Best AI Prompt Templates & .cursorrules
Discover optimized prompt templates — .cursorrules, SYSTEM_PROMPT.md, and GitHub Copilot prompts. Compatible with any AI assistant including Claude, Cursor, ChatGPT, and Gemini.
What is a AI Prompt Template?
AI Prompt Templates are pre-written instruction sets that shape how AI assistants behave in your projects. They come in many forms — .cursorrules files for Cursor, SYSTEM_PROMPT.md for Claude, .github/prompts/ for Copilot, and .windsurfrules for Windsurf. A good prompt template encodes coding standards, architectural decisions, and team conventions so every AI-generated response follows your project's style. Unlike Skills (which are Claude-specific), prompt templates work with any AI assistant.
Most Popular
GitHub
Spec Kit
Official GitHub toolkit for Spec-Driven Development — bootstraps projects with AI-ready templates and native support for 25+ AI agents (Claude, Cursor, Windsurf, Copilot, Gemini). The Specify CLI sets up PRD/spec workflows and generates per-agent command directories.
browser-use
browser-use — System Prompt
A system prompt that enables AI agents to automate browser tasks, navigate websites, and extract information by operating in an iterative loop. Developers and AI automation engineers use this to enhance AI capabilities for web automation across multiple platforms.
streamlit
streamlit — Cursor Rules
<!-- Generated from e2eplaywright/AGENTS.md. Edit that file instead, then run: uv run python scripts/generateagent_rules.py --> We use playwright with pytest to e2e test Streamlit library. E2E tests verify the complete Streamlit system (frontend, backend, communication, state, visual appearance) fro
Top Rated by Community
See allSpec Kit
Official GitHub toolkit for Spec-Driven Development — bootstraps projects with AI-ready templates and native support for 25+ AI agents (Claude, Cursor, Windsurf, Copilot, Gemini). The Specify CLI sets up PRD/spec workflows and generates per-agent command directories.
browser-use — System Prompt
A system prompt that enables AI agents to automate browser tasks, navigate websites, and extract information by operating in an iterative loop. Developers and AI automation engineers use this to enhance AI capabilities for web automation across multiple platforms.
streamlit — Cursor Rules
<!-- Generated from e2eplaywright/AGENTS.md. Edit that file instead, then run: uv run python scripts/generateagent_rules.py --> We use playwright with pytest to e2e test Streamlit library. E2E tests verify the complete Streamlit system (frontend, backend, communication, state, visual appearance) fro
streamlit — Cursor Rules
Cursor rules that provide AI coding agents with guidance for developing the Streamlit library itself (backend, frontend, protobufs), rather than building Streamlit applications.
GitNexus — Windsurf Rules
Follow .gitnexus/RULES.md for all project context and coding guidelines. This project uses GitNexus MCP for code intelligence. See .gitnexus/RULES.md for available tools and best practices.
tabler — Cursor Rules
When you need to use an icon, always use the Tabler icon include syntax: When linking to other pages, always use the relative page syntax: All pages are statically generated to HTML using Eleventy (11ty). Keep this in mind when:
novu — Cursor Rules
Rules for working with DAL repositories in the Novu monorepo
awesome-cursorrules — Cursor Rules
// Awesome CursorRules // A curated list of awesome .cursorrules files for enhancing Cursor AI experience // General guidelines
medusa — Cursor Rules
This file defines the structure and formatting requirements for creating Medusa tutorials in the directory. All tutorials must follow this structure to ensure consistency and quality. Every tutorial must start with YAML frontmatter containing: After frontmatter, include necessary imports:
mise — Cursor Rules
A Cursor IDE rule enforcing Conventional Commits format for all commit messages and PR titles, helping teams maintain consistent, readable version control history. Developers using Cursor will benefit from automated guidance on proper commit formatting.
forem — Windsurf Rules
This file contains instructions for AI coding assistants working on the Forem codebase (the platform that powers dev.to). Follow these rules and patterns to ensure high-quality contributions. If you are modifying these agent instructions, you MUST replicate your changes across all of Forem's ecosyst
umi — Cursor Rules
1. add a ts file to , the plugin api doc is in . 2. Add to to the part.
zephyr — Copilot Instructions
These instructions are derived from and apply to all AI-assisted contributions to the Zephyr RTOS repository. the file's native comment syntax:
iii — Cursor Rules
You are an expert Documentation Architect using the Divio documentation system. Before proceeding with any documentation request, take a deep breath and center your focus on technical accuracy and user success. 1. Analyze First: When a user requests documentation, first categorize the request into o
SurfSense — System Prompt
You are a Dropbox specialist for the user's connected Dropbox account. Surface the tool's , , , and the you passed inside when the tool returned them. Never invent a field the tool did not return. Return only one JSON object (no markdown or prose outside it):
deepagents — System Prompt
Deep Agents is a system prompt for building intelligent agent assistants with planning, filesystem, and sub-agent capabilities across Claude and other AI platforms. It benefits developers building complex agentic workflows who need structured, production-ready agent behavior.
coreui-free-bootstrap-admin-template — Cursor Rules
This is a Bootstrap 5 admin dashboard template built with CoreUI components. It uses Pug templating, Sass for styles, and vanilla JavaScript for interactivity. 1. Create Pug template in 2. Extend base layout:
datahub — Cursor Rules
A Cursor rules prompt that standardizes the DataHub development workflow by directing developers to use a centralized shell script (datahub-dev.sh) for all build, test, and flag operations. This benefits DataHub contributors by reducing setup friction and ensuring consistent development practices across the team.
inbox-zero — Cursor Rules
This file explains the Knowledge Base feature and how it's implemented. The knowledge base helps users store and manage information that can be used to help draft responses to emails. It acts as a personal database of information that can be referenced when composing replies. Users can create, edit,
woocommerce — Cursor Rules
Branch names should go by the following structure (anything in "{}" brackets is a placeholder). "{short-slug}" should be replaced with a short name that best describes the changes - do ask for confirmation if needed. Make sure each commit addresses an atomic unit of work that independently works. Ma
Humanizer — Copilot Instructions
These instructions apply to the entire repository.
Context-Engineering — System Prompt
A system prompt for Claude Code that enforces defensive security practices and provides CLI guidance, designed to help developers safely use Claude for software engineering tasks while preventing misuse.
RedisInsight — Cursor Rules
For components requiring Router, ThemeProvider, etc., include them in : Create a test store with for Redux-connected components: Use Mock Service Worker for API mocking:
ripple — Copilot Instructions
Ripple is a TypeScript UI framework that combines the best parts of React, Solid, and Svelte. Created by Dominic Gannaway (@trueadm), Ripple is designed to be JS/TS-first with its own file extension that
More Prompt Templates
gocron — Copilot Instructions
Heuristic scoring (no AI key configured).
intentkit — Copilot Instructions
IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.
devin.cursorrules — Cursor Rules
During your interaction with the user, if you find anything reusable in this project (e.g. version of a library, model name), especially about a fix to a mistake you made or a correction you received, you should take note in the section in the file so you will not make the same mistake again. You
FeHelper — Cursor Rules
FeHelper Cursor Rules is a specialized prompt for Chrome extension developers using Cursor IDE to develop and maintain the FeHelper browser extension, providing structured guidelines for project organization, coding standards, and feature module development.
bililive-go — Copilot Instructions
本文档为在此项目中工作的 AI 助手（如 GitHub Copilot、Gemini、Claude、Codex、Antigravity 等）提供指导。 永远使用中文进行交流，包括代码注释和 AI 生成的 markdown 文本。 1. 编译验证：修改代码后必须验证编译通过，绝不能跳过
vibe-tools — Cursor Rules
The changelog should focus on the user-facing changes and user-facing effects of changes. We do not need to record the internal details of changes in the changelog. When updating the changelog stick to the existing writing style and formatting.
byterover-cli — Copilot Instructions
ByteRover CLI () - Interactive REPL with React/Ink TUI oclif v4, TypeScript (ES2022, Node16 modules, strict), React/Ink (TUI), Zustand, axios, socket.io, Mocha + Chai + Sinon + Nock
tmuxp — Windsurf Rules
</pythondocstrings> </testingpractices> <gitcommitstandards>
one — Copilot Instructions
❶ One is a new React framework - target web and native with a single Vite plugin and fully shared code, so you can ship cross-platform nearly as easy as single-platform.
imageflow — Cursor Rules
This rule describes the Continuous Integration and Deployment (CI/CD) workflow for the Imageflow project, primarily defined in and utilizing helper scripts within the directory.
FLAML — Copilot Instructions
FLAML (Fast Library for Automated Machine Learning & Tuning) is a lightweight Python library for efficient automation of machine learning and AI operations. It automates workflow based on large language models, machine learning models, etc. and optimizes their performance. The repository uses pre-co
pollinations — Windsurf Rules
Your Friendly Open-Source Gen-AI Platform
mongo-python-driver — Copilot Instructions
When reviewing code, focus on: Always prioritize security vulnerabilities and performance issues that could impact users. Always suggest changes to improve readability and testability. For example, this suggestion seeks to make the code more readable, reusable, and testable:
skills — System Prompt
A Chinese academic paper editing prompt that removes AI-generated traces and humanizes writing to match natural scholar voice. Benefits researchers, students, and academics writing in Chinese who want their papers to sound authentically human rather than AI-generated.
MQTT-Explorer — Copilot Instructions
1. Long-term memory: If you learn something during a session that would save time in future sessions, add it to 2. Paper knowledge must go: If something is no longer true, update or remove it immediately 3. Evaluate after every session: Consider whether the instructions need updates based on what yo
AI-Infra-Guard — System Prompt
以下是你所需要生成测试用例的对象的描述，也即来自远程MCP服务器的工具描述。你可以使用调用以下工具。 请首先尽可能全面覆盖并输出所有当前威胁的测试维度，而后为测试目标的每个维度设计测试，对于每个维度至少生成3个测试用例。
fluentassertions — Copilot Instructions
The guidelines for this repository are maintained in agents.md at the root of the repository.
Hi.Events — Cursor Rules
See CLAUDE.md for project conventions and development guidelines.
MIRIX — Cursor Rules
MIRIX is a Multi-Agent Personal Assistant with an Advanced Memory System. It features a six-agent memory architecture (Core, Episodic, Semantic, Procedural, Resource, Knowledge Vault) with screen activity tracking and privacy-first design. 1. Follow PEP 8 strictly 3. Documentation
tinymist — Copilot Instructions
This is a Rust+JavaScript repository. It builds: It is primarily responsible for providing integrated typst language service to various editors like VS Code, Neovim, Emacs, and Zed. Please follow these guidelines when contributing: Determine a good PR prefix only by the PR description before work. A
agent-os — System Prompt
You are running inside agentOS, a Linux-like operating system for coding agents. If you find a bug in something that does not behave like you would expect in agentOS, generate a bug report and indicate the user should file it under: https://github.com/rivet-dev/rivet/issues (This repository holds ag
macios — Copilot Instructions
This booster provides AI instructions for the .NET for Apple platforms repository, helping developers understand the codebase structure, comment filtering rules, and organization of iOS, macOS, tvOS, and Mac Catalyst bindings. It's valuable for contributors and maintainers working with this open-source .NET SDK.
ultracite — Cursor Rules
Ultracite is a Cursor rules booster that enforces strict code quality standards for TypeScript/JavaScript projects through automated formatting and linting via Biome. It's designed for developers who want zero-config, opinionated code standards focused on type safety, performance, and maintainability.
panel — Copilot Instructions
A Copilot prompt that roleplays as Linus Torvalds to provide code review and architecture guidance grounded in Linux kernel philosophy and pragmatic software engineering principles.
Recently Updated
See allGitNexus — Windsurf Rules
Follow .gitnexus/RULES.md for all project context and coding guidelines. This project uses GitNexus MCP for code intelligence. See .gitnexus/RULES.md for available tools and best practices.
goldenmatch — Windsurf Rules
Native SQL extensions for GoldenMatch ().
neqsim — Windsurf Rules
Please read and follow the instructions in AGENTS.md. All code MUST compile with Java 8. See AGENTS.md for forbidden features, build commands, code patterns, skills, and the task-solving workflow.
pm-claude-skills — System Prompt
This skill produces a structured contract review identifying key terms, unusual or high-risk clauses, and a plain English summary. Always include the disclaimer that this is not legal advice. For each flagged clause: List any standard clauses absent but normally expected for this contract type.
pbgui — Copilot Instructions
These three steps are REQUIRED after every change, no exception: 1. Changelog — Add entry to . NEVER skip, even for small fixes. 2. serial.txt — If ANY file under , , or any module imported at API startup was changed: increment by 1.
tmuxp — Windsurf Rules
</pythondocstrings> </testingpractices> <gitcommitstandards>
Why use Prompt Templates?
Here's why thousands of developers add these to their AI workflow every week.
Works with any AI
Prompt templates aren't locked to one tool. The same .cursorrules principles translate to Claude, ChatGPT, Copilot, and Gemini.
Zero learning curve
Drop a file into your project root and your AI assistant immediately understands your stack, style, and constraints.
Team-wide consistency
Commit your prompt template to git — every developer on your team gets the same AI behaviour without any extra setup.
Battle-tested
Top-rated templates have been refined by thousands of developers. Start with a proven foundation and customise from there.
How to install
- 1
Find a template
Browse by AI platform (Cursor, Claude, ChatGPT) or use case (coding, writing, DevOps).
- 2
Copy the file
Download or copy the .cursorrules, SYSTEM_PROMPT.md, or equivalent file into your project root.
- 3
Commit it
Commit the file to your repository so every team member gets the same AI behaviour.
- 4
Test it
Open your AI assistant and try a task — the template's instructions will shape the response automatically.
Frequently Asked Questions
Common questions about prompt templates answered.
What is an AI Prompt Template?
An AI Prompt Template is a pre-written instruction set that shapes how an AI assistant behaves in your project. They come in many forms: .cursorrules for Cursor, SYSTEM_PROMPT.md for Claude, .github/prompts/ for GitHub Copilot, and .windsurfrules for Windsurf. A good template encodes your coding standards, architectural decisions, and team conventions so every AI response follows your project's style.
What are .cursorrules files?
.cursorrules files are project-level instruction files placed in the root of your repository. Cursor reads them automatically and applies the instructions to every AI interaction in that project. They're the most widely adopted prompt template format, with hundreds of community-contributed examples on GitHub.
Do prompt templates work with Claude?
Yes. Claude reads SYSTEM_PROMPT.md, CLAUDE.md, and .claude/settings.json files as project-level instructions. You can also place prompt templates in .claude/skills/ for skill-based invocation. Prompt templates tagged as 'Any AI assistant' compatible work across Claude, Cursor, ChatGPT, and Gemini.
How do I create a .cursorrules file?
Create a file named .cursorrules in the root of your project. Write plain-text instructions describing how you want Cursor's AI to behave — your tech stack, code style, naming conventions, and workflow rules. Commit it to your repository so every team member benefits from the same AI behaviour.
Are prompt templates better than Claude Skills?
They serve different purposes. Prompt templates (like .cursorrules) configure general AI behaviour for a whole project and work across multiple AI tools. Claude Skills (SKILL.md) are task-specific and integrate more deeply into Claude Code's workflow. For maximum benefit, use both: a .cursorrules or CLAUDE.md for baseline project rules, and Skills for specific complex tasks.