Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build task dependency graph with predecessor/successor relationships
.claude/skills/yogsoth-ai-dependency-graph-construction/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✓→✓ | ＝ Same ✓ | 28% | 0% |
| case-20 | ✓→✓ | ＝ Same ✓ | 18% | 0% |
| case-21 | ✓→✓ | ＝ Same ✓ | 1% | 0% |
| case-02 | ✗→✗ | ＝ Same ✗ | 37% | 0% |
| case-03 | ✗→✗ | ＝ Same ✗ | -3% | 0% |
Build a task dependency graph from a work breakdown structure. Identify all predecessor/successor relationships, parallel opportunities, and convergence points.
Subagent — spawned via subagent-spawning/spawn-agent skill.
Shared: Used by dependency-constraint strategy and deep-insight campaign.
<!-- 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-22 | pass→pass | 15,741 | 20,365 | +29% | 1 | 1 | 0% | 2,724 | 3,483 | +28% | 0 | 0 | — |
case-02 | fail→fail | 18,511 | 42,285 | +128% | 1 | 1 | 0% | 3,223 | 4,417 | +37% | 0 | 0 | — |
case-03 | fail→fail | 9,522 | 8,661 | -9% | 1 | 1 | 0% | 1,554 | 1,512 | -3% | 0 | 0 | — |
case-01 | fail→fail | 8,036 | 11,220 | +40% | 1 | 1 | 0% | 1,146 | 2,087 | +82% | 0 | 0 | — |
case-04 | fail→fail | 11,843 | 8,258 | -30% | 1 | 1 | 0% | 1,847 | 1,375 | -26% | 0 | 0 | — |
case-05 | fail→fail | 7,223 | 9,243 | +28% | 1 | 1 | 0% | 1,223 | 1,677 | +37% | 0 | 0 | — |
case-06 | fail→fail | 22,151 | 27,264 | +23% | 1 | 1 | 0% | 4,722 | 6,150 | +30% | 0 | 0 | — |
case-07 | fail→fail | 15,547 | 9,135 | -41% | 1 | 1 | 0% | 2,391 | 1,540 | -36% | 0 | 0 | — |
case-08 | fail→fail | 25,097 | 28,699 | +14% | 1 | 1 | 0% | 4,214 | 5,719 | +36% | 0 | 0 | — |
case-15 | fail→fail | 13,535 | 11,019 | -19% | 1 | 1 | 0% | 2,365 | 2,082 | -12% | 0 | 0 | — |
case-09 | fail→fail | 8,255 | 9,729 | +18% | 1 | 1 | 0% | 1,465 | 1,879 | +28% | 0 | 0 | — |
case-10 | fail→fail | 13,973 | 11,252 | -19% | 1 | 1 | 0% | 2,538 | 2,251 | -11% | 0 | 0 | — |
case-11 | fail→fail | 15,123 | 15,250 | +1% | 1 | 1 | 0% | 2,494 | 2,765 | +11% | 0 | 0 | — |
case-12 | fail→fail | 9,248 | 8,336 | -10% | 1 | 1 | 0% | 1,669 | 1,624 | -3% | 0 | 0 | — |
case-13 | fail→fail | 8,353 | 8,563 | +3% | 1 | 1 | 0% | 1,464 | 1,770 | +21% | 0 | 0 | — |
case-14 | fail→fail | 12,665 | 20,028 | +58% | 1 | 1 | 0% | 2,205 | 3,508 | +59% | 0 | 0 | — |
case-16 | fail→fail | 9,264 | 9,337 | +1% | 1 | 1 | 0% | 1,528 | 1,673 | +9% | 0 | 0 | — |
case-17 | fail→fail | 10,910 | 13,941 | +28% | 1 | 1 | 0% | 1,857 | 2,570 | +38% | 0 | 0 | — |
case-18 | fail→fail | 14,165 | 10,282 | -27% | 1 | 1 | 0% | 2,273 | 1,774 | -22% | 0 | 0 | — |
case-19 | fail→fail | 10,745 | 9,162 | -15% | 1 | 1 | 0% | 1,982 | 1,909 | -4% | 0 | 0 | — |
case-20 | pass→pass | 20,708 | 25,283 | +22% | 1 | 1 | 0% | 3,938 | 4,662 | +18% | 0 | 0 | — |
case-21 | pass→pass | 19,171 | 18,884 | -1% | 1 | 1 | 0% | 3,563 | 3,594 | +1% | 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.