Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Top 1% development standard for OC Pipeline and federal-grade construction software. Use when Bill asks to build features, fix bugs, write code, create components, or do any software development work. Activates for requests involving Supabase, Vercel, React, Node.js, database work, API development, or any coding tasks for OC Pipeline or related projects.
.claude/skills/aiskillstore-elite-mvp-master/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-19 | ✗→✓ | ▲ Improved | 205% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 125% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 74% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 76% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 133% | 0% |
Operate as an Elite MVP Master at the top 1% of software development intelligence. Build production-ready, scalable, federal-grade software.
Every response must follow this structure:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-19 | fail→pass | 24,113 | 30,548 | +27% | 1 | 1 | 0% | 1,941 | 5,926 | +205% | 0 | 0 | — |
case-01 | fail→pass | 94,990 | 36,785 | -61% | 1 | 1 | 0% | 3,462 | 7,791 | +125% | 0 | 0 | — |
case-02 | pass→pass | 17,236 | 48,147 | +179% | 1 | 1 | 0% | 3,132 | 5,073 | +62% | 0 | 0 | — |
case-03 | fail→pass | 22,848 | 50,912 | +123% | 1 | 1 | 0% | 4,806 | 8,346 | +74% | 0 | 0 | — |
case-04 | fail→fail | 22,228 | 21,250 | -4% | 1 | 1 | 0% | 3,104 | 3,750 | +21% | 0 | 0 | — |
case-05 | fail→pass | 16,196 | 20,028 | +24% | 1 | 1 | 0% | 2,965 | 5,210 | +76% | 0 | 0 | — |
case-06 | fail→pass | 15,507 | 20,558 | +33% | 1 | 1 | 0% | 1,850 | 4,318 | +133% | 0 | 0 | — |
case-07 | fail→fail | 21,655 | 18,432 | -15% | 1 | 1 | 0% | 3,365 | 3,046 | -9% | 0 | 0 | — |
case-08 | fail→pass | 24,211 | 19,227 | -21% | 1 | 1 | 0% | 3,376 | 4,499 | +33% | 0 | 0 | — |
case-09 | fail→pass | 19,854 | 28,486 | +43% | 1 | 1 | 0% | 3,852 | 5,241 | +36% | 0 | 0 | — |
case-10 | fail→pass | 20,733 | 19,083 | -8% | 1 | 1 | 0% | 3,588 | 4,274 | +19% | 0 | 0 | — |
case-11 | fail→pass | 13,619 | 18,595 | +37% | 1 | 1 | 0% | 1,535 | 3,218 | +110% | 0 | 0 | — |
case-12 | fail→fail | 16,622 | 25,650 | +54% | 1 | 1 | 0% | 3,673 | 5,576 | +52% | 0 | 0 | — |
case-13 | fail→pass | 40,930 | 34,258 | -16% | 1 | 1 | 0% | 7,112 | 8,603 | +21% | 0 | 0 | — |
case-14 | fail→pass | 22,437 | 11,356 | -49% | 1 | 1 | 0% | 3,288 | 2,692 | -18% | 0 | 0 | — |
case-15 | fail→pass | 14,852 | 25,775 | +74% | 1 | 1 | 0% | 1,825 | 5,498 | +201% | 0 | 0 | — |
case-16 | fail→pass | 17,354 | 32,987 | +90% | 1 | 1 | 0% | 1,796 | 6,724 | +274% | 0 | 0 | — |
case-17 | fail→pass | 20,152 | 18,147 | -10% | 1 | 1 | 0% | 3,731 | 2,763 | -26% | 0 | 0 | — |
case-18 | fail→pass | 27,183 | 32,279 | +19% | 1 | 1 | 0% | 4,177 | 6,545 | +57% | 0 | 0 | — |
case-20 | pass→fail | 24,565 | 46,255 | +88% | 1 | 1 | 0% | 3,660 | 5,936 | +62% | 0 | 0 | — |
case-21 | pass→pass | 16,867 | 12,939 | -23% | 1 | 1 | 0% | 2,722 | 2,481 | -9% | 0 | 0 | — |
case-22 | pass→pass | 25,524 | 22,815 | -11% | 1 | 1 | 0% | 2,921 | 2,652 | -9% | 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 +64 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.