Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Calculate project, feeding, and resource buffers — shared with implementation-planning
.claude/skills/yogsoth-ai-buffer-sizing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✓→✓ | ＝ Same ✓ | -12% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 15% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | -34% | 0% |
| case-09 | ✓→✓ | ＝ Same ✓ | 0% | 0% |
| case-10 | ✓→✓ | ＝ Same ✓ | -15% | 0% |
Calculate appropriate project buffer, feeding buffers, and resource buffers for the critical chain using Goldratt's method.
Subagent — spawned via subagent-spawning/spawn-agent skill.
Shared: This SOP is used by resource-constraint and implementation-planning campaigns.
<!-- 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 | 8,437 | 14,262 | +69% | 1 | 1 | 0% | 1,350 | 2,444 | +81% | 0 | 0 | — |
case-02 | fail→fail | 12,031 | 17,597 | +46% | 1 | 1 | 0% | 1,956 | 3,087 | +58% | 0 | 0 | — |
case-03 | fail→fail | 15,751 | 17,387 | +10% | 1 | 1 | 0% | 2,236 | 3,166 | +42% | 0 | 0 | — |
case-04 | pass→pass | 9,534 | 7,787 | -18% | 1 | 1 | 0% | 1,803 | 1,592 | -12% | 0 | 0 | — |
case-05 | pass→pass | 3,453 | 3,506 | +2% | 1 | 1 | 0% | 691 | 792 | +15% | 0 | 0 | — |
case-06 | pass→pass | 12,403 | 7,682 | -38% | 1 | 1 | 0% | 1,929 | 1,264 | -34% | 0 | 0 | — |
case-07 | fail→fail | 7,353 | 6,202 | -16% | 1 | 1 | 0% | 1,166 | 1,148 | -2% | 0 | 0 | — |
case-08 | fail→fail | 7,259 | 5,254 | -28% | 1 | 1 | 0% | 1,441 | 1,157 | -20% | 0 | 0 | — |
case-09 | pass→pass | 5,267 | 4,777 | -9% | 1 | 1 | 0% | 1,031 | 1,030 | -0% | 0 | 0 | — |
case-10 | pass→pass | 4,694 | 3,481 | -26% | 1 | 1 | 0% | 737 | 624 | -15% | 0 | 0 | — |
case-11 | pass→pass | 12,148 | 7,705 | -37% | 1 | 1 | 0% | 1,851 | 1,293 | -30% | 0 | 0 | — |
case-12 | fail→fail | 16,236 | 34,284 | +111% | 1 | 1 | 0% | 2,561 | 6,320 | +147% | 0 | 0 | — |
case-13 | pass→pass | 7,793 | 3,721 | -52% | 1 | 1 | 0% | 1,212 | 725 | -40% | 0 | 0 | — |
case-14 | pass→pass | 5,162 | 6,965 | +35% | 1 | 1 | 0% | 911 | 1,258 | +38% | 0 | 0 | — |
case-15 | pass→pass | 16,106 | 8,824 | -45% | 1 | 1 | 0% | 2,458 | 1,495 | -39% | 0 | 0 | — |
case-16 | pass→pass | 14,193 | 13,238 | -7% | 1 | 1 | 0% | 2,162 | 2,120 | -2% | 0 | 0 | — |
case-17 | pass→pass | 4,852 | 3,497 | -28% | 1 | 1 | 0% | 792 | 736 | -7% | 0 | 0 | — |
case-18 | pass→pass | 10,421 | 5,324 | -49% | 1 | 1 | 0% | 1,470 | 945 | -36% | 0 | 0 | — |
case-19 | pass→pass | 4,000 | 4,724 | +18% | 1 | 1 | 0% | 742 | 914 | +23% | 0 | 0 | — |
case-20 | pass→pass | 7,602 | 6,158 | -19% | 1 | 1 | 0% | 1,205 | 951 | -21% | 0 | 0 | — |
case-21 | pass→pass | 5,528 | 3,891 | -30% | 1 | 1 | 0% | 1,034 | 903 | -13% | 0 | 0 | — |
case-22 | fail→fail | 16,839 | 24,346 | +45% | 1 | 1 | 0% | 2,822 | 4,783 | +69% | 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.