[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72277":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},72277,"awesome-cursor-rules-mdc","sanjeed5\u002Fawesome-cursor-rules-mdc","sanjeed5","Curated list of awesome Cursor Rules .mdc files","",null,"Python",3527,436,34,4,0,6,8,29,18,29.92,"Creative Commons Zero v1.0 Universal",false,"main",true,[],"2026-06-12 02:03:01","# MDC Rules Generator\n\n> **Disclaimer:** This project is not officially associated with or endorsed by Cursor. It is a community-driven initiative to enhance the Cursor experience.\n\nThis project generates Cursor MDC (Markdown Cursor) rule files from a structured JSON file containing library information. It uses Exa for semantic search and LLM (Gemini) for content generation.\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=sanjeed5\u002Fawesome-cursor-rules-mdc&type=Date)](https:\u002F\u002Fwww.star-history.com\u002F#sanjeed5\u002Fawesome-cursor-rules-mdc&Date)\n\n## Features\n\n- Generates comprehensive MDC rule files for libraries\n- Uses Exa for semantic web search to gather best practices\n- Leverages LLM to create detailed, structured content\n- Supports parallel processing for efficiency\n- Tracks progress to allow resuming interrupted runs\n- Smart retry system that focuses on failed libraries by default\n\n## Prerequisites\n\n- Python 3.8+\n- [uv](https:\u002F\u002Fgithub.com\u002Fastral-sh\u002Fuv) for dependency management\n- API keys for:\n  - Exa (for semantic search)\n  - LLM provider (Gemini, OpenAI, or Anthropic)\n\n## Installation\n\n1. Clone this repository:\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Fsanjeed5\u002Fawesome-cursor-rules-mdc.git\n   cd awesome-cursor-rules-mdc\n   ```\n\n2. Install dependencies using uv:\n   ```bash\n   uv sync\n   ```\n\n3. Set up environment variables:\n   Create a `.env` file in the project root with your API keys (see `.env.example`):\n   ```\n   EXA_API_KEY=your_exa_api_key\n   GEMINI_API_KEY=your_google_gemini_api_key  # For Gemini\n   # Or use one of these depending on your LLM choice:\n   # OPENAI_API_KEY=your_openai_api_key\n   # ANTHROPIC_API_KEY=your_anthropic_api_key\n   ```\n\n## Usage\n\nRun the generator script with:\n\n```bash\nuv run src\u002Fgenerate_mdc_files.py\n```\n\nBy default, the script will only process libraries that failed in previous runs.\n\n### Command-line Options\n\n- `--test`: Run in test mode (process only one library)\n- `--tag TAG`: Process only libraries with a specific tag\n- `--library LIBRARY`: Process only a specific library\n- `--output OUTPUT_DIR`: Specify output directory for MDC files\n- `--verbose`: Enable verbose logging\n- `--workers N`: Set number of parallel workers\n- `--rate-limit N`: Set API rate limit calls per minute\n- `--regenerate-all`: Process all libraries, including previously completed ones\n\n### Examples\n\n```bash\n# Process failed libraries (default behavior)\nuv run src\u002Fgenerate_mdc_files.py\n\n# Regenerate all libraries\nuv run src\u002Fgenerate_mdc_files.py --regenerate-all\n\n# Process only Python libraries\nuv run src\u002Fgenerate_mdc_files.py --tag python\n\n# Process a specific library\nuv run src\u002Fgenerate_mdc_files.py --library react\n```\n\n## Adding New Rules\n\nAdding support for new libraries is simple:\n\n1. **Edit the rules.json file**:\n   - Add a new entry to the `libraries` array:\n   ```json\n   {\n     \"name\": \"your-library-name\",\n     \"tags\": [\"relevant-tag1\", \"relevant-tag2\"]\n   }\n   ```\n\n2. **Generate the MDC files**:\n   - Run the generator script:\n   ```bash\n   uv run src\u002Fgenerate_mdc_files.py\n   ```\n   - The script automatically detects and processes new libraries\n\n3. **Contribute back**:\n   - Test your new rules with real projects\n   - Consider raising a PR to contribute your additions back to the community\n\n## Configuration\n\nThe script uses a `config.yaml` file for configuration. You can modify this file to adjust:\n\n- API rate limits\n- Output directories\n- LLM model selection\n- Processing parameters\n\n## Project Structure\n\n```\n.\n├── src\u002F                  # Main source code directory\n│   ├── generate_mdc_files.py  # Main generator script\n│   ├── config.yaml       # Configuration file\n│   ├── mdc-instructions.txt   # Instructions for MDC generation\n│   ├── logs\u002F             # Log files directory\n│   └── exa_results\u002F      # Directory for Exa search results\n├── rules-mdc\u002F            # Output directory for generated MDC files\n├── rules.json            # Input file with library information\n├── pyproject.toml        # Project dependencies and metadata\n├── .env.example          # Example environment variables\n└── LICENSE               # MIT License\n```\n\n## License\n\n[MIT License](LICENSE)\n","该项目是一个用于生成Cursor MDC（Markdown Cursor）规则文件的工具，基于结构化的JSON文件来创建库信息。其核心功能包括使用Exa进行语义搜索以收集最佳实践，并利用大型语言模型（如Gemini）生成详细且结构化的内容。此外，它支持并行处理以提高效率，具有智能重试机制和进度跟踪功能，以便中断后可以继续运行。适用于需要为特定库自动生成高质量MDC规则文件的场景，特别适合开发者社区或团队维护和扩展Cursor规则集时使用。",2,"2026-06-11 03:41:09","high_star"]