Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Morphological Exploration Campaign — systematic dimension-combination enumeration to discover unexplored solution spaces via Zwicky box, CCA, and GMA
.claude/skills/yogsoth-ai-morphological-exploration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 118% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-21 | ✗→✓ | ▲ Improved | -8% | 0% |
Systematic dimension-combination enumeration to discover unexplored solution spaces via Zwicky box, CCA, and GMA.
| Strategy | Signal Keywords | |----------|----------------| | zwicky-box-construction | Zwicky, morphological box, parameter matrix, value grid | | cross-consistency-analysis | CCA, pairwise consistency, reduce combinations, filter inconsistent | | general-morphological-analysis | GMA, Ritchey, iterative morphological, complete analysis | | design-space-mapping | design space, coverage, explored regions, visualization | | parameter-variation | one-factor, parameter sweep, sensitivity, variation |
| Strategy | Description | |----------|-------------| | zwicky-box-construction | Classic Zwicky box: parameter identification → value enumeration → matrix construction | | cross-consistency-analysis | CCA: pairwise consistency checking to reduce solution space 90-99% | | general-morphological-analysis | Ritchey GMA: complete iterative morphological process | | design-space-mapping | Visualize explored/unexplored regions of solution space | | parameter-variation | Systematic one-factor-at-a-time parameter sweep |
| Tactic | Description | |--------|-------------| | combination-mapping | Systematically enumerate parameter dimensions and generate viable combinations (shared) | | consistency-checking | Pairwise consistency evaluation to reduce solution space | | white-space-identification | Identify unexplored viable regions in the morphological matrix |
| SOP | Description | |-----|-------------| | value-enumeration | Enumerate 3-5 values per parameter including extremes | | matrix-construction | Build n-dimensional morphological matrix | | consistency-pair-evaluation | Evaluate pairwise value consistency (logical/empirical/normative) | | solution-space-reduction | Apply CCA to remove inconsistent combinations | | path-generation | Generate combination paths through consistent space | | white-space-detection | Identify matrix regions not covered by existing methods | | combination-evaluation | Evaluate new combinations for feasibility and novelty | | design-space-visualization | Generate structured description of design space | | morphological-synthesis | Synthesize all morphological exploration outputs |
| Strategy | web-search | web-research | paper-overview | paper-search | paper-research | |----------|-----------|-------------|---------------|-------------|---------------| | zwicky-box-construction | 25 | 8 | 25 | 15 | 5 | | cross-consistency-analysis | 15 | 5 | 15 | 10 | 3 | | general-morphological-analysis | 30 | 10 | 30 | 20 | 8 | | design-space-mapping | 25 | 8 | 20 | 12 | 5 | | parameter-variation | 20 | 5 | 20 | 12 | 5 |
| Tool | Server | Purpose | |------|--------|---------| | brave_web_search | brave-search | General web search for morphological 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 | |--------|------| | combination-mapping | Enumerate parameter combinations (shared, from combinatorial-creativity) | | consistency-checking | Pairwise consistency evaluation and space reduction | | white-space-identification | Identify unexplored viable regions |
| SOP | Role | |-----|------| | value-enumeration | Enumerate parameter values with boundary extremes | | matrix-construction | Build n-dimensional morphological matrix | | consistency-pair-evaluation | Evaluate pairwise consistency | | solution-space-reduction | Remove inconsistent combinations via CCA | | path-generation | Generate paths through consistent space | | white-space-detection | Detect uncovered matrix regions | | combination-evaluation | Evaluate combinations for feasibility/novelty | | design-space-visualization | Describe design space structure | | morphological-synthesis | Final output synthesis |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Strategy | When to use | | --- | --- | | cross-consistency-analysis | CCA: pairwise consistency checking to reduce solution space 90-99% | | design-space-mapping | Visualize explored/unexplored regions of solution space | | general-morphological-analysis | Ritchey GMA: complete iterative morphological process | | parameter-variation | Systematic one-factor-at-a-time parameter sweep | | zwicky-box-construction | Classic Zwicky box: parameter identification → value enumeration → matrix construction |
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | creative-ideation-combination-mapping | Systematically enumerate parameter dimensions and generate viable combinations. Orchestrates parameter extraction → value enumeration → compatibility assessment → synthesis. | | creative-ideation-consistency-checking | Pairwise consistency evaluation to reduce solution space by identifying and removing inconsistent combinations. | | evaluation-filtering | Multi-dimensional evaluation and tiered filtering of generated ideas. Orchestrates novelty assessment → feasibility check → ranking → selection. | | white-space-identification | Identify unexplored viable regions in the morphological matrix where no existing methods operate. |
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. | | 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. | | parameter-identification | Identify the key parameters/dimensions of a problem space. Produces a structured parameter list with value ranges for morphological analysis. |
<!-- 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-06 | pass→pass | 20,756 | 36,136 | +74% | 1 | 1 | 0% | 2,965 | 6,945 | +134% | 0 | 0 | — |
case-01 | fail→fail | 53,740 | 20,986 | -61% | 1 | 1 | 0% | 8,304 | 2,406 | -71% | 0 | 0 | — |
case-02 | fail→pass | 20,265 | 47,605 | +135% | 1 | 1 | 0% | 3,221 | 7,006 | +118% | 0 | 0 | — |
case-03 | pass→pass | 25,535 | 23,451 | -8% | 1 | 1 | 0% | 3,106 | 4,744 | +53% | 0 | 0 | — |
case-04 | fail→fail | 18,762 | 19,749 | +5% | 1 | 1 | 0% | 2,217 | 2,326 | +5% | 0 | 0 | — |
case-05 | pass→pass | 18,121 | 12,746 | -30% | 1 | 1 | 0% | 1,936 | 2,977 | +54% | 0 | 0 | — |
case-07 | pass→fail | 14,534 | 12,844 | -12% | 1 | 1 | 0% | 1,539 | 2,163 | +41% | 0 | 0 | — |
case-08 | pass→pass | 16,906 | 6,379 | -62% | 1 | 1 | 0% | 1,991 | 2,924 | +47% | 0 | 0 | — |
case-09 | pass→pass | 20,453 | 13,738 | -33% | 1 | 1 | 0% | 2,290 | 3,271 | +43% | 0 | 0 | — |
case-10 | pass→pass | 21,957 | 13,567 | -38% | 1 | 1 | 0% | 2,181 | 3,091 | +42% | 0 | 0 | — |
case-11 | pass→pass | 26,138 | 40,565 | +55% | 1 | 1 | 0% | 4,067 | 8,522 | +110% | 0 | 0 | — |
case-17 | fail→fail | 23,825 | 6,714 | -72% | 1 | 1 | 0% | 1,061 | 2,165 | +104% | 0 | 0 | — |
case-12 | pass→pass | 19,704 | 29,895 | +52% | 1 | 1 | 0% | 2,025 | 5,098 | +152% | 0 | 0 | — |
case-13 | pass→pass | 35,667 | 36,653 | +3% | 1 | 1 | 0% | 5,627 | 8,165 | +45% | 0 | 0 | — |
case-14 | fail→pass | 18,658 | 11,479 | -38% | 1 | 1 | 0% | 2,145 | 2,973 | +39% | 0 | 0 | — |
case-15 | fail→fail | 11,226 | 44,771 | +299% | 1 | 1 | 0% | 1,841 | 4,475 | +143% | 0 | 0 | — |
case-16 | fail→pass | 16,332 | 10,153 | -38% | 1 | 1 | 0% | 1,656 | 3,279 | +98% | 0 | 0 | — |
case-18 | fail→pass | 10,100 | 2,840 | -72% | 1 | 1 | 0% | 1,662 | 2,132 | +28% | 0 | 0 | — |
case-19 | pass→pass | 6,559 | 14,918 | +127% | 1 | 1 | 0% | 1,045 | 3,373 | +223% | 0 | 0 | — |
case-20 | pass→pass | 6,273 | 7,700 | +23% | 1 | 1 | 0% | 1,162 | 3,255 | +180% | 0 | 0 | — |
case-21 | fail→pass | 19,459 | 2,189 | -89% | 1 | 1 | 0% | 2,258 | 2,082 | -8% | 0 | 0 | — |
case-22 | pass→fail | 13,481 | 10,449 | -22% | 1 | 1 | 0% | 2,168 | 2,207 | +2% | 0 | 0 | — |
case-23 | pass→pass | 10,559 | 13,629 | +29% | 1 | 1 | 0% | 1,797 | 4,037 | +125% | 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 18 counted toward the lift figure. The other 5 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 18 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.