AI · GitHub repo
system-prompts-and-models-of-ai-tools
Repository of extracted system prompts and tools from major AI assistants.
This repository documents leaked and reverse-engineered system prompts, tool schemas, and model configurations from commercial AI tools like Cursor, Lovable, v0, Devin, and Windsurf. It helps developers understand how top AI editors structure interaction rules, XML tags, and file operations. You can study these prompts to design AI products or adapt them into local project rules like Cursor MDC files.
What it's for
- Configure custom coding guidelines and rule files for Cursor or Windsurf
- Study how commercial AI coding tools structure system prompts and tool calling
- Design prompts and interaction protocols for custom AI developer tools
Features
- Includes full prompts from v0, Cursor, Lovable, Devin, Manus, and Claude Code
- Covers tool execution schemas, file operation formats, and XML markup specifications
- Documents internal guidelines for modern web stacks like Tailwind, shadcn, and TanStack
- Openly hosted on GitHub under GPL-3.0
Pricing
Open source. Free and open source
Details
- Type
- GitHub repo
- Category
- AI
- Topic
- System Prompts
- Open source
- Yes
- Platforms
- Web
- For
- Prompt engineers, AI developers, and software engineers using AI coding assistants.
- Tags
- prompts, prompt engineering, cursor, lovable, v0, ai tools
Why it was saved
- @al3rez: Reveals how the most popular AI coding tools are actually instructed, and gives copyable rules to reuse in your own projects or for building an AI coding product.
Related
System prompt to convert rough software ideas into structured, agent-ready PRDs
Curated collection of real-world demo apps built using Cursor AI
Curated repository of prompts and styles for the Gemini Nano Banana model
Open-source framework to apply modular AI prompt patterns via the CLI.
Prompt for drafting detailed PRDs tailored to tools like Cursor and v0
A priming prompt to anchor AI sessions in specific business context
Updated