Coding & Development🤖claude⌨️cursor🌊windsurf🌐universal
CrossRule
Convert editor rules between different AI coding assistants (Cursor, Windsurf, Claude Code, etc.)
Quick Start
Install this Skill
npx skills add ssakone/crossrule# CrossRule A command-line tool for converting AI code editor rules between different formats. Work seamlessly across Cursor, Windsurf, Cline, VSCode, and other AI-powered development environments without losing your carefully crafted coding guidelines. [](https://www.npmjs.com/package/crossrule) [](https://opensource.org/licenses/MIT) ## The Problem You've spent time crafting the perfect coding rules for Cursor, but now you want to try Windsurf. Or maybe your team uses different AI editors, and you need to share consistent guidelines across tools. Manually converting and maintaining rules across multiple editors is tedious and error-prone. ## The Solution CrossRule automatically detects existing AI editor rules in your project and converts them to any other supported format. Your TypeScript conventions, React patterns, and testing requirements can follow you wherever you code. ## Supported Editors CrossRule works with 9 major AI code editors: - **Cursor** - `.mdc` files in `.cursor/rules/` - **Windsurf** - Markdown files in `.windsurf/rules/` - **Cline** - Markdown files in `.clinerules/` - **VSCode** - Instructions and prompts for AI extensions - **AGENTS.md-compatible editors** (Codex CLI, OpenCode, VSCode Agents) - `AGENTS.md` project rules - **Claude Code** - `CLAUDE.md` guidance files - **Qoder** - Natural language rules with trigger conditions - **Trae** - Markdown rules with YAML frontmatter - **QwenCoder** - `QWEN.md` context files ## Installation Install CrossRule globally to use it in any project: ```bash npm install -g crossrule ``` Or run it directly without installing using npx: ```bash npx crossrule init ``` Verify the installation: ```bash crossrule --version # Should output: 1.0.3 ``` ## Quick Start Navigate to your project directory and run: ```bash crossrule init ``` CrossRule will: 1. Scan your project for existing AI editor rules 2. Show you what it found and let you choose a source 3. Present an interactive list of target editors 4. Convert your rules while preserving their meaning and structure ## Universal Rule Management ### Adding New Rules Create and deploy rules across all your AI editors with a single command: ```bash # Simple always-apply rule crossrule add "Use strict TypeScript configuration" --type always --to all # Pattern-based rule for specific file types crossrule add "React components must use functional syntax" \ --type pattern --patterns "*.tsx,*.jsx" --to cursor,windsurf # Complex multi-line rule from file crossrule add --from-file team-standards.md \ --type pattern --patterns "*.ts,*.tsx" --to all # AI-decision rule with context crossrule add "Suggest performance optimizations" \ --type ai-decision --context "performance-critical" --to cursor,qoder ``` ### Rule Types CrossRule supports four intelligent rule types: - **Always (`--type always`)** - Applied to all conversations and code - **Pattern (`--type pattern`)** - Triggered when working with specific file types - **Manual (`--type manual`)** - Invoked explicitly by name or command - **AI-Decision (`--type ai-decision`)** - Applied when AI determines relevance ### Multi-Line Rules Handle complex coding standards with full markdown support: ```bash # Using heredoc for complex rules crossrule add --type always --to all << 'EOF' # TypeScript Best Practices ## Type Safety - Enable all strict mode flags - Use 'unknown' instead of 'any' - Implement proper error boundaries ## Code Organization - One component per file - Index files for clean imports - Separate types into .types.ts files EOF ``` ### Command Options - `--type <type>` - Rule type: always, pattern, manual, ai-decision - `--patterns <patterns>` - File patterns (comma-separated) for pattern rules - `--to <editors>` - Target editors: all, or comma-separated list - `--from-file <file>` - Read rule content from markdown file - `--name <name>` - Custom rule name (auto-generated if not provided) - `--description <desc>` - Rule description for documentation - `--context <context>` - Context hint for AI-decision rules ## How It Works ### Smart Detection CrossRule understands the unique file structures and formats of each AI editor. It correctly parses YAML frontmatter, section delimiters, and trigger conditions to extract the semantic meaning of your rules. ### Semantic Preservation When converting between formats, CrossRule maintains the intent of your rules: - Always-active rules remain always-active - File pattern rules are converted to equivalent glob patterns - Manual trigger rules preserve their conditional nature - Descriptions and metadata are carried forward appropriately ### Format-Specific Output Each editor has its own conventions: - **Cursor**: YAML frontmatter with `alwaysApply` and `globs` fields - **Qoder**: Trigger-based frontmatter (`always_on`, `glob`, `manual`, `model_decisi ... (truncated)
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.
🤖claude🌐universal
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.
🌐universal
6.0k
1.5k
View
ospec
Coding & DevelopmentDocument-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
✨gemini🤖claude💬gpt🌐universal
524
34
View
misakanet-failure-memory
Coding & Development📚 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
🤖claude⌨️cursor🌐universal
424
158
View