💻 Programmierung & Entwicklung
Kanban Board
Beispiel-Ausgaben
So antworten ChatGPT, Claude und Gemini typischerweise auf diesen Prompt:
I'll create a comprehensive Kanban board application for you! The implementation will feature drag-and-drop functionality using the HTML5 Drag and Drop API, with smooth CSS transitions for card movements. I'll structure it with a main board container, draggable cards with metadata (title, description, labels, due dates, priority), and localStorage integration for data persistence. The design will be fully responsive using CSS Grid and Flexbox, with a clean interface that includes modal dialogs for card editing, a color picker for themes, and keyboard shortcuts (like 'N' for new card, 'E' for edit).
I'd be happy to help you build this Kanban board. I should note that this is quite a comprehensive project that will require several interconnected components. I'll provide you with a modular structure using vanilla JavaScript with clear separation of concerns—a Board class for state management, a DragDrop handler for card movement, and separate modules for persistence and UI rendering. For the drag-and-drop, I'll use the native HTML5 API with visual feedback during dragging, though you might want to consider a library like SortableJS for more complex scenarios.
This Kanban board implementation uses the HTML5 Drag and Drop API with `dragstart`, `dragover`, and `drop` event listeners for card movement. The application employs a Model-View-Controller architecture with localStorage for data persistence (note: localStorage has a 5-10MB limit depending on browser). Cards are represented as objects with properties for title, description, assignee, labels, dueDate, and priority. The responsive design uses CSS Grid with `auto-fit` and `minmax()` for column layout, with media queries for mobile optimization at breakpoints of 768px and 480px.
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).