Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate combination paths through consistent space
.claude/skills/yogsoth-ai-path-generation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✓→✓ | ＝ Same ✓ | 5% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | -19% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 341% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | 19% | 0% |
| case-02 | ✗→✗ | ＝ Same ✗ | -84% | 0% |
Generate combination paths through the consistent solution space, prioritizing unexplored and novel configurations.
Subagent — spawned via subagent-spawning/spawn-agent skill.
Path generation requires strategic traversal of the reduced solution space, selecting configurations that maximize coverage, novelty, and diversity rather than random sampling.
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
<!-- 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 | 24,979 | 25,464 | +2% | 1 | 1 | 0% | 3,036 | 3,607 | +19% | 0 | 0 | — |
case-02 | fail→fail | 39,594 | 10,211 | -74% | 1 | 1 | 0% | 5,903 | 954 | -84% | 0 | 0 | — |
case-03 | fail→fail | 21,749 | 15,636 | -28% | 1 | 1 | 0% | 2,640 | 2,641 | +0% | 0 | 0 | — |
case-04 | pass→pass | 11,694 | 21,152 | +81% | 1 | 1 | 0% | 2,034 | 2,129 | +5% | 0 | 0 | — |
case-05 | pass→pass | 13,309 | 11,480 | -14% | 1 | 1 | 0% | 1,850 | 1,497 | -19% | 0 | 0 | — |
case-06 | pass→pass | 3,527 | 17,476 | +395% | 1 | 1 | 0% | 564 | 2,488 | +341% | 0 | 0 | — |
case-07 | fail→fail | 4,507 | 28,419 | +531% | 1 | 1 | 0% | 794 | 4,160 | +424% | 0 | 0 | — |
case-08 | fail→fail | 16,412 | 35,072 | +114% | 1 | 1 | 0% | 1,593 | 5,560 | +249% | 0 | 0 | — |
case-09 | fail→fail | 25,190 | 21,018 | -17% | 1 | 1 | 0% | 4,261 | 871 | -80% | 0 | 0 | — |
case-10 | fail→fail | 8,982 | 31,433 | +250% | 1 | 1 | 0% | 1,616 | 4,896 | +203% | 0 | 0 | — |
case-11 | fail→fail | 14,478 | 16,464 | +14% | 1 | 1 | 0% | 1,751 | 3,224 | +84% | 0 | 0 | — |
case-12 | fail→fail | 19,327 | 22,321 | +15% | 1 | 1 | 0% | 3,862 | 3,542 | -8% | 0 | 0 | — |
case-13 | fail→fail | 8,681 | 27,157 | +213% | 1 | 1 | 0% | 608 | 3,892 | +540% | 0 | 0 | — |
case-14 | fail→fail | 19,673 | 13,996 | -29% | 1 | 1 | 0% | 2,342 | 1,725 | -26% | 0 | 0 | — |
case-15 | fail→fail | 8,627 | 48,211 | +459% | 1 | 1 | 0% | 1,347 | 5,733 | +326% | 0 | 0 | — |
case-16 | fail→fail | 14,331 | 10,802 | -25% | 1 | 1 | 0% | 1,399 | 1,875 | +34% | 0 | 0 | — |
case-17 | fail→fail | 15,303 | 23,597 | +54% | 1 | 1 | 0% | 1,934 | 4,491 | +132% | 0 | 0 | — |
case-18 | fail→fail | 14,727 | 16,698 | +13% | 1 | 1 | 0% | 1,516 | 2,027 | +34% | 0 | 0 | — |
case-19 | fail→fail | 9,084 | 14,411 | +59% | 1 | 1 | 0% | 504 | 1,637 | +225% | 0 | 0 | — |
case-20 | fail→fail | 12,851 | 22,097 | +72% | 1 | 1 | 0% | 2,198 | 2,830 | +29% | 0 | 0 | — |
case-21 | fail→fail | 15,407 | 22,593 | +47% | 1 | 1 | 0% | 2,609 | 3,161 | +21% | 0 | 0 | — |
case-22 | fail→fail | 18,002 | 31,665 | +76% | 1 | 1 | 0% | 2,051 | 4,573 | +123% | 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 0 percentage points is the difference between those two pass rates over the 22 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.