AI Agent rules provided by expert then collected by me
This repository is a comprehensive collection of rules and best practices for AI coding assistants (like Cursor, Claude Code, Antigravity) and 15+ programming languages.
tools/: Configuration files for specific AI tools.
cursor/.cursorrulescursor/CLAUDE.mdantigravity/instructions.mdwindsurf/.windsurfruleslanguages/: Detailed guidelines for 15+ languages (TypeScript, Python, Swift, Go, etc.).prompts/: Universal rules and global prompting strategies.
global_rules.mdCopy the contents of tools/cursor/.cursorrules to your project's .cursorrules file.
Copy tools/cursor/CLAUDE.md to your project root or use it as a reference for your system prompt.
Refer to tools/antigravity/instructions.md for internal consistency and prompting.
Point the AI to the relevant file in the languages/ directory to ensure it follows the latest best practices for your stack.
For a detailed guide on how to integrate this repository with your existing projects and how to use these rules effectively in your prompts, check the Integration Guide.
Mine your Claude Code and Codex logs into a local you.md agent profile.
Local-first AI coding agent for VS Code & Cursor. Ollama, LM Studio & your inference fleet. Cursor-grade agent UX — offline, private, zero token cost.
A self-improving skill for AI coding agents (Claude Code, Cursor, AGENTS.md): recognize a hard-won golden path in a session and harvest it into a reusable skill/rule for next time.
Second brain for Forward Deployed Engineers. Engagement memory + 35 skills across 6 domains, all behind one @fde... Works with any AI coding agent.
Game-development Agent Skills for AI coding agents: install once and a master router loads the right skill for your engine and task. 66 original, version-pinned skills (plus a master router) in the portable SKILL.md format that runs across Claude Code, Cursor, Codex, Copilot, Gemini CLI and more, for Godot, Unity, Unreal, web and beyond.
Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, less prose, and denser agent-to-agent handoffs (−53%, lossless in benchmarks) with no loss of quality. Works with Claude Code, Cursor, GitHub Copilot, Codex, Gemini CLI, Windsurf, Cline & Kiro.
Workflows from the Neura Market marketplace related to this Cursor resource