Install any skill in seconds. Free to start, no credit card required.
Get Started Free →alinaqi/android-java
Android Java development with MVVM, ViewBinding, and Espresso testing
Passed 20 of 22 test cases with the skill, and 15 of 22 without it.
and 4 more in the full report
6 fixed14 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I'm creating a lint.xml file for an Android project. I want to catch memory leaks and hardcoded text issues. Which severity level should be assigned to HardcodedText and StaticFieldLeak?
| Checked | Without skill | With skill |
|---|---|---|
| HardcodedText issue severity is configured as error in lint.xml. | Missed | Passed |
| StaticFieldLeak issue severity is configured as error in lint.xml. | Passed | Passed |
The instructions your model reads when the skill loads.
project/
├── app/
│ ├── src/
│ │ ├── main/
│ │ │ ├── java/com/example/app/
│ │ │ │ ├── data/ # Data layer
│ │ │ │ │ ├── local/ # Room database, SharedPreferences
│ │ │ │ │ ├── remote/ # Retrofit services, API clients
│ │ │ │ │ └── repository/ # Repository implementations
│ │ │ │ ├── di/ # Dependency injection (Hilt/Dagger)
│ │ │ │ ├── domain/ # Business logic
│ │ │ │ │ ├── model/ # Domain models
│ │ │ │ │ ├── repository/ # Repository interfaces
│ │ │ │ │ └── usecase/ # Use cases
│ │ │ │ ├── ui/ # Presentation layer
│ │ │ │ │ ├── feature/ # Feature screens
│ │ │ │ │ │ ├── FeatureActivity.java
│ │ │ │ │ │ ├── FeatureFragment.java
│ │ │ │ │ │ └── FeatureViewModel.java
│ │ │ │ │ └── common/ # Shared UI components
│ │ │ │ └── App.java # Application class
│ │ │ ├── res/
│ │ │ │ ├── layout/
│ │ │ │ ├── values/
│ │ │ │ └── drawable/
│ │ │ └── AndroidManifest.xml
│ │ ├── test/ # Unit tests
│ │ └── androidTest/ # Instrumentation tests
│ └── build.gradle
├── build.gradle # Project-level build file
├── gradle.properties
├── settings.gradle
test cases passed, vs 15 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.