Coding & Developmentš¤claudeš¬gptāØļøcursoršuniversal
Cursorifier
Transform GitHub repositories into cursor rules using multiple LLM providers (Anthropic, OpenAI, Ollama, etc.)
Quick Start
Install this Skill
npx skills add rainmana/cursorifier# Cursorifier <div align="center"> [](https://www.npmjs.com/package/cursorifier) [](https://www.npmjs.com/package/cursorifier) [](https://github.com/rainmana/cursorifier) [](https://github.com/rainmana/cursorifier) [](https://opensource.org/licenses/MIT) [](https://nodejs.org/) [](https://starchart.cc/rainmana/cursorifier) </div> **Supercharge your Cursor AI with codebase-specific intelligence.** Cursorifier transforms your GitHub repositories into custom rules that teach Cursor AI how your project works, resulting in more accurate code suggestions, better refactoring, and contextually aware assistance. Now supports multiple LLM providers including Anthropic Claude, OpenAI, and local models like Ollama. ## Why Cursorifier? - ā **Instant Expertise**: Your AI assistant immediately understands your project conventions and architecture - ā **Better Suggestions**: Get code completions that match your project's style and patterns - ā **Fewer Hallucinations**: Rules constrain the AI to work within your codebase's patterns and dependencies - ā **Zero Learning Curve**: One command to analyze your repo and generate optimized rules ## Features - š Analyze GitHub repositories or local codebases with a single command - š§© Intelligently extract project structure, conventions, and patterns - š Handles large codebases that exceed the token limit for LLMs - š¤ Generate tailored rules for both **Cursor AI** and **Cline** using multiple LLM providers - š **Multi-Provider Support**: Anthropic Claude, OpenAI, Ollama, LM Studio, and more - š **Local AI Support**: Use your own models with Ollama or LM Studio - š Create production-ready `.rules.mdc` files for Cursor AI - š Create `.clinerules` files for Cline AI assistant - š§ Customize analysis with flexible configuration options ## š Installation ### Quick Install (Recommended) ```bash # Install globally from npm npm install -g cursorifier # Or use with npx (no installation required) npx cursorifier ``` ### Alternative Installation Methods ```bash # Install from GitHub (latest development version) npm install -g https://github.com/rainmana/cursorifier.git # Or clone and install locally git clone https://github.com/rainmana/cursorifier.git cd cursorifier npm install npm link ``` ### Verify Installation ```bash cursorifier --version cursorifier --list-providers ``` š¦ **Available on [npmjs.com](https://www.npmjs.com/package/cursorifier)** ## š¬ Quick Demo ```bash # Generate rules for any GitHub repository cursorifier https://github.com/facebook/react # Use with local models (Ollama) cursorifier . --provider local --base-url http://localhost:11434 --model llama2 # Use existing repomix output cursorifier --repomix-file ./my-repo-analysis.xml ``` ## šÆ Output Formats Cursorifier supports two AI assistant formats: ### **Cursor AI Rules** (Default) ```bash # Generate Cursor AI rules cursorifier https://github.com/facebook/react # Output: react-output/react.rules.mdc ``` **Features:** - `.rules.mdc` file format with FrontMatter - AI behavior instructions and patterns - Glob patterns for file targeting - Always/Manual/Auto rule types ### **Cline Rules** ```bash # Generate Cline rules cursorifier https://github.com/facebook/react --output-format cline # Output: react-output/.clinerules ``` **Features:** - `.clinerules` file format - Project guidelines and coding standards - Team consistency and best practices - Focus on development workflow ### **Roo Custom Modes** ```bash # Generate Roo Custom Modes cursorifier https://github.com/facebook/react --output-format roo # Output: react-output/.roomodes ``` **Features:** - `.roomodes` YAML configuration file - Specialized AI personas for different tasks - Tool access permissions and file restrictions - Custom behavioral instructions - Mode-specific expertise and capabilities ## š”ļø Reliability Features ### **Automatic Rate Limit Handling** - **Smart Retries**: Automatically retries on rate limits with exponential backoff (2s, 4s, 8s) - **Configurable Delays**: Control chunk processing speed with `--chunk-delay` - **Progress Tracking**: Clear feedback on retry attempts and delays ### **Robust Text Processing** - **Token Sanitization**: Automatically removes problematic tokens like `<|endoftext|>` - **Large Repository Support**: Handles repositories with millions of tokens - **Chunk Processing ... (truncated)
Repository
3stars
0forks
Details
Related Skills
More coding & development skills you might like
Reticle
Coding & DevelopmentAI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
š¤claudešuniversal
1.2k
190
View
agentscope-java
Coding & DevelopmentExpert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or Java agent development. Specializes in non-blocking code, tool integration, hooks, pipelines, and production-ready agent applications.
šuniversal
6.0k
1.5k
View
ospec
Coding & DevelopmentDocument-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
āØgeminiš¤claudeš¬gptšuniversal
524
34
View
misakanet-failure-memory
Coding & Developmentš A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org
š¤claudeāØļøcursoršuniversal
424
158
View