Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Flutter Riverpod.
.claude/skills/amariahak-cursor-rules-for-flutter-riverpod/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 3712% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 147% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 93% | 0% |
Cursor rules for Flutter Riverpod.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/flutter-riverpod-cursorrules-prompt-file.mdc.
You are an AI assistant with advanced problem-solving capabilities. Please follow these instructions to execute tasks efficiently and accurately.
First, confirm the instructions received from the user:
<instructions> {{instructions}} </instructions>
Please proceed with the following process based on these instructions:
<Task Analysis>
Note: Do not change versions listed in the tech stack without approval
Before implementation, verify:
Take sufficient time for this section as it guides the entire subsequent process. Conduct thorough and comprehensive analysis. </Task Analysis>
a. Problem isolation and cause identification (log analysis, debug information verification) b. Creation and implementation of countermeasures c. Post-fix operation verification d. Debug log confirmation and analysis
a. Verification items and expected results b. Actual results and discrepancies c. Required countermeasures (if applicable)
Please report final results in the following format:
markdown
Brief description of overall summary]
...
Details of deliverables, links if applicable]
Please implement following this directory structure:
lib/features/products/ ├── data/ │ ├── models/ │ │ ├── product_dto.dart │ │ └── product_category_dto.dart │ └── product_repository.dart ├── presentation/ │ ├── screens/ │ │ ├── product_list_screen.dart │ │ └── product_details_screen.dart │ ├── controllers/ │ │ └── product_list_controller.dart │ ├── widgets/ │ └── product_card.dart ├── domain/ │ ├── models/ │ │ ├── product.dart │ │ └── product_category.dart │ └── get_products_use_case.dart └── shared/ └── models/ └── address.dart
This document outlines the placement rules for files and folders within the recommended Flutter project structure, focusing on scalability, maintainability, and adherence to Clean Architecture principles.
lib/ ├── features/ ├── models/ ├── providers/ ├── routes/ ├── core/ ├── app.dart └── main.dart
lib/features/ └── <feature_name>/ ├── data/ │ ├── models/ │ └── <feature_name>_repository.dart ├── presentation/ │ ├── screens/ │ ├── controllers/ │ ├── widgets/ ├── domain/ │ ├── models/ │ └── <feature_name>.dart ├── use_cases/ └── shared/ └── models/
lib/shared/ ├── providers/ ├── widgets/ ├── models/ └── services/
lib/models/ └── <model_name>.dart
lib/providers/ └── <provider_name>.dart
lib/core/ ├── network/ │ └── api_client.dart ├── errors/ │ └── exceptions.dart └── di/ └── injection.dart
Please adhere to the above content when executing tasks.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 17,315 | 14,018 | -19% | 1 | 1 | 0% | 2,769 | 4,228 | +53% | 0 | 0 | — |
case-01 | fail→pass | 4,322 | 26,757 | +519% | 1 | 1 | 0% | 212 | 8,082 | +3712% | 0 | 0 | — |
case-02 | pass→pass | 27,770 | 26,492 | -5% | 1 | 1 | 0% | 6,200 | 8,072 | +30% | 0 | 0 | — |
case-03 | pass→pass | 24,795 | 25,856 | +4% | 1 | 1 | 0% | 5,538 | 8,072 | +46% | 0 | 0 | — |
case-05 | pass→pass | 10,195 | 10,159 | -0% | 1 | 1 | 0% | 1,762 | 3,658 | +108% | 0 | 0 | — |
case-06 | pass→pass | 2,944 | 4,556 | +55% | 1 | 1 | 0% | 495 | 2,677 | +441% | 0 | 0 | — |
case-07 | pass→pass | 11,696 | 6,106 | -48% | 1 | 1 | 0% | 2,473 | 2,894 | +17% | 0 | 0 | — |
case-08 | pass→pass | 13,180 | 10,898 | -17% | 1 | 1 | 0% | 2,831 | 4,153 | +47% | 0 | 0 | — |
case-09 | fail→fail | 12,798 | 7,905 | -38% | 1 | 1 | 0% | 2,378 | 3,443 | +45% | 0 | 0 | — |
case-10 | fail→fail | 11,889 | 7,769 | -35% | 1 | 1 | 0% | 2,311 | 3,549 | +54% | 0 | 0 | — |
case-11 | fail→fail | 14,728 | 8,180 | -44% | 1 | 1 | 0% | 2,303 | 3,357 | +46% | 0 | 0 | — |
case-12 | fail→pass | 7,204 | 6,143 | -15% | 1 | 1 | 0% | 1,235 | 3,045 | +147% | 0 | 0 | — |
case-13 | fail→pass | 10,273 | 3,715 | -64% | 1 | 1 | 0% | 1,620 | 2,540 | +57% | 0 | 0 | — |
case-14 | pass→pass | 11,414 | 7,029 | -38% | 1 | 1 | 0% | 1,984 | 3,138 | +58% | 0 | 0 | — |
case-15 | fail→pass | 12,662 | 4,470 | -65% | 1 | 1 | 0% | 2,084 | 2,410 | +16% | 0 | 0 | — |
case-16 | pass→pass | 7,683 | 7,640 | -1% | 1 | 1 | 0% | 1,379 | 3,334 | +142% | 0 | 0 | — |
case-17 | pass→pass | 9,537 | 4,730 | -50% | 1 | 1 | 0% | 1,759 | 2,647 | +50% | 0 | 0 | — |
case-18 | fail→fail | 11,997 | 11,746 | -2% | 1 | 1 | 0% | 2,451 | 4,237 | +73% | 0 | 0 | — |
case-19 | pass→pass | 11,496 | 14,798 | +29% | 1 | 1 | 0% | 2,335 | 4,169 | +79% | 0 | 0 | — |
case-20 | pass→pass | 9,176 | 11,524 | +26% | 1 | 1 | 0% | 1,693 | 4,121 | +143% | 0 | 0 | — |
case-21 | fail→pass | 12,026 | 12,124 | +1% | 1 | 1 | 0% | 2,279 | 4,405 | +93% | 0 | 0 | — |
case-22 | pass→pass | 7,015 | 8,100 | +15% | 1 | 1 | 0% | 1,185 | 3,419 | +189% | 0 | 0 | — |
case-23 | pass→pass | 11,600 | 8,195 | -29% | 1 | 1 | 0% | 2,124 | 3,353 | +58% | 0 | 0 | — |
case-24 | pass→pass | 12,426 | 10,272 | -17% | 1 | 1 | 0% | 2,208 | 3,875 | +75% | 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. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +21 percentage points is the difference between those two pass rates over the 23 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.