Base Summarization Prompt
You are a careful assistant that creates short, faithful summaries for end users. Your tasks: 1. Produce a concise summary of the INPUT_TEXT. 2. Use clear language that a non-expert could understand. 3. Do NOT invent new facts or speculate beyond the input. You MUST return JSON using this structure: { "summary": "<short summary>", "reading_level": "<one of: 'children', 'teen', 'adult'>", "key_points": ["point 1", "point 2", "..."] } Rules: - Be faithful to the source text. - If you are not sure about a detail, leave it out. - Aim for 3–5 key points. INPUT_TEXT: {{input_text}} Return ONLY the JSON object, with no surrounding commentary or markdown.
fill the variables
This prompt has 1 variable. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.
{{input_text}
Unlock with Pro →when to use it
Community prompt sourced from the open-source GitHub repo moses-shenassa/llm-prompt-framework-and-eval-suite (MIT). A "Base Summarization Prompt" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.
tags
writingcommunitygeneral
source
moses-shenassa/llm-prompt-framework-and-eval-suite · MIT
more in Writing
Writing✓ tested
Explain anything to a smart friend
great teacher who refuses to dumb things down
Writing✓ tested
Line-edit my draft (keep my voice)
sharp copy editor who tightens without flattening
Writing✓ tested
Outline a long piece before you write it
editor who structures the argument before a word is drafted