Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Flutter development with expert integration.
.claude/skills/amariahak-cursor-rules-for-flutter-development-with-expert-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -16% | 0% |
| case-03 | ✓→✓ | = Same ✓ | -9% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 13% | 0% |
| case-07 | ✓→✓ | = Same ✓ | 25% | 0% |
Cursor rules for Flutter development with expert integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/flutter-app-expert-cursorrules-prompt-file.mdc.
// Flutter App Expert .cursorrules
// Flexibility Notice
// Note: This is a recommended project structure, but be flexible and adapt to existing project structures. // Do not enforce these structural patterns if the project follows a different organization. // Focus on maintaining consistency with the existing project architecture while applying Flutter best practices.
// Flutter Best Practices
const flutterBestPractices = "Adapt to existing project architecture while maintaining clean code principles", "Use Flutter 3.x features and Material 3 design", "Implement clean architecture with BLoC pattern", "Follow proper state management principles", "Use proper dependency injection", "Implement proper error handling", "Follow platform-specific design guidelines", "Use proper localization techniques", ];
// Project Structure
// Note: This is a reference structure. Adapt to the project's existing organization
const projectStructure = lib/ core/ constants/ theme/ utils/ widgets/ features/ feature_name/ data/ datasources/ models/ repositories/ domain/ entities/ repositories/ usecases/ presentation/ bloc/ pages/ widgets/ l10n/ main.dart test/ unit/ widget/ integration/ ;
// Coding Guidelines
const codingGuidelines =
;
// Widget Guidelines
const widgetGuidelines =
;
// Performance Guidelines
const performanceGuidelines =
;
// Testing Guidelines
const testingTestingGuidelines =
;
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 18,027 | 15,959 | -11% | 1 | 1 | 0% | 3,897 | 4,396 | +13% | 0 | 0 | — |
case-02 | fail→fail | 13,936 | 16,633 | +19% | 1 | 1 | 0% | 3,303 | 4,598 | +39% | 0 | 0 | — |
case-03 | pass→pass | 15,635 | 11,121 | -29% | 1 | 1 | 0% | 3,417 | 3,118 | -9% | 0 | 0 | — |
case-04 | fail→pass | 11,400 | 9,170 | -20% | 1 | 1 | 0% | 2,215 | 2,518 | +14% | 0 | 0 | — |
case-05 | pass→pass | 13,440 | 10,730 | -20% | 1 | 1 | 0% | 2,634 | 2,966 | +13% | 0 | 0 | — |
case-06 | fail→pass | 9,468 | 5,464 | -42% | 1 | 1 | 0% | 2,110 | 1,780 | -16% | 0 | 0 | — |
case-07 | pass→pass | 8,536 | 7,646 | -10% | 1 | 1 | 0% | 1,522 | 1,900 | +25% | 0 | 0 | — |
case-08 | pass→pass | 15,480 | 8,701 | -44% | 1 | 1 | 0% | 3,161 | 2,548 | -19% | 0 | 0 | — |
case-09 | pass→pass | 14,267 | 12,133 | -15% | 1 | 1 | 0% | 2,687 | 3,392 | +26% | 0 | 0 | — |
case-10 | fail→fail | 15,039 | 8,057 | -46% | 1 | 1 | 0% | 2,591 | 2,236 | -14% | 0 | 0 | — |
case-11 | pass→pass | 15,716 | 12,089 | -23% | 1 | 1 | 0% | 2,485 | 2,788 | +12% | 0 | 0 | — |
case-12 | pass→pass | 13,049 | 11,488 | -12% | 1 | 1 | 0% | 2,233 | 2,000 | -10% | 0 | 0 | — |
case-13 | pass→pass | 4,685 | 7,698 | +64% | 1 | 1 | 0% | 855 | 2,237 | +162% | 0 | 0 | — |
case-14 | fail→fail | 12,496 | 14,253 | +14% | 1 | 1 | 0% | 2,728 | 2,999 | +10% | 0 | 0 | — |
case-15 | pass→pass | 8,394 | 7,434 | -11% | 1 | 1 | 0% | 1,697 | 2,365 | +39% | 0 | 0 | — |
case-16 | pass→pass | 11,529 | 5,649 | -51% | 1 | 1 | 0% | 2,075 | 1,722 | -17% | 0 | 0 | — |
case-17 | pass→pass | 13,797 | 2,369 | -83% | 1 | 1 | 0% | 1,986 | 1,070 | -46% | 0 | 0 | — |
case-18 | pass→pass | 12,553 | 8,449 | -33% | 1 | 1 | 0% | 2,042 | 2,049 | +0% | 0 | 0 | — |
case-19 | pass→pass | 15,541 | 13,745 | -12% | 1 | 1 | 0% | 2,778 | 3,020 | +9% | 0 | 0 | — |
case-20 | pass→pass | 21,475 | 10,166 | -53% | 1 | 1 | 0% | 3,221 | 2,808 | -13% | 0 | 0 | — |
case-21 | pass→pass | 19,868 | 10,989 | -45% | 1 | 1 | 0% | 2,960 | 2,882 | -3% | 0 | 0 | — |
case-22 | pass→pass | 13,127 | 11,282 | -14% | 1 | 1 | 0% | 2,659 | 2,808 | +6% | 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 +9 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.