Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Identify opposing forces that keep gaps open. Uses evaporating cloud to expose hidden assumptions behind conflicts and polarity mapping for unresolvable tensions.
.claude/skills/yogsoth-ai-tension-mining/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 225% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 135% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 104% | 0% |
Identify the opposing forces that keep a gap persistently open.
A gap persists despite awareness — need to understand what structural tensions prevent resolution.
| Base SOP | Target | ±10% Range | |----------|--------|------------| | web-search | 20 | 18–22 | | web-research | 10 | 9–11 | | paper-overview | 30 | 27–33 | | paper-search | 20 | 18–22 | | paper-research | 10 | 9–11 |
<HARD-GATE>
| SOP | Done | Target | % |
|-----|------|--------|---|
| web-search | ? | 20 | ? |
| web-research | ? | 10 | ? |
| paper-overview | ? | 30 | ? |
| paper-search | ? | 20 | ? |
| paper-research | ? | 10 | ? |
Budget Gate: OPEN/CLOSED (>=80% required to exit)
</HARD-GATE>Import: web-search, web-research, paper-overview, paper-search, paper-research Subagent: evaporating-cloud, polarity-mapping
Identify opposing forces that keep the gap open. Use evaporating cloud to expose hidden assumptions behind conflicts. Use polarity mapping for tensions that cannot be resolved (only managed).
Tension Report — identified tensions, evaporating clouds, polarity maps, resolution strategies.
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | dialectical-synthesis | Hegelian thesis-antithesis-synthesis cycle — propose position, generate opposition, structured debate, synthesize transcending insight. Combines evaporating-cloud and polarity-mapping SOPs. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | evaporating-cloud | Model conflicts as Goldratt's Evaporating Cloud — expose hidden assumptions behind opposing needs to dissolve the conflict. | | polarity-mapping | Map unresolvable tensions as Johnson polarities — 4 quadrants (positive/negative of each pole), early warnings, action steps for managing rather than solving. |
<!-- 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→fail | 42,658 | 21,843 | -49% | 1 | 1 | 0% | 5,568 | 1,326 | -76% | 0 | 0 | — |
case-02 | fail→pass | 44,634 | 50,882 | +14% | 1 | 1 | 0% | 8,284 | 8,866 | +7% | 0 | 0 | — |
case-03 | fail→fail | 38,947 | 62,526 | +61% | 1 | 1 | 0% | 6,078 | 8,866 | +46% | 0 | 0 | — |
case-04 | pass→pass | 29,295 | 88,617 | +202% | 1 | 1 | 0% | 2,780 | 8,811 | +217% | 0 | 0 | — |
case-05 | pass→fail | 26,108 | 54,089 | +107% | 1 | 1 | 0% | 3,699 | 8,824 | +139% | 0 | 0 | — |
case-06 | pass→fail | 18,159 | 49,639 | +173% | 1 | 1 | 0% | 2,996 | 7,455 | +149% | 0 | 0 | — |
case-07 | fail→fail | 29,473 | 46,221 | +57% | 1 | 1 | 0% | 3,588 | 7,791 | +117% | 0 | 0 | — |
case-08 | fail→pass | 24,002 | 52,518 | +119% | 1 | 1 | 0% | 2,712 | 8,826 | +225% | 0 | 0 | — |
case-09 | pass→pass | 16,171 | 54,908 | +240% | 1 | 1 | 0% | 2,524 | 6,416 | +154% | 0 | 0 | — |
case-10 | fail→pass | 21,116 | 35,226 | +67% | 1 | 1 | 0% | 3,238 | 6,323 | +95% | 0 | 0 | — |
case-11 | fail→pass | 17,286 | 40,986 | +137% | 1 | 1 | 0% | 2,614 | 6,142 | +135% | 0 | 0 | — |
case-12 | fail→pass | 31,961 | 68,004 | +113% | 1 | 1 | 0% | 4,048 | 8,255 | +104% | 0 | 0 | — |
case-13 | fail→pass | 25,361 | 55,753 | +120% | 1 | 1 | 0% | 3,014 | 8,802 | +192% | 0 | 0 | — |
case-14 | fail→pass | 21,322 | 39,432 | +85% | 1 | 1 | 0% | 3,306 | 6,284 | +90% | 0 | 0 | — |
case-15 | fail→pass | 25,271 | 39,278 | +55% | 1 | 1 | 0% | 3,159 | 6,613 | +109% | 0 | 0 | — |
case-16 | fail→pass | 24,261 | 49,336 | +103% | 1 | 1 | 0% | 3,536 | 8,813 | +149% | 0 | 0 | — |
case-17 | fail→pass | 43,384 | 41,527 | -4% | 1 | 1 | 0% | 3,116 | 6,981 | +124% | 0 | 0 | — |
case-18 | fail→pass | 55,830 | 47,125 | -16% | 1 | 1 | 0% | 8,227 | 7,746 | -6% | 0 | 0 | — |
case-19 | fail→pass | 28,939 | 54,824 | +89% | 1 | 1 | 0% | 3,085 | 7,902 | +156% | 0 | 0 | — |
case-20 | fail→pass | 26,524 | 55,430 | +109% | 1 | 1 | 0% | 3,251 | 7,189 | +121% | 0 | 0 | — |
case-21 | fail→fail | 51,914 | 51,240 | -1% | 1 | 1 | 0% | 7,680 | 8,814 | +15% | 0 | 0 | — |
case-22 | fail→fail | 17,976 | 48,676 | +171% | 1 | 1 | 0% | 2,638 | 1,358 | -49% | 0 | 0 | — |
case-23 | fail→pass | 30,709 | 34,194 | +11% | 1 | 1 | 0% | 3,723 | 5,366 | +44% | 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. 23 cases were attempted, and 21 counted toward the lift figure. The other 2 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 +52 percentage points is the difference between those two pass rates over the 21 comparable cases. 4 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.