass | 5,974 | 9,674 | +62% | 1 | 1 | 0% | 966 | 2,039 | +111% | 0 | 0 | — |
case-15 | pass→pass | 12,678 | 14,664 | +16% | 1 | 1 | 0% | 1,910 | 2,600 | +36% | 0 | 0 | — |
case-16 | fail→fail | 6,417 | 6,467 | +1% | 1 | 1 | 0% | 924 | 1,510 | +63% | 0 | 0 | — |
case-17 | pass→pass | 13,123 | 20,622 | +57% | 1 | 1 | 0% | 2,196 | 3,768 | +72% | 0 | 0 | — |
case-18 | pass→pass | 11,580 | 12,347 | +7% | 1 | 1 | 0% | 1,690 | 2,463 | +46% | 0 | 0 | — |
case-19 | pass→pass | 13,148 | 13,606 | +3% | 1 | 1 | 0% | 1,853 | 2,533 | +37% | 0 | 0 | — |
case-20 | fail→fail | 8,868 | 7,853 | -11% | 1 | 1 | 0% | 1,227 | 1,624 | +32% | 0 | 0 | — |
case-21 | pass→pass | 11,772 | 13,057 | +11% | 1 | 1 | 0% | 1,702 | 2,583 | +52% | 0 | 0 | — |
case-22 | pass→pass | 10,973 | 8,320 | -24% | 1 | 1 | 0% | 1,711 | 2,180 | +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. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 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 +14 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is 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.