Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for DragonRuby development with best practices integration.
.claude/skills/amariahak-cursor-rules-for-dragonruby-development-with-best-practices-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 44% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 25% | 0% |
Cursor rules for DragonRuby development with best practices integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/dragonruby-best-practices-cursorrules-prompt-file.mdc.
You are an expert game developer in Ruby using the DragonRuby Game Toolkit.
Code Style and Structure
Naming Conventions
Syntax and Formatting
Error Handling and Validation
Follow the official DragonRuby Game Toolkit guides for best practices in routing, controllers, models, views, and other Rails components.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 15,796 | 15,930 | +1% | 1 | 1 | 0% | 3,316 | 3,088 | -7% | 0 | 0 | — |
case-02 | fail→pass | 10,567 | 11,877 | +12% | 1 | 1 | 0% | 2,074 | 2,987 | +44% | 0 | 0 | — |
case-03 | fail→fail | 5,501 | 3,940 | -28% | 1 | 1 | 0% | 1,048 | 1,026 | -2% | 0 | 0 | — |
case-04 | pass→pass | 4,316 | 4,652 | +8% | 1 | 1 | 0% | 736 | 1,058 | +44% | 0 | 0 | — |
case-05 | fail→pass | 12,933 | 7,334 | -43% | 1 | 1 | 0% | 2,392 | 1,682 | -30% | 0 | 0 | — |
case-06 | pass→pass | 6,236 | 5,164 | -17% | 1 | 1 | 0% | 1,112 | 1,385 | +25% | 0 | 0 | — |
case-07 | pass→pass | 7,490 | 5,652 | -25% | 1 | 1 | 0% | 1,424 | 1,350 | -5% | 0 | 0 | — |
case-08 | pass→pass | 10,271 | 6,391 | -38% | 1 | 1 | 0% | 1,951 | 1,543 | -21% | 0 | 0 | — |
case-09 | pass→pass | 8,416 | 9,675 | +15% | 1 | 1 | 0% | 1,597 | 1,839 | +15% | 0 | 0 | — |
case-10 | fail→pass | 8,662 | 10,534 | +22% | 1 | 1 | 0% | 1,589 | 2,441 | +54% | 0 | 0 | — |
case-11 | fail→fail | 10,381 | 10,190 | -2% | 1 | 1 | 0% | 2,023 | 2,557 | +26% | 0 | 0 | — |
case-12 | pass→pass | 10,551 | 7,229 | -31% | 1 | 1 | 0% | 2,059 | 1,634 | -21% | 0 | 0 | — |
case-13 | pass→pass | 24,135 | 16,306 | -32% | 1 | 1 | 0% | 5,503 | 3,790 | -31% | 0 | 0 | — |
case-14 | pass→pass | 14,915 | 5,210 | -65% | 1 | 1 | 0% | 1,615 | 1,267 | -22% | 0 | 0 | — |
case-15 | pass→pass | 4,785 | 4,630 | -3% | 1 | 1 | 0% | 837 | 1,245 | +49% | 0 | 0 | — |
case-16 | pass→pass | 5,423 | 6,681 | +23% | 1 | 1 | 0% | 1,173 | 1,741 | +48% | 0 | 0 | — |
case-17 | pass→pass | 10,308 | 7,952 | -23% | 1 | 1 | 0% | 2,105 | 1,926 | -9% | 0 | 0 | — |
case-18 | pass→pass | 6,367 | 4,147 | -35% | 1 | 1 | 0% | 1,031 | 1,067 | +3% | 0 | 0 | — |
case-19 | pass→pass | 10,880 | 11,789 | +8% | 1 | 1 | 0% | 2,106 | 2,643 | +25% | 0 | 0 | — |
case-20 | pass→pass | 5,342 | 4,831 | -10% | 1 | 1 | 0% | 984 | 1,177 | +20% | 0 | 0 | — |
case-21 | pass→pass | 10,710 | 7,238 | -32% | 1 | 1 | 0% | 2,173 | 1,625 | -25% | 0 | 0 | — |
case-22 | pass→pass | 7,001 | 7,302 | +4% | 1 | 1 | 0% | 1,232 | 1,592 | +29% | 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 +14 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.