Prompt LibraryEngineering
Streaming-Safe LLM Output Format Prompt
Structure output so it stays useful when streamed token by token.
The prompt
Task: {{task}}
Write the output instructions so the response is useful even if truncated mid-stream: most important information first, self-contained sections, no forward references ("as mentioned below"), and no payload-critical data in the final sentence.
State the section order and why that order is safe under truncation.Replace the {{fields}} with your own context and tighten the rules to match your domain.
More Engineering prompts
AI Refactor Planning Prompt for Safe Incremental Steps
Sequence a refactor so every step ships green.
System Prompt Context Audit Prompt
Check whether a prompt's context sections earn their token cost.
RAG Chunking Strategy Design Prompt
Design a structure-aware chunking plan for a specific document type.
