#614 · Primary category: AI Coding Assistants
llm-cursor-rules
My go-to rules for using Cursor and LLMs in software development.
Project last updated:11/26/25
GitHub Stars
888
Forks
134
Contributors
1
License
MIT
Why we included this project
Anyone doing real work in Cursor or a similar AI-assisted editor quickly learns that the output is only as good as the instructions you feed it. This repo collects a practical, opinionated set of rules that push the assistant toward consistent structure, sound state management, and performance-aware choices instead of its first guess. Right now it covers Swift and SwiftUI plus Next.js 14, so it is most useful to developers in those stacks, but the bigger value is the pattern: each rule set shows how to turn your own team's conventions into something an editor can actually follow. The author also livestreams sessions where he applies these rules, which gives you a real look at them in day-to-day use. Treat it as a solid starting point to fork and adapt, not as a drop-in tool.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.