Vibe-Skills
Vibe-Skills is a Python AI agent skill for Cursor, Windsurf, Codex. Vibe-Skills is an all-in-one AI skills package. It seamlessly integrates expert-level capabilities and context management into a general-purpose skills package， enabling any AI agent to instantly upgrade its fun.
How to use Vibe-Skills
Client configuration
{
"version": "1.0",
"last_updated": "2026-02-13T00:00:00Z",
"known_mcp_servers": {
"puppeteer": {
"package": "@anthropic-ai/mcp-server-puppeteer",
"install_command": "npx -y @anthropic-ai/mcp-server-puppeteer",
"description": "Browser automation - navigate, click, type, screenshot",
"capabilities": ["browser_automation", "screenshot", "form_filling", "javascript_execution", "web_scraping"],
"tools": [
"mcp__puppeteer_navigate",
"mcp__puppeteer_click",
"mcp__puppeteer_type",
"mcp__puppeteer_screenshot",
"mcp__puppeteer_evaluate",
"mcp__puppeteer_fill",
"mcp__puppeteer_select",
"mcp__puppeteer_hover",
"mcp__puppeteer_wait"
],
"priority": "high",
"use_cases": ["web_testing", "form_automation", "screenshot", "web_scraping"]
},
"filesystem": {
"package": "@anthropic-ai/mcp-server-filesystem",
"install_command": "npx -y @anthropic-ai/mcp-server-filesystem --path {{PROJECT_DIR}}",
"description": "File system operations",
"capabilities": ["file_operations", "directory_operations", "file_search"],
"tools": [
"mcp__filesystem_read",
"mcp__filesystem_write",
"mcp__filesystem_list",
"mcp__filesystem_mkdir",
"mcp__filesystem_delete",
"mcp__filesystem_move",
"mcp__filesystem_copy",
"mcp__filesystem_search"
],
"priority": "critical",
"use_cases": ["file_management", "project_setup"]
},
"desktop": {
"package": "@anthropic-ai/mcp-server-desktop",
"install_command": "npx -y @anthropic-ai/mcp-server-desktop",
"description": "Desktop automation - mouse, keyboard, screen capture",
"capabilities": ["desktop_contCompatible clients
What is Vibe-Skills?
Vibe-Skills is a Python AI agent skill for Cursor, Windsurf, Codex. Vibe-Skills is an all-in-one AI skills package. It seamlessly integrates expert-level capabilities and context management into a general-purpose skills package， enabling any AI agent to instantly upgrade its fun. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Reusable instructions support
- Includes SKILL.md support
- Shell commands support
- Browser use support
- Presentation work support
- Document generation support
- Anthropic provider support
Available tools
Technical details
- Built for Python
- Built for Rust
- Works with Cursor
- Works with Windsurf
- Works with Codex
- Uses SSE transport
- API key required
- Database access
Requirements and access
Security and permissions
Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.
When to use Vibe-Skills
- Use it for reusing agent instructions, scripts, and references.
- Use it for agent skills workflows.
- Use it for coding workflows.
- Use it for data workflows.
- Use it for cursor users.
Built with
Explore related resources
Frequently asked questions
What is Vibe-Skills?
Vibe-Skills is a Python AI agent skill for Cursor, Windsurf, Codex. Vibe-Skills is an all-in-one AI skills package. It seamlessly integrates expert-level capabilities and context management into a general-purpose skills package， enabling any AI agent to instantly upgrade its.
Who is Vibe-Skills best for?
Vibe-Skills is best for reusing agent instructions, scripts, and references, agent skills workflows, coding workflows, data workflows, cursor users.
How do I install Vibe-Skills?
Check the Vibe-Skills GitHub repository for installation instructions.
Is Vibe-Skills actively maintained?
Vibe-Skills may need a closer maintenance check before production use.
Auto-fetched from GitHub.
