Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Lateral Thinking Campaign — escape logical thinking tracks via PO/movement, random entry, concept fan, challenge, and six hats (de Bono)
.claude/skills/yogsoth-ai-lateral-thinking/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 222% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 101% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 106% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -6% | 0% |
Escape logical thinking tracks via PO/movement, random entry, concept fan, challenge, and six hats (de Bono).
| Strategy | Signal Keywords | |----------|----------------| | provocation-and-movement | PO, provocation, movement, escape pattern, lateral jump | | random-entry | random word, random input, unrelated stimulus, entry point | | concept-fan | purpose, concept levels, directions, fan out, broaden | | challenge-operation | why, challenge, question practice, non-threatening | | six-hats-ideation | green hat, creative hat, six hats, parallel thinking |
| Strategy | Description | |----------|-------------| | provocation-and-movement | PO + Movement: generate provocations then extract useful directions (4 movement types) | | random-entry | Random word/concept as thinking entry point (de Bono Random Entry) | | concept-fan | Expand from purpose to concepts to directions to ideas (de Bono Concept Fan) | | challenge-operation | Non-threatening 'Why?' questioning of current practices (de Bono Challenge) | | six-hats-ideation | Green Hat focused creative thinking within Six Hats framework |
| Tactic | Description | |--------|-------------| | provocation-generation | Generate PO provocations using 5 techniques (shared) | | movement-extraction | Extract constructive directions from provocations via 4 movement types | | concept-hierarchy | Build concept levels from purpose through concepts to ideas |
| SOP | Description | |-----|-------------| | movement-operation | Extract constructive directions from PO provocations (4 movement types) | | concept-fan-expansion | Expand concept fan from purpose through concepts to ideas | | challenge-questioning | Non-threatening 'Why?' questioning of current practices | | escape-technique | Identify dominant thinking pattern and escape it | | stepping-stone | Use impractical ideas as stepping stones to practical ones | | green-hat-session | Structured creative thinking in Six Hats Green Hat mode | | fractionation | Split concepts into smaller units, recombine differently | | alternatives-generation | Generate alternatives for every known approach | | lateral-synthesis | Synthesize all lateral thinking outputs |
| Strategy | web-search | web-research | paper-overview | paper-search | paper-research | |----------|-----------|-------------|---------------|-------------|---------------| | provocation-and-movement | 20 | 5 | 20 | 12 | 5 | | random-entry | 15 | 5 | 15 | 10 | 3 | | concept-fan | 20 | 8 | 20 | 12 | 5 | | challenge-operation | 20 | 8 | 20 | 12 | 5 | | six-hats-ideation | 15 | 5 | 15 | 10 | 3 |
| Tool | Server | Purpose | |------|--------|---------| | brave_web_search | brave-search | General web search for methods and examples | | 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 | |--------|------| | provocation-generation | Generate PO provocations (shared, from combinatorial-creativity) | | movement-extraction | Extract constructive directions from provocations | | concept-hierarchy | Build concept levels with ideas per level |
| SOP | Role | |-----|------| | movement-operation | 4 movement types extraction | | concept-fan-expansion | Purpose → concepts → directions → ideas | | challenge-questioning | Non-threatening challenge questioning | | escape-technique | Dominant pattern escape | | stepping-stone | Impractical → practical via stepping stones | | green-hat-session | Pure creative output (judgment suspended) | | fractionation | Split and recombine concepts | | alternatives-generation | Generate alternatives per approach | | lateral-synthesis | Final output synthesis |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | challenge-operation | Non-threatening 'Why?' questioning of current practices (de Bono Challenge) | | concept-fan | Expand from purpose to concepts to directions to ideas (de Bono Concept Fan) | | provocation-and-movement | PO + Movement: generate provocations then extract useful directions (4 movement types) | | random-entry | Random word/concept as thinking entry point (de Bono Random Entry) | | six-hats-ideation | Green Hat focused creative thinking within Six Hats framework |
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. | | 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. | | movement-extraction | Extract constructive directions from provocations via 4 movement types (moment-to-moment, principle, focus difference, positive aspects). |
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. | | challenge-questioning | Non-threatening 'Why?' questioning of current practices to reveal historical accidents vs. genuine constraints. | | concept-fan-expansion | Expand concept fan from purpose through concepts to directions to ideas (de Bono Concept Fan). | | constraint-injection | Inject artificial constraints to force creative divergence. Generates and applies constraints (resource, time, material, audience, scale) to existing ideas to produce variants. | | 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. | | 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. | | green-hat-session | Structured creative thinking in Six Hats Green Hat mode — pure creative output with judgment suspended. | | idea-synthesis | Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions. | | lateral-synthesis | Synthesize all lateral thinking intermediate outputs into a structured idea report. | | movement-operation | Extract constructive directions from PO provocations using 4 movement types (moment-to-moment, principle, focus difference, positive aspects). | | po-provocation | Generate PO (Provocative Operation) statements per de Bono's lateral thinking. Creates deliberately illogical provocations to escape dominant thinking patterns. | | random-word-stimulus | Use random word/concept injection as creative stimulus. Selects random concepts and forces connection to the problem space, generating unexpected solution paths. | | 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 | pass→pass | 67,330 | 45,205 | -33% | 1 | 1 | 0% | 4,400 | 10,264 | +133% | 0 | 0 | — |
case-02 | pass→pass | 18,830 | 50,286 | +167% | 1 | 1 | 0% | 1,639 | 6,210 | +279% | 0 | 0 | — |
case-03 | pass→pass | 23,127 | 66,520 | +188% | 1 | 1 | 0% | 4,474 | 9,755 | +118% | 0 | 0 | — |
case-04 | pass→pass | 22,612 | 36,118 | +60% | 1 | 1 | 0% | 2,764 | 7,330 | +165% | 0 | 0 | — |
case-05 | pass→pass | 17,093 | 41,911 | +145% | 1 | 1 | 0% | 3,114 | 6,930 | +123% | 0 | 0 | — |
case-06 | pass→pass | 30,790 | 31,923 | +4% | 1 | 1 | 0% | 3,621 | 5,516 | +52% | 0 | 0 | — |
case-07 | pass→pass | 23,861 | 16,537 | -31% | 1 | 1 | 0% | 1,569 | 3,539 | +126% | 0 | 0 | — |
case-08 | fail→pass | 34,787 | 35,177 | +1% | 1 | 1 | 0% | 2,361 | 7,596 | +222% | 0 | 0 | — |
case-09 | pass→pass | 16,549 | 30,902 | +87% | 1 | 1 | 0% | 2,699 | 6,035 | +124% | 0 | 0 | — |
case-10 | pass→pass | 23,189 | 46,423 | +100% | 1 | 1 | 0% | 2,630 | 7,442 | +183% | 0 | 0 | — |
case-11 | pass→pass | 23,733 | 43,024 | +81% | 1 | 1 | 0% | 3,156 | 7,447 | +136% | 0 | 0 | — |
case-12 | pass→pass | 20,229 | 37,187 | +84% | 1 | 1 | 0% | 2,770 | 4,457 | +61% | 0 | 0 | — |
case-13 | pass→pass | 16,166 | 30,158 | +87% | 1 | 1 | 0% | 2,550 | 6,765 | +165% | 0 | 0 | — |
case-14 | pass→pass | 17,592 | 77,995 | +343% | 1 | 1 | 0% | 2,535 | 8,532 | +237% | 0 | 0 | — |
case-15 | fail→pass | 9,646 | 7,693 | -20% | 1 | 1 | 0% | 1,584 | 3,187 | +101% | 0 | 0 | — |
case-16 | fail→pass | 14,774 | 9,186 | -38% | 1 | 1 | 0% | 1,819 | 3,171 | +74% | 0 | 0 | — |
case-17 | fail→pass | 22,197 | 27,663 | +25% | 1 | 1 | 0% | 3,295 | 6,777 | +106% | 0 | 0 | — |
case-18 | pass→pass | 22,038 | 22,957 | +4% | 1 | 1 | 0% | 2,715 | 5,844 | +115% | 0 | 0 | — |
case-19 | pass→pass | 17,588 | 41,839 | +138% | 1 | 1 | 0% | 2,852 | 9,502 | +233% | 0 | 0 | — |
case-20 | pass→pass | 22,499 | 63,103 | +180% | 1 | 1 | 0% | 3,634 | 6,510 | +79% | 0 | 0 | — |
case-21 | pass→pass | 19,040 | 35,418 | +86% | 1 | 1 | 0% | 3,079 | 8,348 | +171% | 0 | 0 | — |
case-22 | fail→pass | 17,499 | 8,975 | -49% | 1 | 1 | 0% | 2,799 | 2,621 | -6% | 0 | 0 | — |
case-23 | fail→pass | 19,768 | 27,446 | +39% | 1 | 1 | 0% | 3,169 | 5,065 | +60% | 0 | 0 | — |
case-24 | pass→pass | 15,779 | 27,164 | +72% | 1 | 1 | 0% | 2,414 | 5,926 | +145% | 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. 24 cases were attempted. The headline lift of +25 percentage points is the difference between those two pass rates over the 24 comparable cases.
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.