Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate compressed conflicts (oxymorons) from problem contradictions and extract concrete idea directions from the symbolic tension.
.claude/skills/yogsoth-ai-compressed-conflict/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 7% | 0% |
Generate compressed conflicts (oxymorons) from problem contradictions and extract concrete idea directions.
Identify the core contradiction in the problem and compress it into 2-3 word oxymorons using symbolic-compression SOP. Generate multiple oxymorons capturing different facets of the tension.
Take the most evocative oxymorons and deepen them through analogy chaining using analogy-chain SOP. Each layer reveals new aspects of the contradiction and potential resolution paths.
Extract concrete idea directions from the symbolic tensions. Each oxymoron should suggest at least one mechanism that resolves the contradiction it embodies.
| Metric | Floor | |--------|-------| | Contradictions identified | ≥2 | | Oxymorons generated | ≥4 | | Oxymorons with concrete idea directions | ≥2 | | Analogy chain depth | ≥3 layers |
| SOP | Role | |-----|------| | symbolic-compression | Stage 1 — compress contradictions into oxymorons | | analogy-chain | Stage 2 — deepen oxymorons through layers | | springboard-launch | Stage 3 — convert symbolic insights to solutions | | synectics-synthesis | Post — synthesize compressed conflict outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | analogy-chain | Chain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface. | | springboard-launch | Convert analogy insights into concrete feasible solutions. Transform abstract connections into actionable mechanisms. | | symbolic-compression | Compress problem contradiction into 2-3 word oxymoron. Produces oxymorons with interpretation directions for each. |
<!-- 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 | 20,916 | 22,104 | +6% | 1 | 1 | 0% | 3,328 | 3,776 | +13% | 0 | 0 | — |
case-02 | pass→fail | 15,488 | 25,892 | +67% | 1 | 1 | 0% | 2,368 | 4,501 | +90% | 0 | 0 | — |
case-03 | pass→fail | 10,803 | 22,698 | +110% | 1 | 1 | 0% | 1,758 | 4,160 | +137% | 0 | 0 | — |
case-04 | fail→fail | 5,294 | 20,851 | +294% | 1 | 1 | 0% | 970 | 3,913 | +303% | 0 | 0 | — |
case-05 | fail→pass | 18,475 | 17,441 | -6% | 1 | 1 | 0% | 2,800 | 3,324 | +19% | 0 | 0 | — |
case-06 | fail→pass | 22,716 | 25,699 | +13% | 1 | 1 | 0% | 3,438 | 4,373 | +27% | 0 | 0 | — |
case-07 | pass→pass | 19,992 | 19,382 | -3% | 1 | 1 | 0% | 2,882 | 3,223 | +12% | 0 | 0 | — |
case-08 | fail→pass | 26,922 | 21,114 | -22% | 1 | 1 | 0% | 3,687 | 3,438 | -7% | 0 | 0 | — |
case-09 | fail→pass | 22,271 | 20,475 | -8% | 1 | 1 | 0% | 3,131 | 3,340 | +7% | 0 | 0 | — |
case-10 | pass→pass | 22,857 | 17,975 | -21% | 1 | 1 | 0% | 3,795 | 2,918 | -23% | 0 | 0 | — |
case-11 | pass→pass | 20,902 | 19,937 | -5% | 1 | 1 | 0% | 2,918 | 3,243 | +11% | 0 | 0 | — |
case-12 | pass→pass | 22,408 | 36,559 | +63% | 1 | 1 | 0% | 3,003 | 6,012 | +100% | 0 | 0 | — |
case-13 | pass→pass | 24,264 | 23,151 | -5% | 1 | 1 | 0% | 3,364 | 3,881 | +15% | 0 | 0 | — |
case-14 | pass→pass | 12,714 | 17,642 | +39% | 1 | 1 | 0% | 1,929 | 3,014 | +56% | 0 | 0 | — |
case-15 | pass→pass | 20,639 | 20,601 | -0% | 1 | 1 | 0% | 3,083 | 3,364 | +9% | 0 | 0 | — |
case-16 | pass→pass | 19,082 | 20,940 | +10% | 1 | 1 | 0% | 2,629 | 3,560 | +35% | 0 | 0 | — |
case-17 | pass→pass | 15,233 | 19,585 | +29% | 1 | 1 | 0% | 2,183 | 3,296 | +51% | 0 | 0 | — |
case-18 | pass→pass | 17,079 | 17,399 | +2% | 1 | 1 | 0% | 2,371 | 2,942 | +24% | 0 | 0 | — |
case-19 | pass→pass | 18,231 | 21,475 | +18% | 1 | 1 | 0% | 2,563 | 3,498 | +36% | 0 | 0 | — |
case-20 | pass→pass | 17,741 | 20,240 | +14% | 1 | 1 | 0% | 2,614 | 3,563 | +36% | 0 | 0 | — |
case-21 | pass→pass | 15,480 | 22,484 | +45% | 1 | 1 | 0% | 2,569 | 3,630 | +41% | 0 | 0 | — |
case-22 | pass→pass | 20,429 | 21,086 | +3% | 1 | 1 | 0% | 3,023 | 3,485 | +15% | 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 +14 percentage points is the difference between those two pass rates over the 22 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.