Prompt engineering · Markdown
A large community collection of prompt personas and reusable instructions.
Search prompts, categories, platforms and repositories
This guide covers zero-shot, few-shot, chain-of-thought, self-consistency, ReAct and more, with figures and cited papers. It is one of the best free starting points for understanding why a prompt works. Examples are educational rather than production templates, so adapt them to your model and task.
Commands are copied from the project documentation at the time of review. Check the repository for the current version.
git clone https://github.com/dair-ai/Prompt-Engineering-Guide.git
The website is the easiest way to read it.
Prompt-Engineering-Guide is a strong default for prompt engineering, but the right choice depends on your stack, licence constraints and how much control you need. These are the projects we compare most often.
Build a reusable editing checklist
Build a reusable editing checklist with a prompt built for ChatGPT and Claude. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
Explain a proof step by step
This copy-ready education prompt helps you explain a proof step by step with fewer blank-page decisions. Paste it into DeepSeek and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
Write a system prompt with a strict output schema
This copy-ready system prompts prompt helps you write a system prompt with a strict output schema with fewer blank-page decisions. Paste it into ChatGPT and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
Adoption questions we hear most often about this project.
Prompt engineering · Markdown
A large community collection of prompt personas and reusable instructions.
Prompt engineering · Markdown
A curated list of autonomous agents, frameworks and agent infrastructure.