cursor
About
The Cursor Skill enables CLI control of the Cursor AI code editor, allowing developers to quickly open files, folders, and diffs directly from the terminal. Key features include opening files at specific line/column positions, managing windows, and handling multiple files. Use it to streamline your workflow when navigating projects or reviewing code changes within the Cursor environment.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/cursorCopy and paste this command in Claude Code to install this skill
Documentation
Cursor Skill
Use the cursor CLI to control the Cursor AI-powered code editor (VS Code fork).
CLI Location
/usr/local/bin/cursor
Opening Files and Folders
Open current directory:
cursor .
Open specific file:
cursor /path/to/file.ts
Open file at specific line:
cursor /path/to/file.ts:42
Open file at line and column:
cursor /path/to/file.ts:42:10
Open folder:
cursor /path/to/project
Open multiple files:
cursor file1.ts file2.ts file3.ts
Window Options
Open in new window:
cursor -n /path/to/project
Open in new window (alias):
cursor --new-window /path/to/project
Reuse existing window:
cursor -r /path/to/file
Reuse existing window (alias):
cursor --reuse-window /path/to/file
Diff Mode
Compare two files:
cursor -d file1.ts file2.ts
Diff (alias):
cursor --diff file1.ts file2.ts
Wait Mode
Wait for file to close (useful in scripts):
cursor --wait /path/to/file
Short form:
cursor -w /path/to/file
Use as git editor:
git config --global core.editor "cursor --wait"
Adding to Workspace
Add folder to current workspace:
cursor --add /path/to/folder
Extensions
List installed extensions:
cursor --list-extensions
Install extension:
cursor --install-extension <extension-id>
Uninstall extension:
cursor --uninstall-extension <extension-id>
Disable all extensions:
cursor --disable-extensions
Verbose and Debugging
Show version:
cursor --version
Show help:
cursor --help
Verbose output:
cursor --verbose /path/to/file
Open developer tools:
cursor --inspect-extensions
Settings
User settings location:
~/Library/Application Support/Cursor/User/settings.json
Keybindings location:
~/Library/Application Support/Cursor/User/keybindings.json
Portable Mode / Profiles
Specify user data directory:
cursor --user-data-dir /path/to/data
Specify extensions directory:
cursor --extensions-dir /path/to/extensions
Piping Input
Read from stdin:
echo "console.log('hello')" | cursor -
Remote Development
Cursor supports remote development similar to VS Code. SSH remotes are configured in:
~/.ssh/config
Then use command palette or remote explorer in the GUI.
GitHub Repository
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.
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.
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.
