This repository provides a curated collection of reusable rules and knowledge documents designed to enhance the capabilities of AI coding assistants like Claude Code and Cursor. It offers structured workflows for development tasks, code quality, problem-solving, documentation, and automation, benefiting developers seeking to streamline their AI-assisted coding processes.

How It Works

The project utilizes a .mdc (Markdown with Configuration) file format, which combines standard Markdown for content with YAML frontmatter for metadata. This dual-purpose format allows Cursor to interpret the frontmatter for rule application (e.g., file globs, alwaysApply flags) while Claude Code processes the Markdown content directly. This unified approach ensures compatibility and reusability across different AI coding assistants.

Quick Start & Requirements

• Cursor Users: Copy .mdc files from project-rules/ to .cursor/rules/.
• Claude Code Users: Copy .mdc content into CLAUDE.md or use @import syntax. Global rules can be placed in ~/.claude/CLAUDE.md.
• Global Rules: Requires ~/.claude/CLAUDE.md for global configurations.
• Terminal Title Management: Requires Zsh and placing terminal-title-wrapper.zsh in ~/.config/zsh/ and sourcing it in ~/.zshrc.
• MCP Server Setup (Peekaboo): Requires Node.js 20.0+ and macOS 14.0+.

Highlighted Details

• Comprehensive rules for commit workflows, code quality checks, issue analysis, bug fixing, and documentation generation.
• Includes language-specific rules, such as modern SwiftUI architecture and Swift 6 migration guides.
• Features global rules for GitHub issue creation and MCP server setup with AI analysis.
• Supports advanced automation for Safari and screenshots via AppleScript.

Maintenance & Community

The repository is open for contributions, encouraging users to add reusable rules following specific guidelines regarding format, frontmatter, and placement.

Licensing & Compatibility

The project is released under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

Some global rules, like the MCP Server Setup for Peekaboo, have specific OS and Node.js version requirements. The effectiveness of rules is dependent on the AI assistant's interpretation and the quality of the provided context.