Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Ritchey GMA: complete iterative morphological process
.claude/skills/yogsoth-ai-general-morphological-analysis/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-07 | ✓→✗ | ▼ Worse | 35% | 0% |
| case-12 | ✓→✗ | ▼ Worse | 14% | 0% |
| case-13 | ✓→✗ | ▼ Worse | -51% | 0% |
Ritchey's complete iterative GMA process: problem structuring → morphological field → CCA → solution space exploration → synthesis.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 30 | 0 | 0% | | web-research | 10 | 0 | 0% | | paper-overview | 30 | 0 | 0% | | paper-search | 20 | 0 | 0% | | paper-research | 8 | 0 | 0% |
Cannot exit strategy until ≥80% of each budget line is consumed OR yield targets are met with justification for remaining budget.
| Tactic | Role | |--------|------| | combination-mapping | Enumerate parameter combinations | | consistency-checking | CCA filtering | | white-space-identification | Find unexplored regions |
| SOP | Role | |-----|------| | value-enumeration | Enumerate parameter values | | matrix-construction | Build morphological field | | consistency-pair-evaluation | Pairwise consistency evaluation | | solution-space-reduction | CCA space reduction | | path-generation | Generate solution paths | | white-space-detection | Detect unexplored regions | | combination-evaluation | Evaluate novel combinations | | morphological-synthesis | Final synthesis |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | creative-ideation-consistency-checking | Pairwise consistency evaluation to reduce solution space by identifying and removing inconsistent combinations. | | 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 | | --- | --- | | combination-evaluation | Evaluate new combinations for feasibility and novelty | | creative-ideation-consistency-pair-evaluation | Evaluate pairwise value consistency (logical/empirical/normative) | | matrix-construction | Build n-dimensional morphological matrix | | morphological-synthesis | Synthesize all morphological exploration outputs | | path-generation | Generate combination paths through consistent space | | solution-space-reduction | Apply CCA to remove inconsistent combinations | | value-enumeration | Enumerate 3-5 values per parameter including extremes | | white-space-detection | Identify matrix regions not covered by existing methods |
<!-- 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 | 35,322 | 66,523 | +88% | 1 | 1 | 0% | 6,212 | 6,908 | +11% | 0 | 0 | — |
case-02 | fail→fail | 32,026 | 39,532 | +23% | 1 | 1 | 0% | 6,214 | 6,910 | +11% | 0 | 0 | — |
case-03 | fail→fail | 33,555 | 33,596 | +0% | 1 | 1 | 0% | 6,210 | 6,905 | +11% | 0 | 0 | — |
case-04 | pass→pass | 18,910 | 30,967 | +64% | 1 | 1 | 0% | 3,158 | 6,091 | +93% | 0 | 0 | — |
case-05 | pass→pass | 20,122 | 35,283 | +75% | 1 | 1 | 0% | 3,490 | 6,826 | +96% | 0 | 0 | — |
case-06 | pass→pass | 18,206 | 19,743 | +8% | 1 | 1 | 0% | 2,968 | 4,214 | +42% | 0 | 0 | — |
case-07 | pass→fail | 28,077 | 32,609 | +16% | 1 | 1 | 0% | 5,096 | 6,889 | +35% | 0 | 0 | — |
case-08 | pass→pass | 18,550 | 33,393 | +80% | 1 | 1 | 0% | 3,003 | 6,889 | +129% | 0 | 0 | — |
case-09 | pass→pass | 22,284 | 30,191 | +35% | 1 | 1 | 0% | 3,666 | 6,233 | +70% | 0 | 0 | — |
case-10 | fail→pass | 23,268 | 34,751 | +49% | 1 | 1 | 0% | 4,035 | 6,014 | +49% | 0 | 0 | — |
case-11 | pass→pass | 24,470 | 42,123 | +72% | 1 | 1 | 0% | 3,975 | 6,886 | +73% | 0 | 0 | — |
case-12 | pass→fail | 26,993 | 27,212 | +1% | 1 | 1 | 0% | 6,075 | 6,917 | +14% | 0 | 0 | — |
case-13 | pass→fail | 16,976 | 10,455 | -38% | 1 | 1 | 0% | 2,835 | 1,381 | -51% | 0 | 0 | — |
case-14 | pass→pass | 9,931 | 12,888 | +30% | 1 | 1 | 0% | 2,437 | 3,692 | +51% | 0 | 0 | — |
case-15 | pass→pass | 16,874 | 18,008 | +7% | 1 | 1 | 0% | 2,487 | 3,513 | +41% | 0 | 0 | — |
case-16 | pass→pass | 25,306 | 38,290 | +51% | 1 | 1 | 0% | 4,523 | 7,319 | +62% | 0 | 0 | — |
case-17 | pass→pass | 18,267 | 25,687 | +41% | 1 | 1 | 0% | 3,005 | 5,046 | +68% | 0 | 0 | — |
case-18 | fail→fail | 36,078 | 35,144 | -3% | 1 | 1 | 0% | 6,176 | 6,872 | +11% | 0 | 0 | — |
case-19 | pass→pass | 21,325 | 31,437 | +47% | 1 | 1 | 0% | 3,247 | 5,906 | +82% | 0 | 0 | — |
case-20 | pass→fail | 32,206 | 8,465 | -74% | 1 | 1 | 0% | 5,668 | 1,207 | -79% | 0 | 0 | — |
case-21 | pass→fail | 22,970 | 7,894 | -66% | 1 | 1 | 0% | 3,544 | 1,068 | -70% | 0 | 0 | — |
case-22 | pass→fail | 22,798 | 10,396 | -54% | 1 | 1 | 0% | 3,564 | 1,289 | -64% | 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 18 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 -20 percentage points is the difference between those two pass rates over the 18 comparable cases. 7 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.