Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems.
.claude/skills/davila7-sql-pro/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-13 | ✓→✗ | ▼ Worse | 73% | 0% |
| case-10 | ✓→✓ | = Same ✓ | 66% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 70% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 78% | 0% |
You are an expert SQL specialist mastering modern database systems, performance optimization, and advanced analytical techniques across cloud-native and hybrid OLTP/OLAP environments.
Expert SQL professional focused on high-performance database systems, advanced query optimization, and modern data architecture. Masters cloud-native databases, hybrid transactional/analytical processing (HTAP), and cutting-edge SQL techniques to deliver scalable and efficient data solutions for enterprise applications.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-10 | pass→pass | 12,388 | 13,085 | +6% | 1 | 1 | 0% | 2,409 | 3,993 | +66% | 0 | 0 | — |
case-01 | fail→fail | 15,289 | 16,510 | +8% | 1 | 1 | 0% | 3,149 | 4,752 | +51% | 0 | 0 | — |
case-02 | pass→pass | 10,439 | 10,985 | +5% | 1 | 1 | 0% | 2,161 | 3,669 | +70% | 0 | 0 | — |
case-03 | pass→pass | 8,444 | 9,352 | +11% | 1 | 1 | 0% | 1,753 | 3,122 | +78% | 0 | 0 | — |
case-09 | pass→pass | 12,235 | 12,939 | +6% | 1 | 1 | 0% | 2,357 | 3,789 | +61% | 0 | 0 | — |
case-04 | fail→pass | 17,206 | 19,555 | +14% | 1 | 1 | 0% | 3,214 | 4,965 | +54% | 0 | 0 | — |
case-05 | fail→fail | 11,493 | 10,464 | -9% | 1 | 1 | 0% | 2,150 | 3,337 | +55% | 0 | 0 | — |
case-06 | pass→pass | 10,435 | 13,264 | +27% | 1 | 1 | 0% | 1,975 | 3,913 | +98% | 0 | 0 | — |
case-07 | pass→pass | 10,401 | 9,065 | -13% | 1 | 1 | 0% | 2,001 | 3,223 | +61% | 0 | 0 | — |
case-08 | pass→pass | 8,335 | 8,644 | +4% | 1 | 1 | 0% | 1,581 | 2,997 | +90% | 0 | 0 | — |
case-11 | pass→pass | 11,971 | 11,443 | -4% | 1 | 1 | 0% | 2,114 | 3,535 | +67% | 0 | 0 | — |
case-12 | pass→pass | 8,611 | 8,317 | -3% | 1 | 1 | 0% | 1,680 | 2,974 | +77% | 0 | 0 | — |
case-13 | pass→fail | 14,019 | 18,434 | +31% | 1 | 1 | 0% | 2,894 | 5,004 | +73% | 0 | 0 | — |
case-14 | pass→pass | 9,846 | 10,364 | +5% | 1 | 1 | 0% | 1,793 | 3,280 | +83% | 0 | 0 | — |
case-15 | pass→pass | 12,547 | 15,740 | +25% | 1 | 1 | 0% | 2,292 | 4,354 | +90% | 0 | 0 | — |
case-16 | pass→pass | 16,007 | 16,359 | +2% | 1 | 1 | 0% | 2,945 | 4,678 | +59% | 0 | 0 | — |
case-17 | pass→pass | 14,200 | 16,059 | +13% | 1 | 1 | 0% | 2,363 | 4,105 | +74% | 0 | 0 | — |
case-18 | pass→pass | 8,516 | 10,355 | +22% | 1 | 1 | 0% | 1,450 | 3,132 | +116% | 0 | 0 | — |
case-19 | pass→pass | 10,061 | 12,630 | +26% | 1 | 1 | 0% | 1,761 | 3,675 | +109% | 0 | 0 | — |
case-20 | pass→pass | 8,249 | 8,523 | +3% | 1 | 1 | 0% | 1,571 | 2,976 | +89% | 0 | 0 | — |
case-21 | pass→pass | 5,270 | 6,590 | +25% | 1 | 1 | 0% | 978 | 2,563 | +162% | 0 | 0 | — |
case-22 | pass→pass | 5,981 | 9,428 | +58% | 1 | 1 | 0% | 1,025 | 3,125 | +205% | 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. 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.