Install any skill in seconds. Free to start, no credit card required.
Get Started Free →What are all possible combinations? — Zwicky Box construction with CCA consistency filtering for systematic scenario enumeration
.claude/skills/yogsoth-ai-morphological-scenario/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-18 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 64% | 0% |
General Morphological Analysis (Zwicky) combined with Cross-Consistency Assessment (Ritchey). Systematically enumerate all possible combinations of key uncertainty parameters, filter for internal consistency, and assess surviving configurations as plausible scenarios.
Key principles:
scenario-driver-identificationparameter-enumerationconsistency-pair-evaluationscenario-narrative-construction (per surviving config)scenario-impact-assessment (per scenario)robustness-scoringscenario-synthesis| Step | Token Budget | Notes | |------|-------------|-------| | Driver identification | 8K | Single pass | | Parameter enumeration | 10K | May iterate once | | Consistency filtering | 15K | O(n²) pairwise | | Narrative construction | 12K × N | N = surviving configs (typically 4-8) | | Impact assessment | 10K × N | Per scenario | | Robustness scoring | 8K | Aggregation | | Synthesis | 12K | Final compilation |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | cross-consistency-filtering | Orchestrates pairwise consistency evaluation and narrative construction to filter the morphological field | | parameter-space-construction | Orchestrates driver identification and parameter enumeration to build the complete morphological field | | strategy-robustness-testing | Orchestrates impact assessment and robustness scoring to evaluate research approach resilience across scenarios |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | experiment-execution-consistency-pair-evaluation | Pairwise consistency assessment using Cross-Consistency Assessment (CCA) matrix | | parameter-enumeration | Enumerate possible values for each uncertainty driver using MECE principles | | robustness-scoring | Compute robustness index across scenarios with sensitivity analysis | | scenario-driver-identification | Identify key uncertainty drivers using PESTEL framework scanning | | scenario-impact-assessment | Assess each scenario's impact on the research approach across multiple dimensions | | scenario-narrative-construction | Build rich narratives for surviving morphological configurations using Shell method | | scenario-synthesis | Comprehensive scenario analysis report synthesizing all scenario work |
<!-- 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-18 | fail→pass | 31,374 | 7,710 | -75% | 1 | 1 | 0% | 1,950 | 1,249 | -36% | 0 | 0 | — |
case-01 | fail→pass | 50,733 | 56,340 | +11% | 1 | 1 | 0% | 8,281 | 8,431 | +2% | 0 | 0 | — |
case-02 | fail→pass | 53,269 | 74,218 | +39% | 1 | 1 | 0% | 8,278 | 9,055 | +9% | 0 | 0 | — |
case-03 | fail→fail | 65,946 | 62,118 | -6% | 1 | 1 | 0% | 8,275 | 1,626 | -80% | 0 | 0 | — |
case-04 | fail→pass | 36,236 | 46,826 | +29% | 1 | 1 | 0% | 5,108 | 5,224 | +2% | 0 | 0 | — |
case-05 | pass→fail | 20,860 | 5,065 | -76% | 1 | 1 | 0% | 2,493 | 1,219 | -51% | 0 | 0 | — |
case-06 | fail→pass | 19,283 | 26,754 | +39% | 1 | 1 | 0% | 2,476 | 4,054 | +64% | 0 | 0 | — |
case-07 | pass→pass | 35,949 | 51,007 | +42% | 1 | 1 | 0% | 2,953 | 8,236 | +179% | 0 | 0 | — |
case-08 | pass→pass | 19,345 | 8,252 | -57% | 1 | 1 | 0% | 2,181 | 2,176 | -0% | 0 | 0 | — |
case-13 | fail→fail | 20,539 | 7,569 | -63% | 1 | 1 | 0% | 1,581 | 1,270 | -20% | 0 | 0 | — |
case-09 | pass→pass | 18,125 | 26,384 | +46% | 1 | 1 | 0% | 2,905 | 4,349 | +50% | 0 | 0 | — |
case-10 | fail→fail | 6,786 | 9,293 | +37% | 1 | 1 | 0% | 1,116 | 1,583 | +42% | 0 | 0 | — |
case-11 | fail→fail | 29,151 | 24,879 | -15% | 1 | 1 | 0% | 3,673 | 3,959 | +8% | 0 | 0 | — |
case-12 | fail→fail | 15,914 | 2,580 | -84% | 1 | 1 | 0% | 1,664 | 1,205 | -28% | 0 | 0 | — |
case-14 | fail→fail | 10,889 | 2,995 | -72% | 1 | 1 | 0% | 1,589 | 1,337 | -16% | 0 | 0 | — |
case-15 | fail→pass | 12,424 | 2,535 | -80% | 1 | 1 | 0% | 1,950 | 1,247 | -36% | 0 | 0 | — |
case-16 | fail→pass | 45,865 | 2,807 | -94% | 1 | 1 | 0% | 1,994 | 1,287 | -35% | 0 | 0 | — |
case-17 | pass→pass | 12,974 | 3,559 | -73% | 1 | 1 | 0% | 1,870 | 1,340 | -28% | 0 | 0 | — |
case-19 | fail→pass | 18,738 | 6,570 | -65% | 1 | 1 | 0% | 3,009 | 1,916 | -36% | 0 | 0 | — |
case-20 | pass→pass | 15,338 | 38,702 | +152% | 1 | 1 | 0% | 2,552 | 5,245 | +106% | 0 | 0 | — |
case-21 | pass→pass | 12,381 | 39,636 | +220% | 1 | 1 | 0% | 1,959 | 5,743 | +193% | 0 | 0 | — |
case-22 | pass→pass | 16,259 | 38,584 | +137% | 1 | 1 | 0% | 3,221 | 9,054 | +181% | 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 19 counted toward the lift figure. The other 3 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 +32 percentage points is the difference between those two pass rates over the 19 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.