Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Rotate through reviewer/practitioner/theorist/time-machine/novice perspectives systematically. Ensures comprehensive viewpoint coverage.
.claude/skills/yogsoth-ai-creative-ideation-perspective-rotation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 88% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 138% | 0% |
Rotate through reviewer/practitioner/theorist/time-machine/novice perspectives systematically.
Adopt hostile reviewer stance. Find fatal flaws, logical gaps, missing evidence, and unstated assumptions. Use reviewer2-hat SOP.
Switch to engineer perspective. Assess buildability, cost, timeline, technical debt, and integration challenges. Use practitioner-hat SOP.
Adopt theorist role. Assess formal foundations, mathematical rigor, theoretical completeness, and formalization opportunities. Use theorist-hat SOP.
Project to multiple time horizons. How does this look from 5yr/50yr/500yr future? What's obsolete, what endures? Use time-machine SOP.
Become deliberate novice. Question every "obvious" assumption. Ask "why?" repeatedly. Find hidden complexity masquerading as simplicity. Use novice-perspective SOP.
Combine all perspective outputs into integrated multi-perspective assessment. Identify convergent insights and divergent tensions. Use perspective-synthesis SOP.
| Metric | Floor | |--------|-------| | Perspectives applied | ≥5 | | Unique insights per perspective | ≥3 | | Cross-perspective convergences | ≥2 | | Actionable improvements identified | ≥5 |
| SOP | Role | |-----|------| | reviewer2-hat | Stage 1 — hostile reviewer perspective | | practitioner-hat | Stage 2 — engineer perspective | | theorist-hat | Stage 3 — theorist perspective | | time-machine | Stage 4 — temporal projection | | novice-perspective | Stage 5 — novice questioning | | perspective-synthesis | Stage 6 — synthesize all outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | novice-perspective | Novice perspective — question the 'obvious' by adopting deliberate ignorance to reveal hidden complexity. | | perspective-synthesis | Synthesize all perspective outputs into a structured multi-perspective idea report. | | practitioner-hat | Engineer perspective — assess buildability, cost, timeline, and integration challenges. | | reviewer2-hat | Hostile reviewer perspective — find fatal flaws, logical gaps, and missing evidence in a solution. | | theorist-hat | Theorist perspective — assess theoretical foundations, formal rigor, and formalization opportunities. | | time-machine | Temporal projection — view a solution from future/past time horizons to generate temporally-informed insights. |
<!-- 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-13 | pass→pass | 17,013 | 24,241 | +42% | 1 | 1 | 0% | 2,496 | 4,125 | +65% | 0 | 0 | — |
case-01 | fail→pass | 25,264 | 24,930 | -1% | 1 | 1 | 0% | 4,079 | 4,576 | +12% | 0 | 0 | — |
case-02 | fail→pass | 24,914 | 29,200 | +17% | 1 | 1 | 0% | 3,955 | 5,287 | +34% | 0 | 0 | — |
case-03 | fail→fail | 23,991 | 26,146 | +9% | 1 | 1 | 0% | 3,663 | 4,431 | +21% | 0 | 0 | — |
case-04 | fail→fail | 28,849 | 34,975 | +21% | 1 | 1 | 0% | 5,318 | 5,869 | +10% | 0 | 0 | — |
case-05 | fail→fail | 22,322 | 31,267 | +40% | 1 | 1 | 0% | 3,058 | 5,229 | +71% | 0 | 0 | — |
case-06 | fail→fail | 16,742 | 26,174 | +56% | 1 | 1 | 0% | 2,618 | 4,518 | +73% | 0 | 0 | — |
case-07 | pass→fail | 26,750 | 35,704 | +33% | 1 | 1 | 0% | 4,282 | 4,406 | +3% | 0 | 0 | — |
case-08 | fail→fail | 26,206 | 28,171 | +7% | 1 | 1 | 0% | 3,848 | 5,087 | +32% | 0 | 0 | — |
case-09 | pass→fail | 17,749 | 27,453 | +55% | 1 | 1 | 0% | 2,689 | 4,654 | +73% | 0 | 0 | — |
case-10 | fail→pass | 25,923 | 40,316 | +56% | 1 | 1 | 0% | 3,498 | 6,589 | +88% | 0 | 0 | — |
case-11 | fail→pass | 36,014 | 40,178 | +12% | 1 | 1 | 0% | 4,006 | 6,489 | +62% | 0 | 0 | — |
case-12 | fail→fail | 27,982 | 32,909 | +18% | 1 | 1 | 0% | 4,096 | 5,397 | +32% | 0 | 0 | — |
case-14 | fail→fail | 25,446 | 25,234 | -1% | 1 | 1 | 0% | 3,694 | 4,252 | +15% | 0 | 0 | — |
case-15 | fail→fail | 25,232 | 37,418 | +48% | 1 | 1 | 0% | 3,624 | 6,385 | +76% | 0 | 0 | — |
case-16 | fail→fail | 7,656 | 11,777 | +54% | 1 | 1 | 0% | 1,093 | 2,254 | +106% | 0 | 0 | — |
case-17 | fail→fail | 78,039 | 27,047 | -65% | 1 | 1 | 0% | 3,589 | 4,604 | +28% | 0 | 0 | — |
case-18 | fail→fail | 9,565 | 69,375 | +625% | 1 | 1 | 0% | 1,446 | 5,207 | +260% | 0 | 0 | — |
case-19 | fail→pass | 15,877 | 48,763 | +207% | 1 | 1 | 0% | 2,274 | 5,421 | +138% | 0 | 0 | — |
case-20 | fail→fail | 8,278 | 13,138 | +59% | 1 | 1 | 0% | 962 | 1,843 | +92% | 0 | 0 | — |
case-21 | pass→pass | 13,175 | 17,569 | +33% | 1 | 1 | 0% | 2,598 | 4,505 | +73% | 0 | 0 | — |
case-22 | pass→fail | 36,145 | 23,988 | -34% | 1 | 1 | 0% | 3,642 | 5,122 | +41% | 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. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 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.