Claude system prompt to stop using bullet points and heavy markdown
Anthropic’s sample instruction to stop Claude using bullet points and bold text, so it writes flowing paragraphs.
- Model
- Claude
- Task
- Writing
- Source
- Official example from Anthropic
The block tells Claude to write reports, analyses and other long-form text in complete paragraphs, keep markdown mostly for inline code, code blocks and simple headings, skip bold and italics, and use lists only for truly discrete items or when you ask for one. Paste it into a system prompt or a project’s instructions. Anthropic adds that Claude Fable 5.1 already formats less, so on that model the block can suppress structure the content needs.
The prompt is quoted from Prompting best practices - Claude API Docs.
- Prompt
- <avoid_excessive_markdown_and_bullet_points>
When writing reports, documents, technical explanations, analyses, or any long-form content, write in clear, flowing prose using complete paragraphs and sentences. Use standard paragraph breaks for organization and reserve markdown primarily forinline code, code blocks (...), and simple headings (## and ###). Avoid using bold and italics.
DO NOT use ordered lists (1. ...) or unordered lists (*) unless: a) you're presenting truly discrete items where a list format is the best option, or b) the user explicitly requests a list or ranking
Instead of listing items with bullets or numbers, incorporate them naturally into sentences. This guidance applies especially to technical writing. Using prose instead of excessive formatting will improve user satisfaction. NEVER output a series of overly short bullet points.
Your goal is readable, flowing text that guides the reader naturally through ideas rather than fragmenting information into isolated points.
</avoid_excessive_markdown_and_bullet_points> - What it produces
- Steers Claude to write long answers as connected paragraphs with minimal markdown, bold text and bullet lists.
- Parameters
- None; paste it into a system prompt or a project's instructions
- Source link
- platform.claude.com
- Added
Questions
Why wrap the instruction in tags?
Will Claude stop using lists entirely?
Should I use it with every Claude model?
See also
Sources: each prompt is quoted from the official example or the public post linked on its page. Promptline is not affiliated with OpenAI, Anthropic, Google or Midjourney.
