dontriskit/awesome-ai-system-prompts

★ 5,881TypeScriptAudience · developerComplexity · 1/5Setup · easy

Mindmap

mindmap
  root((awesome-ai-system-prompts))
    What it does
      Prompt collection
      Educational guide
      Pattern analysis
    AI tools covered
      ChatGPT
      Claude
      Cline
      Bolt
      Notion
    Key principles
      Role definition
      Tool descriptions
      Safety boundaries
      Step-by-step reasoning
    Audience
      AI builders
      Prompt engineers

mindmap root((awesome-ai-system-prompts)) What it does Prompt collection Educational guide Pattern analysis AI tools covered ChatGPT Claude Cline Bolt Notion Key principles Role definition Tool descriptions Safety boundaries Step-by-step reasoning Audience AI builders Prompt engineers

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Study how top AI products configure their system prompts before building your own AI agent or tool.

USE CASE 2

Copy and adapt real system prompts from tools like Cline or Bolt as a starting point for your own AI-powered product.

USE CASE 3

Learn which prompt engineering patterns are common across production AI systems by comparing them side by side.

Tech stack

TypeScript

Getting it running

Difficulty · easy Time to first run · 5min

In plain English

This repository is a collection of system prompts from popular AI tools, paired with a guide explaining how those prompts are structured and why certain patterns work. A system prompt is the hidden set of instructions that shapes how an AI assistant behaves before a user ever types anything. Tools like ChatGPT, Claude, Vercel's v0, Manus, and others all rely on carefully written system prompts to define their personality, capabilities, and limits. The main README doubles as an educational document. It walks through eight recurring principles found in well-designed agentic system prompts: defining the AI's role clearly, organizing instructions with structure, describing tools and when to use them, encouraging step-by-step reasoning, making the AI aware of its environment, constraining it to a specific domain, setting safety boundaries, and establishing a consistent tone. Each principle comes with direct excerpts from real prompts in the collection so readers can see concrete examples rather than abstract advice. The target audience is people building AI-powered tools or agents, sometimes called prompt engineers. If you are wiring up an AI model to perform tasks automatically and you want to understand how established products configure their AI, this repository gives you both the raw materials and a framework for thinking about them. Beyond the guide, the repository stores the actual prompt files for systems like Claude, ChatGPT, Cline, Bolt, Windsurf, Notion, and others. These are organized by product name so they can be read and compared side by side. The full README is longer than what was shown.

Copy-paste prompts

Prompt 1

I'm building an AI coding assistant. Using the patterns from this collection, write a system prompt that defines the AI's role, lists its available tools, and sets safety boundaries.

Prompt 2

Compare the system prompts from Claude and ChatGPT in this repo, what are the three biggest structural differences in how they define AI behavior?

Prompt 3

Using the 8 principles from this repo's README, critique and rewrite this system prompt I wrote for my AI agent: [paste your prompt here].

Prompt 4

Based on the agentic prompt patterns in this collection, write a system prompt for an AI that helps product managers write clear user stories.

Open on GitHub → Explain another repo

← dontriskit on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.