Talk Normal Llm Prompt

A system prompt that strips the corporate padding and bullet point bloat from LLM responses while keeping the actual information. You paste it into ChatGPT's custom instructions, Claude project settings, or the system parameter of any API call, and it teaches the model to drop phrases like "I'd be happy to help" and nested lists that say nothing. The repo reports roughly 73% character reduction on GPT-4o and GPT-5.4 in testing. Works across OpenAI, Anthropic, Gemini, and local Ollama models. If you're tired of scrolling past three paragraphs of throat-clearing to get a two sentence answer, this does exactly one thing well.