Feature Addition by Conversation
Starting with architecture explanation catches misunderstandings before code is written. The backend-to-frontend order prevents UI code that references non-existent APIs.
I have an existing {{framework}} application. I want to add a new feature.\n\nCurrent app description: {{app_description}}\nExisting file structure:\n{{file_structure}}\n\nNew feature: {{feature_description}}\n\nPlease:\n1. Explain how this feature fits into the existing architecture\n2. List every file that needs to be created or modified\n3. Implement the changes file by file, starting with data/backend changes and ending with UI\n4. After all changes, explain how to test the new feature\n\nImportant: Do not modify any existing functionality. The new feature should be additive only.
Variables to customize
Why this prompt works
Starting with architecture explanation catches misunderstandings before code is written. The backend-to-frontend order prevents UI code that references non-existent APIs.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Tool Selection AgentThe ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Prompt CompressorExplicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.
Memory Management AgentExplicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.