Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Decompose systems into components and reassemble via SCAMPER, SIT, TRIZ, and recombination. Campaign orchestrating 5 strategies for systematic structural transformation.
.claude/skills/yogsoth-ai-structural-deconstruction/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 154% | 0% |
| case-03 | ✓→✗ | ▼ Worse | -31% | 0% |
| case-09 | ✓→✗ | ▼ Worse | -20% | 0% |
| case-13 | ✓→✗ | ▼ Worse | -2% | 0% |
Decompose systems into components and reassemble via SCAMPER, SIT, TRIZ, and recombination.
| Strategy | Signal Keywords | |----------|----------------| | scamper-transformation | substitute, combine, adapt, modify, eliminate, reverse, rearrange | | component-surgery | subtract, multiply, divide, unify, redirect, SIT | | triz-contradiction-resolution | contradiction, trade-off, conflict, opposing requirements, parameter | | function-trimming | simplify, remove, trim, reduce complexity, minimize components | | recombination-architecture | reassemble, recombine, novel structure, new arrangement, merge fragments |
| Strategy | Description | |----------|-------------| | scamper-transformation | 7 operators (Substitute/Combine/Adapt/Modify/Put/Eliminate/Reverse) for systematic transformation | | component-surgery | Component-level surgical operations (subtract/multiply/divide/unify/redirect) from SIT | | triz-contradiction-resolution | Resolve technical/physical contradictions via 40 principles + separation | | function-trimming | Remove components while preserving function via TRIZ trimming | | recombination-architecture | Reassemble decomposed fragments into novel structures |
| Tactic | Description | |--------|-------------| | combination-mapping | Systematically enumerate parameter dimensions and generate viable combinations (shared) | | contradiction-identification | Identify technical and physical contradictions in a system | | component-decomposition | Decompose system into functional components with trimming candidates |
| SOP | Description | |-----|-------------| | scamper-divergence | Execute SCAMPER 7 operators | | surgery-operation | Component surgery (subtract/multiply/divide/unify/redirect) | | triz-principle-application | Select principles from contradiction matrix, generate solutions | | separation-principle | Apply time/space/condition/scale separation | | function-model-construction | Build substance-field functional model | | trimming-execution | Progressively remove components, verify function preservation | | recombination-generation | Reassemble decomposed fragments into new structures | | structural-synthesis | Synthesize all structural transformation outputs | | contradiction-matrix-lookup | Query 39x39 TRIZ contradiction matrix |
| Strategy | web-search | web-research | paper-overview | paper-search | paper-research | |----------|-----------|-------------|---------------|-------------|---------------| | scamper-transformation | 20 | 5 | 15 | 10 | 3 | | component-surgery | 20 | 5 | 15 | 10 | 3 | | triz-contradiction-resolution | 30 | 10 | 25 | 15 | 5 | | function-trimming | 25 | 8 | 20 | 12 | 5 | | recombination-architecture | 20 | 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 | |--------|------| | combination-mapping | Enumerate parameter combinations (shared, from combinatorial-creativity) | | contradiction-identification | Identify contradictions with resolution paths | | component-decomposition | Decompose into components with trimming candidates |
| SOP | Role | |-----|------| | scamper-divergence | SCAMPER 7-operator divergence | | surgery-operation | SIT component surgery | | triz-principle-application | TRIZ principle selection and application | | separation-principle | Physical contradiction separation | | function-model-construction | Substance-field modeling | | trimming-execution | Progressive component removal | | recombination-generation | Fragment reassembly | | structural-synthesis | Final output synthesis | | contradiction-matrix-lookup | 39x39 matrix query |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | component-surgery | Component-level surgical operations (subtract/multiply/divide/unify/redirect) from Systematic Inventive Thinking (SIT). | | function-trimming | Remove components while preserving function via TRIZ trimming methodology. Simplify systems by redistributing functions. | | recombination-architecture | Reassemble decomposed fragments into novel structures through systematic recombination of components. | | scamper-transformation | 7 operators (Substitute/Combine/Adapt/Modify/Put/Eliminate/Reverse) for systematic transformation of existing solutions. | | triz-contradiction-resolution | Resolve technical and physical contradictions via TRIZ 40 inventive principles and separation methods. |
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | component-decomposition | Decompose system into functional components, identify dependencies, and surface trimming candidates. | | contradiction-identification | Identify technical and physical contradictions in a system through functional modeling and matrix analysis. | | creative-ideation-combination-mapping | Systematically enumerate parameter dimensions and generate viable combinations. Orchestrates parameter extraction → value enumeration → compatibility assessment → synthesis. | | 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 | | --- | --- | | 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. | | contradiction-matrix-lookup | Query the 39x39 TRIZ contradiction matrix to find recommended inventive principles for a given technical contradiction. | | 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. | | function-model-construction | Build substance-field functional model of a system, annotating useful, harmful, insufficient, and excessive interactions. | | idea-synthesis | Synthesize diverse ideas into coherent solution concepts. Combines fragments from multiple ideation passes into structured, actionable ideas with clear mechanism descriptions. | | parameter-identification | Identify the key parameters/dimensions of a problem space. Produces a structured parameter list with value ranges for morphological analysis. | | recombination-generation | Reassemble decomposed system fragments into novel structural arrangements that create emergent value. | | scamper-divergence | Execute SCAMPER 7 operators on a target solution. Subagent self-selects best 2-3 operators for deepest exploration. | | separation-principle | Apply time/space/condition/scale separation to resolve physical contradictions where the same parameter must satisfy opposing requirements. | | structural-synthesis | Synthesize all structural transformation outputs into a coherent, ranked idea report with lineage tracking. | | surgery-operation | Execute component surgery operations (subtract/multiply/divide/unify/redirect) from Systematic Inventive Thinking. | | trimming-execution | Progressively remove components from a system while verifying function preservation through redistribution. | | triz-principle-application | Select inventive principles from the contradiction matrix and generate concrete solutions for identified contradictions. |
<!-- 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-02 | pass→pass | 26,171 | 63,834 | +144% | 1 | 1 | 0% | 3,721 | 9,620 | +159% | 0 | 0 | — |
case-01 | fail→fail | 60,607 | 24,235 | -60% | 1 | 1 | 0% | 3,665 | 2,631 | -28% | 0 | 0 | — |
case-03 | pass→fail | 30,733 | 12,982 | -58% | 1 | 1 | 0% | 3,347 | 2,326 | -31% | 0 | 0 | — |
case-04 | pass→pass | 19,990 | 55,291 | +177% | 1 | 1 | 0% | 2,708 | 8,785 | +224% | 0 | 0 | — |
case-05 | pass→pass | 28,344 | 53,535 | +89% | 1 | 1 | 0% | 3,182 | 7,660 | +141% | 0 | 0 | — |
case-06 | pass→pass | 22,428 | 10,157 | -55% | 1 | 1 | 0% | 2,594 | 2,861 | +10% | 0 | 0 | — |
case-11 | pass→pass | 27,538 | 27,953 | +2% | 1 | 1 | 0% | 3,294 | 5,750 | +75% | 0 | 0 | — |
case-07 | fail→pass | 17,037 | 16,084 | -6% | 1 | 1 | 0% | 2,396 | 3,979 | +66% | 0 | 0 | — |
case-08 | fail→fail | 26,418 | 14,780 | -44% | 1 | 1 | 0% | 3,518 | 2,730 | -22% | 0 | 0 | — |
case-09 | pass→fail | 26,340 | 21,314 | -19% | 1 | 1 | 0% | 3,217 | 2,572 | -20% | 0 | 0 | — |
case-10 | pass→pass | 10,722 | 15,395 | +44% | 1 | 1 | 0% | 994 | 3,795 | +282% | 0 | 0 | — |
case-12 | pass→pass | 18,741 | 25,003 | +33% | 1 | 1 | 0% | 2,901 | 6,154 | +112% | 0 | 0 | — |
case-13 | pass→fail | 22,977 | 10,314 | -55% | 1 | 1 | 0% | 2,829 | 2,776 | -2% | 0 | 0 | — |
case-14 | pass→pass | 18,201 | 14,346 | -21% | 1 | 1 | 0% | 2,248 | 3,542 | +58% | 0 | 0 | — |
case-15 | pass→pass | 66,473 | 53,188 | -20% | 1 | 1 | 0% | 6,206 | 7,832 | +26% | 0 | 0 | — |
case-16 | pass→pass | 26,976 | 63,862 | +137% | 1 | 1 | 0% | 3,668 | 7,700 | +110% | 0 | 0 | — |
case-17 | pass→fail | 35,916 | 19,294 | -46% | 1 | 1 | 0% | 2,760 | 2,703 | -2% | 0 | 0 | — |
case-18 | fail→fail | 18,015 | 14,997 | -17% | 1 | 1 | 0% | 2,266 | 2,646 | +17% | 0 | 0 | — |
case-19 | pass→pass | 25,534 | 48,797 | +91% | 1 | 1 | 0% | 2,028 | 10,275 | +407% | 0 | 0 | — |
case-20 | pass→pass | 47,835 | 50,441 | +5% | 1 | 1 | 0% | 8,237 | 10,279 | +25% | 0 | 0 | — |
case-21 | fail→pass | 12,150 | 8,699 | -28% | 1 | 1 | 0% | 1,028 | 2,606 | +154% | 0 | 0 | — |
case-22 | pass→fail | 24,873 | 33,340 | +34% | 1 | 1 | 0% | 3,150 | 4,293 | +36% | 0 | 0 | — |
case-23 | pass→pass | 31,391 | 47,562 | +52% | 1 | 1 | 0% | 4,376 | 9,692 | +121% | 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. 23 cases were attempted, and 15 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 -13 percentage points is the difference between those two pass rates over the 15 comparable cases. 6 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.