Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Map technical functions to biological systems. Orchestrates problem-biologization → organism-discovery → functional-model-biology.
.claude/skills/yogsoth-ai-biological-function-mapping/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 120% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -45% | 0% |
Map technical functions to biological systems via biologize→discover→model pipeline.
Translate the technical problem into a biological function need statement using problem-biologization SOP. Frame in terms of what function nature must achieve, not how.
Search for organisms that solve the biologized problem using organism-discovery SOP. Identify champion organisms across multiple phyla/kingdoms for diversity.
For each promising organism, build a functional model (energy/matter/information flows) using functional-model-biology SOP. Identify the mechanism that achieves the target function.
| Metric | Floor | |--------|-------| | Biological function statements | ≥2 | | Organisms discovered | ≥5 | | Biological systems mapped to technical functions | ≥3 | | Functional models completed | ≥3 |
| SOP | Role | |-----|------| | problem-biologization | Stage 1 — translate technical→biological | | organism-discovery | Stage 2 — find champion organisms | | functional-model-biology | Stage 3 — build functional models | | biological-strategy-extraction | Post — extract transferable strategies | | web-search | Support — search for biological solutions | | paper-overview | Support — find academic biology sources |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | functional-model-biology | Build biological system functional model. Map energy, matter, and information flows. | | organism-discovery | Find organisms solving similar problems. Search across kingdoms for biological champions. | | problem-biologization | Restate technical problem as biological question. Translate engineering challenges into nature's language. |
<!-- 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 | 36,830 | 40,281 | +9% | 1 | 1 | 0% | 5,114 | 6,626 | +30% | 0 | 0 | — |
case-02 | pass→fail | 24,562 | 10,939 | -55% | 1 | 1 | 0% | 3,525 | 871 | -75% | 0 | 0 | — |
case-03 | pass→pass | 12,287 | 9,946 | -19% | 1 | 1 | 0% | 1,804 | 1,918 | +6% | 0 | 0 | — |
case-04 | pass→pass | 14,156 | 25,327 | +79% | 1 | 1 | 0% | 1,926 | 4,225 | +119% | 0 | 0 | — |
case-05 | fail→pass | 12,970 | 24,844 | +92% | 1 | 1 | 0% | 1,935 | 4,265 | +120% | 0 | 0 | — |
case-15 | pass→pass | 11,708 | 5,016 | -57% | 1 | 1 | 0% | 1,704 | 1,203 | -29% | 0 | 0 | — |
case-06 | fail→pass | 14,358 | 3,483 | -76% | 1 | 1 | 0% | 2,003 | 1,012 | -49% | 0 | 0 | — |
case-07 | fail→pass | 10,186 | 3,937 | -61% | 1 | 1 | 0% | 1,450 | 1,038 | -28% | 0 | 0 | — |
case-08 | pass→pass | 12,020 | 2,554 | -79% | 1 | 1 | 0% | 1,726 | 804 | -53% | 0 | 0 | — |
case-09 | fail→pass | 16,002 | 2,914 | -82% | 1 | 1 | 0% | 2,265 | 858 | -62% | 0 | 0 | — |
case-10 | fail→pass | 15,849 | 5,766 | -64% | 1 | 1 | 0% | 2,404 | 1,320 | -45% | 0 | 0 | — |
case-11 | fail→pass | 12,223 | 3,157 | -74% | 1 | 1 | 0% | 1,709 | 883 | -48% | 0 | 0 | — |
case-12 | fail→pass | 13,585 | 22,071 | +62% | 1 | 1 | 0% | 1,926 | 2,755 | +43% | 0 | 0 | — |
case-13 | pass→pass | 13,921 | 19,953 | +43% | 1 | 1 | 0% | 2,097 | 3,494 | +67% | 0 | 0 | — |
case-14 | fail→pass | 12,623 | 9,012 | -29% | 1 | 1 | 0% | 1,740 | 1,738 | -0% | 0 | 0 | — |
case-16 | fail→pass | 14,599 | 11,483 | -21% | 1 | 1 | 0% | 2,155 | 2,228 | +3% | 0 | 0 | — |
case-17 | fail→pass | 11,953 | 2,813 | -76% | 1 | 1 | 0% | 1,850 | 795 | -57% | 0 | 0 | — |
case-18 | fail→pass | 7,864 | 2,531 | -68% | 1 | 1 | 0% | 1,118 | 785 | -30% | 0 | 0 | — |
case-19 | fail→pass | 10,982 | 4,219 | -62% | 1 | 1 | 0% | 1,581 | 1,002 | -37% | 0 | 0 | — |
case-20 | fail→fail | 28,305 | 35,354 | +25% | 1 | 1 | 0% | 4,849 | 6,607 | +36% | 0 | 0 | — |
case-21 | fail→fail | 11,995 | 28,606 | +138% | 1 | 1 | 0% | 2,210 | 5,195 | +135% | 0 | 0 | — |
case-22 | fail→fail | 10,633 | 14,538 | +37% | 1 | 1 | 0% | 1,736 | 2,859 | +65% | 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 21 counted toward the lift figure. The other 1 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 +45 percentage points is the difference between those two pass rates over the 21 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.