Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →TRIZ function analysis: function-level recombination and redistribution
.claude/skills/yogsoth-ai-function-combination/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 86% | 0% |
| case-01 | ✓→✗ | ▼ Worse | -54% | 0% |
| case-02 | ✓→✗ | ▼ Worse | -48% | 0% |
| case-03 | ✓→✗ | ▼ Worse | -55% | 0% |
TRIZ function analysis: function-level recombination and redistribution. Decompose systems into functions and recombine them in novel ways — moving functions between components, merging functions, or splitting them to create new system architectures.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 20 | 0 | 0% | | web-research | 8 | 0 | 0% | | paper-overview | 20 | 0 | 0% | | paper-search | 12 | 0 | 0% | | paper-research | 5 | 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 function recombination possibilities | | emergence-detection | Detect emergent capabilities from function redistribution |
| SOP | Role | |-----|------| | function-redistribution | Redistribute functions across components | | emergent-property-identification | Identify emergent properties from recombination | | input-space-construction | Build function spaces for system components | | combinatorial-synthesis | Synthesize function combination outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | emergence-detection | Detect and validate emergent properties from combinations. Orchestrates emergent-property-identification → blend-elaboration. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | combinatorial-synthesis | Synthesize all combinatorial creativity outputs | | emergent-property-identification | Identify non-additive properties from combinations | | function-redistribution | Redistribute functions across different components | | input-space-construction | Build input spaces for two source concepts |
<!-- 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 | pass→fail | 16,481 | 15,331 | -7% | 1 | 1 | 0% | 2,634 | 1,203 | -54% | 0 | 0 | — |
case-02 | pass→fail | 17,588 | 9,628 | -45% | 1 | 1 | 0% | 2,257 | 1,166 | -48% | 0 | 0 | — |
case-03 | pass→fail | 17,888 | 9,844 | -45% | 1 | 1 | 0% | 2,379 | 1,059 | -55% | 0 | 0 | — |
case-04 | pass→pass | 17,271 | 40,366 | +134% | 1 | 1 | 0% | 2,480 | 6,562 | +165% | 0 | 0 | — |
case-05 | pass→pass | 14,649 | 20,045 | +37% | 1 | 1 | 0% | 1,986 | 3,257 | +64% | 0 | 0 | — |
case-06 | fail→fail | 18,698 | 24,851 | +33% | 1 | 1 | 0% | 2,591 | 3,998 | +54% | 0 | 0 | — |
case-07 | pass→pass | 14,886 | 29,741 | +100% | 1 | 1 | 0% | 2,043 | 4,586 | +124% | 0 | 0 | — |
case-08 | pass→pass | 16,363 | 23,388 | +43% | 1 | 1 | 0% | 2,112 | 3,234 | +53% | 0 | 0 | — |
case-09 | fail→fail | 16,992 | 34,634 | +104% | 1 | 1 | 0% | 2,138 | 5,092 | +138% | 0 | 0 | — |
case-10 | pass→pass | 18,267 | 19,012 | +4% | 1 | 1 | 0% | 2,583 | 3,201 | +24% | 0 | 0 | — |
case-11 | pass→pass | 14,108 | 21,492 | +52% | 1 | 1 | 0% | 2,030 | 3,817 | +88% | 0 | 0 | — |
case-12 | fail→fail | 19,644 | 44,184 | +125% | 1 | 1 | 0% | 2,850 | 5,918 | +108% | 0 | 0 | — |
case-13 | fail→pass | 9,252 | 13,912 | +50% | 1 | 1 | 0% | 1,418 | 2,742 | +93% | 0 | 0 | — |
case-14 | pass→fail | 15,741 | 26,203 | +66% | 1 | 1 | 0% | 2,168 | 4,121 | +90% | 0 | 0 | — |
case-15 | pass→fail | 14,415 | 32,254 | +124% | 1 | 1 | 0% | 2,121 | 4,592 | +117% | 0 | 0 | — |
case-16 | fail→fail | 16,792 | 22,231 | +32% | 1 | 1 | 0% | 2,441 | 3,804 | +56% | 0 | 0 | — |
case-17 | fail→fail | 17,672 | 9,230 | -48% | 1 | 1 | 0% | 2,441 | 1,204 | -51% | 0 | 0 | — |
case-18 | fail→pass | 16,019 | 31,221 | +95% | 1 | 1 | 0% | 2,333 | 4,346 | +86% | 0 | 0 | — |
case-19 | pass→pass | 16,599 | 27,170 | +64% | 1 | 1 | 0% | 2,366 | 4,448 | +88% | 0 | 0 | — |
case-20 | pass→fail | 26,676 | 38,767 | +45% | 1 | 1 | 0% | 3,652 | 6,163 | +69% | 0 | 0 | — |
case-21 | pass→fail | 13,294 | 22,462 | +69% | 1 | 1 | 0% | 2,160 | 3,964 | +84% | 0 | 0 | — |
case-22 | pass→fail | 21,255 | 32,455 | +53% | 1 | 1 | 0% | 3,307 | 5,440 | +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 -43 percentage points is the difference between those two pass rates over the 18 comparable cases. 8 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.