llm-cursor-rules
My go-to rules for using Cursor and LLMs in software development.
Install / Use
npx skills add RayFernando1337/llm-cursor-rulesInstalls into whichever agent you are using.
.cursorrules
Cursor IDE rules (legacy)
Quality Score
Category
AI & Machine LearningSupported Platforms
Skill content
View source on GitHubLLM Cursor Rules
Welcome to my repository of go-to rules for using Cursor and LLMs in software development!
About
This repository contains my opinionated rules and best practices for leveraging Large Language Models (LLMs) and the Cursor editor in software development workflows. The rules are designed to enhance productivity and code quality when working with AI-assisted coding tools.
Rules
Currently, the repository includes two sets of rules:
- Swift and SwiftUI Development Rules
- Next.js 14 Development Rules
These rules cover best practices, code structure, state management, performance optimization, and more for their respective domains.
Usage
Feel free to use these rules in your own projects or as a starting point for developing your own set of best practices. If you find them helpful, I'd appreciate attribution (see below).
Contributing
Contributions are welcome! If you have suggestions for improvements or additional rules, please feel free to open an issue or submit a pull request.
Attribution
If you use parts of this work in your own projects or writings, please provide attribution by referencing this repository and my X (formerly Twitter) account: @RayFernando1337
Live Coding
I regularly livestream coding sessions where I use Cursor and apply these rules. You can watch these streams on my YouTube channel: Ray Fernando
Connect
- Follow me on X: @RayFernando1337
- Subscribe to my YouTube channel: Ray Fernando
License
This project is open source. While I welcome sharing and usage of this work, I kindly request that you provide attribution as mentioned above.
Related Skills
caveman
107.2k🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
claude-mem
94.4kPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
83.6kGraphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
headroom
73.4kCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Security Score
Audited on Nov 26, 2025
