Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Systematically enumerate parameter dimensions and generate viable combinations. Orchestrates parameter extraction → value enumeration → compatibility assessment → synthesis.
.claude/skills/yogsoth-ai-creative-ideation-combination-mapping/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 48% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 43% | 0% |
Systematically enumerate parameter dimensions and generate viable combinations.
Identify independent parameters of the problem space using parameter-identification SOP. Verify orthogonality.
For each parameter, enumerate 3-5 meaningful values including boundary and extreme values. Use value-enumeration SOP or direct generation.
Evaluate pairwise compatibility of value combinations. Flag logically/empirically/normatively inconsistent pairs. Use consistency-pair-evaluation SOP if available.
Generate viable combination paths through the consistent solution space. Prioritize unexplored regions (white space). Use path-generation or recombination-generation SOP.
Evaluate generated combinations for novelty and feasibility. Synthesize into structured ideas.
| Metric | Floor | |--------|-------| | Parameters identified | ≥4 | | Values per parameter | ≥3 | | Combinations evaluated | ≥10 | | Viable novel combinations | ≥5 |
| SOP | Role | |-----|------| | parameter-identification | Stage 1 — decompose problem into parameters | | value-enumeration | Stage 2 — enumerate parameter values | | consistency-pair-evaluation | Stage 3 — check pairwise compatibility | | path-generation | Stage 4 — generate combination paths | | recombination-generation | Stage 4 — alternative combination approach | | constraint-injection | Stage 3 — inject constraints to reduce space | | novelty-scoring | Stage 5 — score combinations | | idea-synthesis | Stage 5 — synthesize into concepts | | saturation-detection | Post — check if space is exhausted |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | creative-ideation-consistency-pair-evaluation | Evaluate pairwise value consistency (logical/empirical/normative) | | value-enumeration | Enumerate 3-5 values per parameter including extremes |
<!-- 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-13 | fail→pass | 25,661 | 31,808 | +24% | 1 | 1 | 0% | 4,046 | 5,943 | +47% | 0 | 0 | — |
case-05 | pass→pass | 19,768 | 23,512 | +19% | 1 | 1 | 0% | 2,942 | 4,751 | +61% | 0 | 0 | — |
case-06 | pass→pass | 17,975 | 21,839 | +21% | 1 | 1 | 0% | 2,982 | 4,408 | +48% | 0 | 0 | — |
case-01 | fail→fail | 17,038 | 32,101 | +88% | 1 | 1 | 0% | 3,374 | 6,196 | +84% | 0 | 0 | — |
case-02 | fail→pass | 18,808 | 25,221 | +34% | 1 | 1 | 0% | 3,309 | 5,717 | +73% | 0 | 0 | — |
case-03 | fail→pass | 27,105 | 33,551 | +24% | 1 | 1 | 0% | 4,511 | 6,679 | +48% | 0 | 0 | — |
case-04 | pass→pass | 17,073 | 25,265 | +48% | 1 | 1 | 0% | 3,150 | 5,047 | +60% | 0 | 0 | — |
case-07 | fail→pass | 26,808 | 34,053 | +27% | 1 | 1 | 0% | 3,843 | 6,442 | +68% | 0 | 0 | — |
case-08 | fail→pass | 22,814 | 27,970 | +23% | 1 | 1 | 0% | 3,525 | 5,046 | +43% | 0 | 0 | — |
case-09 | fail→pass | 18,566 | 28,124 | +51% | 1 | 1 | 0% | 3,010 | 5,855 | +95% | 0 | 0 | — |
case-10 | fail→fail | 27,780 | 32,106 | +16% | 1 | 1 | 0% | 4,566 | 6,646 | +46% | 0 | 0 | — |
case-11 | fail→pass | 15,497 | 20,546 | +33% | 1 | 1 | 0% | 2,795 | 3,791 | +36% | 0 | 0 | — |
case-12 | pass→pass | 21,351 | 28,926 | +35% | 1 | 1 | 0% | 3,211 | 5,702 | +78% | 0 | 0 | — |
case-14 | fail→fail | 25,537 | 31,902 | +25% | 1 | 1 | 0% | 4,076 | 6,649 | +63% | 0 | 0 | — |
case-15 | pass→pass | 19,791 | 34,702 | +75% | 1 | 1 | 0% | 3,119 | 5,998 | +92% | 0 | 0 | — |
case-16 | pass→pass | 20,682 | 56,583 | +174% | 1 | 1 | 0% | 2,906 | 5,276 | +82% | 0 | 0 | — |
case-17 | fail→pass | 22,952 | 28,363 | +24% | 1 | 1 | 0% | 3,150 | 5,293 | +68% | 0 | 0 | — |
case-18 | fail→pass | 20,058 | 25,719 | +28% | 1 | 1 | 0% | 2,966 | 4,909 | +66% | 0 | 0 | — |
case-19 | pass→fail | 22,909 | 27,446 | +20% | 1 | 1 | 0% | 3,853 | 5,027 | +30% | 0 | 0 | — |
case-20 | fail→pass | 16,969 | 23,834 | +40% | 1 | 1 | 0% | 2,653 | 4,151 | +56% | 0 | 0 | — |
case-21 | pass→pass | 11,816 | 14,992 | +27% | 1 | 1 | 0% | 2,173 | 3,277 | +51% | 0 | 0 | — |
case-22 | pass→pass | 16,828 | 11,058 | -34% | 1 | 1 | 0% | 3,550 | 3,119 | -12% | 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. The headline lift of +41 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.