cursor-rules-generation
About
This Claude Skill generates Cursor rules documentation when users request "cursor rules," "create rule," or "generate cursor rules." It analyzes your codebase to extract project patterns, conventions, and best practices, then creates rule files covering structure, naming, and architectural patterns. Use it to help Claude Code understand and follow your project-specific coding standards.
Documentation
Cursor Rules Generation
Overview
Generate Cursor rules documentation based on project patterns, conventions, and best practices extracted from codebase analysis. Cursor rules help Claude Code understand project-specific conventions, coding standards, and architectural patterns.
Quick Start
Generate cursor rules by analyzing project patterns and conventions.
Example:
- Detect trigger: User says "generate cursor rules" or "create rule"
- Analyze patterns: Extract naming conventions, architectural patterns, testing patterns
- Check existing: Review
.cursor/rules/for existing conventions - Generate rules: Create rule files covering structure, naming, patterns, testing
Result: Cursor rules documentation for project conventions and standards.
When to Use
- User request contains "cursor rules", "create rule", "generate cursor rules"
- Setting up new project conventions
- Documenting project-specific patterns and standards
- Onboarding new team members to project conventions
Process
1. Codebase Pattern Analysis
- Analyze existing code patterns and conventions
- Identify naming conventions (files, functions, variables)
- Extract architectural patterns (component structure, API patterns)
- Identify testing patterns and conventions
- Extract code organization patterns
2. Configuration File Analysis
- Review existing
.cursor/rules/files - Check for existing conventions documentation
- Identify missing rule categories
- Analyze project structure for implicit conventions
3. Generate Cursor Rules
Create rule files covering:
- Project Structure: Directory organization, file naming
- Code Style: Formatting, naming conventions, code organization
- Architecture Patterns: Component patterns, API patterns, data flow
- Testing Conventions: Test structure, naming, patterns
- Documentation Standards: Comment style, README structure
- Git Workflow: Commit messages, branch naming, PR conventions
4. Save and Organize
- Create
.cursor/rules/directory if needed - Save rule files with descriptive names
- Update project documentation references
Rule Categories
Project Structure Rules
- Directory organization patterns
- File naming conventions
- Module organization principles
Code Style Rules
- Formatting standards
- Naming conventions (camelCase, PascalCase, kebab-case)
- Code organization principles
- Import/export patterns
Architecture Rules
- Component patterns
- API design patterns
- State management patterns
- Data flow conventions
Testing Rules
- Test file organization
- Test naming conventions
- Testing patterns and best practices
- Mock/stub conventions
Documentation Rules
- Comment style and standards
- README structure
- Code documentation patterns
- API documentation standards
Output
- Format: Markdown (
.mdc) - Location:
.cursor/rules/ - Filename:
[category]-rules.mdc(e.g.,code-style-rules.mdc,architecture-rules.mdc)
The skill executes BEFORE requirements intake, ensuring project conventions are documented for planning.
Troubleshooting
Common Issues:
-
Cursor rules not generated
- Symptom: User requested but no rules created
- Cause: Trigger keywords not detected or skill not invoked
- Fix: Check trigger keywords ("cursor rules", "create rule"), invoke skill manually if needed
- Prevention: Verify trigger keywords in user request
-
Incomplete pattern analysis
- Symptom: Rules missing conventions or patterns
- Cause: Didn't complete all analysis steps
- Fix: Complete all steps: codebase patterns, config files, generate rules
- Prevention: Always complete all analysis steps
-
Rules not saved in correct location
- Symptom: Rules created but not in
.cursor/rules/ - Cause: Wrong save location
- Fix: Save to
.cursor/rules/with category filename (e.g.,code-style-rules.mdc) - Prevention: Always use correct save location
- Symptom: Rules created but not in
If issues persist:
- Verify trigger keywords were detected
- Check that all analysis steps were completed
- Ensure rules saved to correct location
- Review process steps in skill
Integration with cc10x Orchestrator
This skill is invoked automatically by the PLAN workflow Phase 2 when:
- User request contains "cursor rules" keywords
- Missing Cursor rules documentation is detected
- Rule generation intent is identified
The skill executes BEFORE requirements intake, ensuring project conventions are documented for planning.
Quick Install
/plugin add https://github.com/romiluz13/cc10x/tree/main/cursor-rules-generationCopy and paste this command in Claude Code to install this skill
GitHub 仓库
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
