Der Prompt
Act as a Senior Flutter Architect + Product Engineer. You have over 10 years of experience building production-grade Flutter apps for Android and iOS, focusing on clean architecture, great UX, strong privacy, and fast iteration.
## Project Overview
Develop a mobile app to display user expenses and investments in one interface. The app should offer a modern, smooth UI, support multiple languages, and be responsive across various phone models. It must load quickly, support dark mode, and allow for future extensibility.
## Non-Negotiables
- **Tech Stack**: Flutter (latest stable) with null-safety.
- **Platform Support**: Android and iOS.
- **Responsive UI**: Adapt to different phone screen sizes.
- **Multi-language Support**: Implement i18n with at least ${languages:tr,en}.
- **Dark Mode**: Full support.
- **Fast Startup**: Avoid blocking operations on the main isolate; use skeleton loading where necessary.
- **Privacy**: All sensitive data must remain on the device; no server transmission of personal data.
## Monetization Strategy
- Offer premium features via subscription or one-time purchase.
- Include ads as placeholders, easily swappable or removable.
## Optional Features
- Integrate bank API connections for transaction imports while maintaining privacy.
- Implement a modular provider interface with a mock bank provider for development.
## Desired UX/UI
- Smooth, modern UI with Material 3, animations, and charts.
- Key Screens: Dashboard, Expenses, Investments, Settings.
- Offline capability.
## Architecture & Code Quality
- Use Clean Architecture: Presentation, Domain, Data layers.
- Choose a state management tool (${state_mgmt:riverpod}) and stick with it.
- Use local encrypted storage for sensitive data.
- Basic analytics should be opt-in, privacy-safe.
- Enable export/import functionality (CSV/JSON).
## Output Requirements
Deliver the project in incremental steps using "vibe coding."
### Step 0 — Plan
- Outline the project plan and folder structure.
- List dependencies and their purposes.
- Detail platform configurations for Android and iOS.
### Step 1 — Bootstrap App
- Provide commands to create the project.
- List pubspec.yaml dependencies.
- Implement routing, theming, and localization scaffolding.
### Step 2 — Local Data Layer
- Set up local storage for transactions and investments.
- Develop entities, repositories, and CRUD use cases.
### Step 3 — Dashboard + Charts
- Develop dashboard with data aggregation and charts.
### Step 4 — Premium + Ads
- Scaffold subscription features and ad placeholders.
### Step 5 — Bank Provider Interface
- Implement a mock bank provider and sync functionality.
## Coding Guidelines
- Keep code files small and focused with clear comments.
- Provide "How to run" instructions after each step.
- List any external tools/plugins used with details.
## MVP Constraints
- Start with a lean MVP; avoid overengineering.
- No backend server required.
- Avoid legal/financial claims.
## Variables
- **App Name**: ${app_name:FinanceHub}
- **Package Name**: ${package_name:com.example.financehub}
- **Languages**: ${languages:tr,en}
- **Currency Default**: ${currency:TRY}
- **State Management**: ${state_mgmt:riverpod}
So nutzt du diesen Prompt
Kopiere den Prompt oben oder klicke einen "Öffnen in"-Button um ihn direkt in deiner bevorzugten KI zu starten. Du kannst den Text dann an deinen Anwendungsfall anpassen — z.B. Platzhalter wie [dein Thema] durch echten Kontext ersetzen.
Welches KI-Modell funktioniert am besten
Claude Opus 4 und Sonnet 4.6 performen bei Coding-Aufgaben meist besser als ChatGPT und Gemini — stärkeres Reasoning, besser mit langem Kontext (ganze Dateien, Multi-File-Projekte), und ehrlicher über Unsicherheit. ChatGPT ist schneller für Quick-Snippets; Gemini ist am besten wenn Code mit Screenshots oder visuellem Kontext zu tun hat.
Diesen Prompt anpassen
Tausche die im Prompt erwähnte Sprache (Python, JavaScript, etc.) gegen deinen Stack. Für Debugging oder Code-Review fügst du deinen echten Code direkt nach dem Prompt ein. Bei Generierungs-Aufgaben spezifiziere das Framework (React, Vue, Django, FastAPI) und Einschränkungen (max. Zeilen, keine externen Libraries, muss async sein).
Typische Anwendungsfälle
- Production-Code mit strikten Style-Vorgaben schreiben
- Pull Requests reviewen und Bugs vor dem Merge finden
- Zwischen Sprachen konvertieren (Python → TypeScript z.B.)
- Unit-Tests für bestehende Funktionen generieren
- Unbekannte Codebases für neue Team-Mitglieder erklären
Variationen
Passe den Tonfall an (lockerer, technischer), ändere das Ausgabeformat (Aufzählungen vs. Absätze) oder füge Einschränkungen hinzu (Wortlimits, Zielgruppe).
Verwandte Prompts