Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Perspective Forcing Campaign — discover hidden solutions by systematically switching viewpoints via roles, six hats, temporal projection, and constraint injection
.claude/skills/yogsoth-ai-perspective-forcing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 58% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 266% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 953% | 0% |
Discover hidden solutions by systematically switching viewpoints via roles, six hats, temporal projection, and constraint injection.
| Strategy | Signal Keywords | |----------|----------------| | role-based-ideation | role-play, reviewer, practitioner, theorist, novice, competitor, persona | | six-hats-rotation | six hats, de Bono, white hat, red hat, black hat, yellow hat, green hat, blue hat | | temporal-projection | future, past, 5 years, 50 years, backcast, time horizon, temporal | | stakeholder-simulation | stakeholder, user, engineer, investor, regulator, society, multi-perspective | | constraint-driven-ideation | constraint, extreme limitation, force innovation, impossible, restriction |
| Strategy | Description | |----------|-------------| | role-based-ideation | Role-play as reviewer/practitioner/theorist/novice/competitor | | six-hats-rotation | Complete Six Hats rotation (White→Red→Black→Yellow→Green→Blue) | | temporal-projection | View problem from 5yr/50yr/500yr future, backcast | | stakeholder-simulation | Simulate user/engineer/investor/regulator/society perspectives | | constraint-driven-ideation | Inject extreme constraints to force innovation |
| Tactic | Description | |--------|-------------| | evaluation-filtering | Filter and rank ideas by novelty and feasibility (shared) | | constraint-protocol | Inject constraints → force response → extract transferable principles | | perspective-rotation | Rotate through reviewer/practitioner/theorist/time-machine/novice perspectives |
| SOP | Description | |-----|-------------| | reviewer2-hat | Hostile reviewer perspective: find fatal flaws | | practitioner-hat | Engineer perspective: assess buildability | | theorist-hat | Theorist perspective: assess theoretical foundations | | time-machine | Temporal projection: view from future/past | | novice-perspective | Novice perspective: question the 'obvious' | | competitor-simulation | Competitor perspective: how to defeat this solution | | constraint-response | Generate creative solutions under extreme constraints | | perspective-synthesis | Synthesize all perspective outputs |
| Strategy | web-search | web-research | paper-overview | paper-search | paper-research | |----------|-----------|-------------|---------------|-------------|---------------| | role-based-ideation | 20 | 5 | 20 | 12 | 5 | | six-hats-rotation | 15 | 5 | 15 | 10 | 3 | | temporal-projection | 20 | 8 | 20 | 12 | 5 | | stakeholder-simulation | 25 | 10 | 20 | 12 | 5 | | constraint-driven-ideation | 20 | 8 | 20 | 12 | 5 |
| Tool | Server | Purpose | |------|--------|---------| | brave_web_search | brave-search | General web search for perspective methods | | brave_llm_context | brave-search | Deep content extraction from web pages | | apify/rag-web-browser | apify | Full page scraping for detailed content | | get_paper_content | alphaxiv | Read academic paper content | | discover_papers | alphaxiv | Find relevant research papers | | relevanceSearch | semantic-scholar | Search academic literature | | paper | semantic-scholar | Get paper details | | citations | semantic-scholar | Trace citation networks |
| Tactic | Role | |--------|------| | evaluation-filtering | Filter and rank ideas by novelty and feasibility (shared) | | constraint-protocol | Inject constraints → force response → extract transferable principles | | perspective-rotation | Rotate through multiple expert/temporal/novice perspectives |
| SOP | Role | |-----|------| | reviewer2-hat | Hostile reviewer: find fatal flaws | | practitioner-hat | Engineer: assess buildability | | theorist-hat | Theorist: assess theoretical foundations | | time-machine | Temporal projection from future/past | | novice-perspective | Novice: question the obvious | | competitor-simulation | Competitor: how to defeat this solution | | constraint-response | Generate solutions under extreme constraints | | perspective-synthesis | Synthesize all perspective outputs into report |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | constraint-driven-ideation | Inject extreme constraints to force innovation — impossibility breeds creativity. | | role-based-ideation | Role-play as reviewer/practitioner/theorist/novice/competitor to generate diverse perspectives on a solution. | | six-hats-rotation | Complete Six Hats rotation (White→Red→Black→Yellow→Green→Blue) to force systematic perspective diversity. | | stakeholder-simulation | Simulate user/engineer/investor/regulator/society perspectives to surface hidden requirements and opportunities. | | temporal-projection | View problem from 5yr/50yr/500yr future, backcast to generate temporally-informed creative solutions. |
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | constraint-protocol | Inject constraints → force creative response → extract transferable principles. Orchestrates constraint injection, response generation, and principle extraction. | | creative-ideation-perspective-rotation | Rotate through reviewer/practitioner/theorist/time-machine/novice perspectives systematically. Ensures comprehensive viewpoint coverage. | | creative-ideation-provocation-generation | Generate PO provocations and extract constructive movement. Orchestrates assumption surfacing → provocation creation → movement extraction → idea formation. | | evaluation-filtering | Multi-dimensional evaluation and tiered filtering of generated ideas. Orchestrates novelty assessment → feasibility check → ranking → selection. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | competitor-simulation | Competitor perspective — design strategies to defeat this solution, then use attack vectors to improve it. | | constraint-injection | Inject artificial constraints to force creative divergence. Generates and applies constraints (resource, time, material, audience, scale) to existing ideas to produce variants. | | constraint-response | Generate creative solutions under extreme constraints — no "impossible" allowed, find a way. | | context-checkpoint | Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. | | context-init | Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. | | creative-ideation-assumption-surfacing | Enumerate implicit assumptions in a problem statement or existing solution. Produces categorized assumption inventory (physical, social, temporal, economic, technical). | | creative-ideation-novelty-scoring | Score ideas on novelty dimensions — structural distance from known solutions, conceptual surprise, domain-crossing depth. Produces ranked novelty assessment. | | creative-ideation-saturation-detection | Determine when additional ideation yields diminishing returns. Analyzes latest idea batch against existing corpus to judge continue/near-saturation/saturated. | | idea-synthesis | Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions. | | 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. | | po-provocation | Generate PO (Provocative Operation) statements per de Bono's lateral thinking. Creates deliberately illogical provocations to escape dominant thinking patterns. | | 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-01 | fail→fail | 54,564 | 39,973 | -27% | 1 | 1 | 0% | 6,135 | 2,653 | -57% | 0 | 0 | — |
case-02 | fail→fail | 20,123 | 72,460 | +260% | 1 | 1 | 0% | 2,264 | 2,689 | +19% | 0 | 0 | — |
case-03 | fail→pass | 20,487 | 58,868 | +187% | 1 | 1 | 0% | 2,386 | 2,970 | +24% | 0 | 0 | — |
case-04 | fail→pass | 35,443 | 62,954 | +78% | 1 | 1 | 0% | 4,176 | 6,604 | +58% | 0 | 0 | — |
case-10 | fail→fail | 21,817 | 42,621 | +95% | 1 | 1 | 0% | 3,144 | 6,824 | +117% | 0 | 0 | — |
case-05 | fail→fail | 26,482 | 18,903 | -29% | 1 | 1 | 0% | 3,320 | 2,952 | -11% | 0 | 0 | — |
case-06 | fail→fail | 12,996 | 15,651 | +20% | 1 | 1 | 0% | 1,119 | 3,672 | +228% | 0 | 0 | — |
case-07 | fail→pass | 48,098 | 51,643 | +7% | 1 | 1 | 0% | 8,231 | 9,759 | +19% | 0 | 0 | — |
case-08 | fail→fail | 29,247 | 24,871 | -15% | 1 | 1 | 0% | 2,015 | 3,958 | +96% | 0 | 0 | — |
case-09 | fail→fail | 17,914 | 15,207 | -15% | 1 | 1 | 0% | 2,563 | 2,758 | +8% | 0 | 0 | — |
case-11 | fail→fail | 28,900 | 46,682 | +62% | 1 | 1 | 0% | 3,807 | 8,894 | +134% | 0 | 0 | — |
case-12 | fail→fail | 11,233 | 37,416 | +233% | 1 | 1 | 0% | 871 | 3,061 | +251% | 0 | 0 | — |
case-13 | fail→pass | 19,486 | 24,465 | +26% | 1 | 1 | 0% | 1,620 | 5,926 | +266% | 0 | 0 | — |
case-14 | pass→fail | 26,939 | 28,016 | +4% | 1 | 1 | 0% | 3,156 | 3,540 | +12% | 0 | 0 | — |
case-15 | fail→fail | 14,719 | 37,824 | +157% | 1 | 1 | 0% | 1,999 | 7,621 | +281% | 0 | 0 | — |
case-16 | fail→fail | 26,842 | 28,616 | +7% | 1 | 1 | 0% | 3,246 | 6,912 | +113% | 0 | 0 | — |
case-17 | fail→fail | 15,176 | 31,072 | +105% | 1 | 1 | 0% | 1,783 | 2,879 | +61% | 0 | 0 | — |
case-18 | fail→pass | 10,995 | 23,743 | +116% | 1 | 1 | 0% | 552 | 5,815 | +953% | 0 | 0 | — |
case-19 | fail→fail | 7,658 | 26,762 | +249% | 1 | 1 | 0% | 1,361 | 5,982 | +340% | 0 | 0 | — |
case-20 | pass→pass | 18,071 | 9,518 | -47% | 1 | 1 | 0% | 2,329 | 3,607 | +55% | 0 | 0 | — |
case-21 | pass→pass | 10,484 | 11,652 | +11% | 1 | 1 | 0% | 1,735 | 3,833 | +121% | 0 | 0 | — |
case-22 | pass→fail | 14,960 | 16,164 | +8% | 1 | 1 | 0% | 2,840 | 2,631 | -7% | 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 14 counted toward the lift figure. The other 8 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 14 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.