Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate structured description of design space
.claude/skills/yogsoth-ai-design-space-visualization/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-20 | ✓→✗ | ▼ Worse | -74% | 0% |
| case-21 | ✓→✗ | ▼ Worse | -4% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | 12% | 0% |
| case-10 | ✗→✗ | ＝ Same ✗ | 17% | 0% |
| case-16 | ✗→✗ | ＝ Same ✗ | 86% | 0% |
Generate a structured textual description of the design space showing explored, unexplored, and infeasible regions.
Subagent — spawned via subagent-spawning/spawn-agent skill.
Design space visualization requires synthesizing matrix structure, coverage data, and white-space analysis into a coherent spatial description that communicates opportunity zones.
<!-- 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-10 | fail→fail | 15,484 | 15,340 | -1% | 1 | 1 | 0% | 2,310 | 2,708 | +17% | 0 | 0 | — |
case-16 | fail→fail | 8,954 | 14,453 | +61% | 1 | 1 | 0% | 1,451 | 2,696 | +86% | 0 | 0 | — |
case-02 | fail→fail | 16,808 | 23,580 | +40% | 1 | 1 | 0% | 2,673 | 4,390 | +64% | 0 | 0 | — |
case-01 | fail→fail | 20,911 | 22,554 | +8% | 1 | 1 | 0% | 3,495 | 3,919 | +12% | 0 | 0 | — |
case-09 | fail→fail | 16,243 | 23,507 | +45% | 1 | 1 | 0% | 2,533 | 2,716 | +7% | 0 | 0 | — |
case-03 | fail→fail | 18,888 | 23,618 | +25% | 1 | 1 | 0% | 3,277 | 4,218 | +29% | 0 | 0 | — |
case-04 | fail→fail | 14,022 | 16,779 | +20% | 1 | 1 | 0% | 2,511 | 3,140 | +25% | 0 | 0 | — |
case-05 | fail→fail | 80,040 | 18,524 | -77% | 1 | 1 | 0% | 2,849 | 2,986 | +5% | 0 | 0 | — |
case-06 | fail→fail | 14,724 | 13,384 | -9% | 1 | 1 | 0% | 2,722 | 2,467 | -9% | 0 | 0 | — |
case-07 | fail→fail | 15,636 | 19,458 | +24% | 1 | 1 | 0% | 2,564 | 3,450 | +35% | 0 | 0 | — |
case-08 | fail→fail | 13,469 | 11,684 | -13% | 1 | 1 | 0% | 2,082 | 2,023 | -3% | 0 | 0 | — |
case-11 | fail→fail | 19,805 | 24,575 | +24% | 1 | 1 | 0% | 3,466 | 3,562 | +3% | 0 | 0 | — |
case-12 | fail→fail | 12,734 | 16,258 | +28% | 1 | 1 | 0% | 2,273 | 3,180 | +40% | 0 | 0 | — |
case-13 | fail→fail | 22,617 | 11,643 | -49% | 1 | 1 | 0% | 3,845 | 2,088 | -46% | 0 | 0 | — |
case-14 | fail→fail | 6,249 | 12,519 | +100% | 1 | 1 | 0% | 1,000 | 2,264 | +126% | 0 | 0 | — |
case-15 | fail→fail | 21,098 | 17,909 | -15% | 1 | 1 | 0% | 3,555 | 2,924 | -18% | 0 | 0 | — |
case-17 | fail→fail | 17,281 | 20,791 | +20% | 1 | 1 | 0% | 2,866 | 3,699 | +29% | 0 | 0 | — |
case-18 | fail→fail | 14,038 | 19,055 | +36% | 1 | 1 | 0% | 2,422 | 3,605 | +49% | 0 | 0 | — |
case-19 | fail→fail | 13,752 | 13,695 | -0% | 1 | 1 | 0% | 2,028 | 2,377 | +17% | 0 | 0 | — |
case-20 | pass→fail | 22,366 | 16,600 | -26% | 1 | 1 | 0% | 5,140 | 1,360 | -74% | 0 | 0 | — |
case-21 | pass→fail | 18,787 | 17,215 | -8% | 1 | 1 | 0% | 3,014 | 2,892 | -4% | 0 | 0 | — |
case-22 | pass→pass | 22,760 | 25,540 | +12% | 1 | 1 | 0% | 3,694 | 4,149 | +12% | 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 -9 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.
Other measured skills in the registry, with their headline benchmark lift.