Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Synectics Campaign — systematic use of analogy and metaphor for breakthrough associations via Gordon's 4 analogy types and excursion method.
.claude/skills/yogsoth-ai-synectics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 23% | 0% |
Systematic use of analogy and metaphor for breakthrough associations via Gordon's 4 analogy types and excursion method.
| Strategy | Signal Keywords | |----------|----------------| | direct-analogy | analogy, parallel, similar system, nature, biomimicry, structural similarity | | personal-analogy | empathy, become, identify with, first-person, feel like, embody | | symbolic-analogy | oxymoron, compressed conflict, poetic image, paradox, essence | | fantasy-analogy | wish, ideal, magic, ignore constraints, if only, perfect world | | excursion-method | excursion, departure, unrelated domain, force-fit, full process |
| Strategy | Description | |----------|-------------| | direct-analogy | Find structurally similar systems in nature/technology/society | | personal-analogy | Empathic identification — become the system/component | | symbolic-analogy | Compress core contradiction into poetic imagery/oxymoron | | fantasy-analogy | Wish-fulfillment thinking — ignore physical laws for ideal solution | | excursion-method | Full 8-stage Gordon-Prince excursion process |
| Tactic | Description | |--------|-------------| | analogy-extraction | Extract structural analogies from cross-domain sources (shared) | | excursion-orchestration | Orchestrate departure → force-fit → springboard sequence | | compressed-conflict | Generate oxymorons from contradictions and extract idea directions |
| SOP | Description | |-----|-------------| | direct-analogy-generation | Find direct analogies from nature/tech/society | | personal-identification | First-person empathic identification with system | | symbolic-compression | Compress contradiction into 2-3 word oxymoron | | fantasy-wish | Unconstrained wish-fulfillment ideation | | excursion-departure | Leave problem, explore unrelated domain | | force-fit | Force-fit excursion discoveries back to problem | | analogy-chain | Chain analogies to deeper levels (3-5 layers) | | springboard-launch | Convert analogy insights into concrete solutions | | synectics-synthesis | Synthesize all synectics outputs |
| Strategy | web-search | web-research | paper-overview | paper-search | paper-research | |----------|-----------|-------------|---------------|-------------|---------------| | direct-analogy | 25 | 8 | 25 | 15 | 5 | | personal-analogy | 15 | 5 | 15 | 10 | 3 | | symbolic-analogy | 15 | 5 | 15 | 10 | 3 | | fantasy-analogy | 15 | 5 | 15 | 10 | 3 | | excursion-method | 30 | 10 | 25 | 15 | 8 |
| Tool | Server | Purpose | |------|--------|---------| | brave_web_search | brave-search | General web search for analogies 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 | |--------|------| | analogy-extraction | Extract structural analogies from cross-domain sources (shared) | | excursion-orchestration | Orchestrate departure → force-fit → springboard | | compressed-conflict | Generate oxymorons and extract idea directions |
| SOP | Role | |-----|------| | direct-analogy-generation | Find direct analogies | | personal-identification | Empathic identification | | symbolic-compression | Oxymoron compression | | fantasy-wish | Wish-fulfillment ideation | | excursion-departure | Domain departure | | force-fit | Force-fit back to problem | | analogy-chain | Deepen analogies in layers | | springboard-launch | Convert insights to solutions | | synectics-synthesis | Final synthesis |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | direct-analogy | Find structurally similar systems in nature/technology/society. Map structural parallels to generate transferable solution principles. | | excursion-method | Full 8-stage Gordon-Prince excursion process. Deliberate departure from the problem into unrelated domains, then force-fit discoveries back. | | fantasy-analogy | Wish-fulfillment thinking — ignore physical laws for ideal solution. Use unconstrained imagination to reveal what the problem truly needs. | | personal-analogy | Empathic identification — become the system/component. First-person embodiment to discover hidden constraints and opportunities. | | symbolic-analogy | Compress core contradiction into poetic imagery/oxymoron. Use compressed conflicts to reveal hidden solution directions. |
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | analogy-extraction | Extract transferable structural principles from source domains. Orchestrates source identification → abstraction → structural mapping → transfer validation. | | compressed-conflict | Generate compressed conflicts (oxymorons) from problem contradictions and extract concrete idea directions from the symbolic tension. | | evaluation-filtering | Multi-dimensional evaluation and tiered filtering of generated ideas. Orchestrates novelty assessment → feasibility check → ranking → selection. | | excursion-orchestration | Orchestrate the excursion sequence — departure into unrelated domain, force-fit discoveries back to problem, launch springboard ideas. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | analogy-chain | Chain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface. | | 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-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. | | direct-analogy-generation | Find direct analogies from nature/tech/society that share structural properties with the problem. Produces analogy list with structural mappings. | | domain-scanning | Scan distant domains for transferable principles. Uses web-search and paper-overview to identify analogous solutions in unrelated fields. | | excursion-departure | Leave the problem entirely and explore an unrelated domain. Produces excursion domain discoveries for later force-fitting. | | fantasy-wish | Unconstrained wish-fulfillment ideation. Ignore all physical laws to imagine the ideal solution, then identify realization directions. | | force-fit | Force-fit excursion discoveries back to the original problem. Deliberately create connections between unrelated findings and the challenge. | | idea-synthesis | Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions. | | personal-identification | First-person empathic identification with a system or component. Produces experience description and design insights from embodiment. | | 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. | | springboard-launch | Convert analogy insights into concrete feasible solutions. Transform abstract connections into actionable mechanisms. | | symbolic-compression | Compress problem contradiction into 2-3 word oxymoron. Produces oxymorons with interpretation directions for each. | | synectics-synthesis | Synthesize all synectics outputs into a structured idea report. Combines results from all analogy types and excursion processes. |
<!-- 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 | 25,624 | 10,249 | -60% | 1 | 1 | 0% | 2,673 | 2,935 | +10% | 0 | 0 | — |
case-14 | pass→pass | 11,675 | 2,772 | -76% | 1 | 1 | 0% | 1,051 | 2,428 | +131% | 0 | 0 | — |
case-02 | pass→pass | 11,478 | 10,566 | -8% | 1 | 1 | 0% | 1,820 | 2,929 | +61% | 0 | 0 | — |
case-03 | fail→pass | 14,330 | 9,437 | -34% | 1 | 1 | 0% | 2,012 | 2,712 | +35% | 0 | 0 | — |
case-04 | fail→pass | 16,683 | 3,534 | -79% | 1 | 1 | 0% | 1,810 | 2,623 | +45% | 0 | 0 | — |
case-05 | fail→pass | 14,226 | 3,764 | -74% | 1 | 1 | 0% | 2,055 | 2,652 | +29% | 0 | 0 | — |
case-06 | fail→pass | 28,915 | 7,502 | -74% | 1 | 1 | 0% | 1,962 | 2,407 | +23% | 0 | 0 | — |
case-07 | fail→pass | 28,252 | 7,700 | -73% | 1 | 1 | 0% | 335 | 2,483 | +641% | 0 | 0 | — |
case-08 | fail→pass | 31,012 | 7,593 | -76% | 1 | 1 | 0% | 1,791 | 2,447 | +37% | 0 | 0 | — |
case-09 | pass→pass | 14,467 | 9,108 | -37% | 1 | 1 | 0% | 1,318 | 2,659 | +102% | 0 | 0 | — |
case-19 | fail→pass | 16,644 | 2,676 | -84% | 1 | 1 | 0% | 1,955 | 2,514 | +29% | 0 | 0 | — |
case-10 | pass→pass | 11,442 | 13,664 | +19% | 1 | 1 | 0% | 1,748 | 3,290 | +88% | 0 | 0 | — |
case-11 | fail→pass | 31,941 | 7,589 | -76% | 1 | 1 | 0% | 1,292 | 2,425 | +88% | 0 | 0 | — |
case-12 | pass→pass | 12,873 | 4,800 | -63% | 1 | 1 | 0% | 1,271 | 2,767 | +118% | 0 | 0 | — |
case-13 | fail→fail | 15,984 | 7,146 | -55% | 1 | 1 | 0% | 1,854 | 2,315 | +25% | 0 | 0 | — |
case-15 | fail→pass | 13,128 | 7,154 | -46% | 1 | 1 | 0% | 1,388 | 2,419 | +74% | 0 | 0 | — |
case-16 | pass→pass | 9,427 | 8,505 | -10% | 1 | 1 | 0% | 1,586 | 3,353 | +111% | 0 | 0 | — |
case-17 | pass→pass | 42,385 | 18,841 | -56% | 1 | 1 | 0% | 2,547 | 4,143 | +63% | 0 | 0 | — |
case-18 | fail→pass | 14,038 | 8,438 | -40% | 1 | 1 | 0% | 2,184 | 2,591 | +19% | 0 | 0 | — |
case-20 | pass→pass | 22,557 | 21,081 | -7% | 1 | 1 | 0% | 2,609 | 4,997 | +92% | 0 | 0 | — |
case-21 | pass→pass | 17,070 | 29,835 | +75% | 1 | 1 | 0% | 2,345 | 5,702 | +143% | 0 | 0 | — |
case-22 | pass→fail | 18,424 | 21,810 | +18% | 1 | 1 | 0% | 3,041 | 2,714 | -11% | 0 | 0 | — |
case-23 | pass→fail | 19,045 | 21,346 | +12% | 1 | 1 | 0% | 2,712 | 2,857 | +5% | 0 | 0 | — |
case-24 | pass→pass | 21,529 | 32,764 | +52% | 1 | 1 | 0% | 3,351 | 6,467 | +93% | 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, and 20 counted toward the lift figure. The other 4 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 +38 percentage points is the difference between those two pass rates over the 20 comparable cases. 2 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.