dontriskit/awesome-ai-system-prompts — explained in plain English
Analysis updated 2026-06-26
Study how top AI products configure their system prompts before building your own AI agent or tool.
Copy and adapt real system prompts from tools like Cline or Bolt as a starting point for your own AI-powered product.
Learn which prompt engineering patterns are common across production AI systems by comparing them side by side.
| dontriskit/awesome-ai-system-prompts | kando-menu/kando | cypress-io/cypress-realworld-app | |
|---|---|---|---|
| Stars | 5,881 | 5,890 | 5,891 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | easy | easy | easy |
| Complexity | 1/5 | 2/5 | 3/5 |
| Audience | developer | general | developer |
Figures from each repo's GitHub metadata at analysis time.
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.
A curated collection of the hidden system prompts used by popular AI tools like ChatGPT, Claude, and Cline, paired with an educational guide explaining what makes these prompts work.
Mainly TypeScript. The stack also includes TypeScript.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.