Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Compress core contradiction into poetic imagery/oxymoron. Use compressed conflicts to reveal hidden solution directions.
.claude/skills/yogsoth-ai-symbolic-analogy/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 126% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 93% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-23 | ✗→✓ | ▲ Improved | 259% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 167% | 0% |
Compress the core contradiction of a problem into poetic imagery or oxymoron, then use the compressed conflict to reveal hidden solution directions.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 15 | 0 | 0% | | web-research | 5 | 0 | 0% | | paper-overview | 15 | 0 | 0% | | paper-search | 10 | 0 | 0% | | paper-research | 3 | 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 | |--------|------| | compressed-conflict | Generate oxymorons and extract idea directions |
| SOP | Role | |-----|------| | symbolic-compression | Compress contradiction into 2-3 word oxymoron | | analogy-chain | Deepen symbolic imagery through layers | | springboard-launch | Convert symbolic insights into solutions | | synectics-synthesis | Synthesize symbolic analogy outputs |
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | compressed-conflict | Generate compressed conflicts (oxymorons) from problem contradictions and extract concrete idea directions from the symbolic tension. |
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. | | synectics-synthesis | Synthesize all synectics outputs into a structured idea report. Combines results from all analogy types and excursion processes. |
<!-- 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→pass | 7,365 | 22,341 | +203% | 1 | 1 | 0% | 1,182 | 3,157 | +167% | 0 | 0 | — |
case-02 | pass→pass | 5,415 | 8,935 | +65% | 1 | 1 | 0% | 843 | 1,283 | +52% | 0 | 0 | — |
case-03 | pass→pass | 16,006 | 31,391 | +96% | 1 | 1 | 0% | 2,298 | 4,301 | +87% | 0 | 0 | — |
case-04 | pass→pass | 23,164 | 31,022 | +34% | 1 | 1 | 0% | 2,609 | 4,591 | +76% | 0 | 0 | — |
case-05 | pass→pass | 27,924 | 48,345 | +73% | 1 | 1 | 0% | 3,479 | 5,677 | +63% | 0 | 0 | — |
case-06 | pass→pass | 19,888 | 29,212 | +47% | 1 | 1 | 0% | 2,986 | 4,976 | +67% | 0 | 0 | — |
case-07 | pass→pass | 25,431 | 24,064 | -5% | 1 | 1 | 0% | 3,056 | 4,261 | +39% | 0 | 0 | — |
case-08 | fail→pass | 18,250 | 39,433 | +116% | 1 | 1 | 0% | 1,881 | 4,246 | +126% | 0 | 0 | — |
case-09 | pass→pass | 23,659 | 31,355 | +33% | 1 | 1 | 0% | 2,762 | 5,399 | +95% | 0 | 0 | — |
case-10 | pass→pass | 22,280 | 33,398 | +50% | 1 | 1 | 0% | 2,658 | 4,936 | +86% | 0 | 0 | — |
case-11 | pass→pass | 13,215 | 23,853 | +80% | 1 | 1 | 0% | 1,342 | 3,501 | +161% | 0 | 0 | — |
case-12 | pass→pass | 29,092 | 30,011 | +3% | 1 | 1 | 0% | 3,599 | 4,526 | +26% | 0 | 0 | — |
case-13 | fail→pass | 18,368 | 23,382 | +27% | 1 | 1 | 0% | 2,022 | 3,912 | +93% | 0 | 0 | — |
case-14 | pass→pass | 22,444 | 35,995 | +60% | 1 | 1 | 0% | 2,499 | 5,675 | +127% | 0 | 0 | — |
case-15 | pass→pass | 23,024 | 47,843 | +108% | 1 | 1 | 0% | 2,661 | 5,615 | +111% | 0 | 0 | — |
case-16 | pass→pass | 16,296 | 24,911 | +53% | 1 | 1 | 0% | 1,766 | 3,164 | +79% | 0 | 0 | — |
case-17 | pass→pass | 19,587 | 27,795 | +42% | 1 | 1 | 0% | 2,882 | 4,254 | +48% | 0 | 0 | — |
case-18 | pass→pass | 26,421 | 54,504 | +106% | 1 | 1 | 0% | 3,223 | 8,561 | +166% | 0 | 0 | — |
case-19 | fail→pass | 12,915 | 8,281 | -36% | 1 | 1 | 0% | 1,303 | 1,194 | -8% | 0 | 0 | — |
case-20 | pass→pass | 22,056 | 38,557 | +75% | 1 | 1 | 0% | 3,986 | 5,578 | +40% | 0 | 0 | — |
case-21 | fail→fail | 9,878 | 15,119 | +53% | 1 | 1 | 0% | 1,487 | 3,577 | +141% | 0 | 0 | — |
case-22 | fail→fail | 18,721 | 20,032 | +7% | 1 | 1 | 0% | 2,418 | 4,030 | +67% | 0 | 0 | — |
case-23 | fail→pass | 14,442 | 30,727 | +113% | 1 | 1 | 0% | 1,441 | 5,179 | +259% | 0 | 0 | — |
case-24 | pass→pass | 9,383 | 26,467 | +182% | 1 | 1 | 0% | 1,500 | 3,862 | +157% | 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. 24 cases were attempted. The headline lift of +17 percentage points is the difference between those two pass rates over the 24 comparable cases.
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.