continuous-learning-v2
Continuous Learning v2
Instinct-based learning with confidence scoring.
Instinct Structure
{
"id": "compose-state-hoisting",
"type": "pattern",
"description": "Always hoist state to caller in Composables",
"confidence": 0.85,
"examples": [...],
"context": "jetpack-compose",
"lastUsed": "2026-02-02"
}
Confidence Scoring
| Score | Meaning |
|---|---|
| 0.0-0.3 | Experimental |
| 0.3-0.6 | Validated |
| 0.6-0.8 | Established |
| 0.8-1.0 | Best practice |
Confidence increases with:
- Successful application
- User acceptance
- Consistency across sessions
Commands
/instinct-status # View with confidence
/instinct-import <file> # Import from others
/instinct-export # Export for sharing
/evolve # Cluster related instincts
Mobile-Specific Instincts
Pre-configured patterns for:
- Compose recomposition optimization
- MVI state management
- Koin module organization
- Ktor error handling
- Espresso test patterns
Remember: Instincts evolve. Low confidence patterns may become best practices.
More from ahmed3elshaer/everything-claude-code-mobile
mvi-architecture
Model-View-Intent architecture patterns for Android with unidirectional data flow, state management, and side effects.
17koin-patterns
Koin dependency injection patterns for Android with modules, scopes, and ViewModel injection.
17kmp-networking
Ktor client for Kotlin Multiplatform. Shared networking layer with platform-specific engines (OkHttp for Android, Darwin for iOS).
17kmp-di
Dependency Injection for KMP. Koin multiplatform setup, platform modules, and manual DI patterns.
16gradle-patterns
Gradle build configuration patterns for Android including Version Catalogs, convention plugins, build optimization, and multi-module setup.
15kmp-repositories
Repository pattern for Kotlin Multiplatform. Shared interfaces with platform-specific implementations, clean data layer architecture.
15