AI Skills

v1.0.0Developer Toolsstable

Collection of agent skills for AI coding assistants

agent-skillsai-skillsatlassianazure-devopsclaude-code
Share:
286
Stars
0
Downloads
0
Weekly
0/5

What is AI Skills?

AI Skills is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to collection of agent skills for ai coding assistants

Collection of agent skills for AI coding assistants

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Collection of agent skills for AI coding assistants

Use Cases

Add agent capabilities for coding assistants
Integrate with Atlassian and Azure DevOps
Enable deep research skills in Claude Code
sanjay3290

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx ai-skills

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use AI Skills

AI Skills is an open collection of 20 agent skills designed for AI coding assistants that support the Agent Skills Standard, including Claude Code, Gemini CLI, Cursor, and OpenAI Codex. The skills span databases (PostgreSQL, MySQL, MSSQL), AI tools (Imagen, Deep Research, Jules, Manus), Google Workspace (Docs, Sheets, Drive, Calendar, Gmail, Chat), Atlassian (Jira and Confluence), Azure DevOps, audio generation (ElevenLabs, Google TTS), and NotebookLM. Each skill is independently installable with its own API key or authentication requirement, making it easy to compose exactly the capabilities your workflow needs.

Prerequisites

  • Claude Code or another AI assistant that supports the Agent Skills Standard (Gemini CLI, Cursor, OpenAI Codex, Goose)
  • Node.js and npm for the npx skills installer
  • API keys for the specific skills you install (e.g., GEMINI_API_KEY for Imagen/Deep Research, OUTLINE_API_KEY for Outline)
  • Python 3.x and pip for database-related skills (psycopg2-binary, mysql-connector-python, pymssql)
  • System keyring for Google Workspace skill authentication (macOS Keychain, Windows Credential Manager, or Linux Secret Service)
1

List available skills

Use the npx skills command to see all available skills in the ai-skills repository before installing anything.

npx skills add sanjay3290/ai-skills --list
2

Install one or more skills

Install individual skills by name, all skills at once, or target a specific AI assistant. Use -g for a global installation or omit it for project-local installation.

# Install a specific skill globally
npx skills add sanjay3290/ai-skills --skill postgres -g

# Install all skills
npx skills add sanjay3290/ai-skills --all

# Install for a specific agent
npx skills add sanjay3290/ai-skills --skill imagen -a claude-code
3

Set required environment variables for your chosen skills

Each skill has its own authentication requirement. Set the environment variables for the skills you installed before starting your AI assistant.

# For Imagen and Deep Research
export GEMINI_API_KEY=your-gemini-api-key

# For Outline knowledge base
export OUTLINE_API_KEY=your-outline-api-key
export OUTLINE_API_URL=https://your-outline-instance.com

# For ElevenLabs TTS
export ELEVENLABS_API_KEY=your-elevenlabs-api-key

# For Manus
export MANUS_API_KEY=your-manus-api-key
4

Configure database connection files if using DB skills

Database skills (postgres, mysql, mssql) read connection credentials from a connections.json file. Create this file in your project or home directory with the required connection parameters.

{
  "connections": [
    {
      "name": "production",
      "type": "postgres",
      "host": "your-db-host",
      "port": 5432,
      "database": "your-db-name",
      "user": "your-db-user",
      "password": "your-db-password"
    }
  ]
}
5

Authenticate Google Workspace skills

Google Workspace skills require per-service authentication. Run the provided auth scripts for each service (Drive, Gmail, Calendar, etc.) before using them. The credentials are stored in your system keyring.

# Example for NotebookLM
python skills/notebooklm/scripts/auth_manager.py setup

AI Skills Examples

Client configuration

Claude Desktop configuration for AI Skills with the npx entry point.

{
  "mcpServers": {
    "ai-skills": {
      "command": "npx",
      "args": ["ai-skills"]
    }
  }
}

Prompts to try

Example prompts for the various skill categories available in ai-skills.

- "Query my production database for all users who signed up in the last 30 days."
- "Generate an image of a futuristic city skyline at sunset using Imagen."
- "Research the competitive landscape of electric vehicle batteries and summarize key findings."
- "Search Jira for all open bugs assigned to me in the DEV project."
- "Create a new Google Doc titled 'Q3 Planning' and add a table of contents outline."
- "Have Jules fix the authentication bug in src/auth.js."

Troubleshooting AI Skills

A skill fails with 'API key not set' or authentication error

Each skill requires its own credentials. Check the skill's documentation in the repository under skills/<skill-name>/ for the exact environment variable or config file needed. Set the variable in your shell profile (e.g., ~/.zshrc) so it persists across sessions.

Database skill cannot connect to PostgreSQL/MySQL/MSSQL

Ensure the required Python driver is installed: 'pip install psycopg2-binary' for PostgreSQL, 'pip install mysql-connector-python' for MySQL, or 'pip install pymssql' for MSSQL. Verify the connections.json file has the correct host, port, and credentials.

Google Workspace skills fail with 'credentials not found' error

Run the auth setup script for the specific service before using it. Google Workspace skills store OAuth tokens in the system keyring. On Linux, install a keyring backend: 'pip install keyring secretstorage'. On macOS, the system Keychain is used automatically.

Frequently Asked Questions about AI Skills

What is AI Skills?

AI Skills is a Model Context Protocol (MCP) server that collection of agent skills for ai coding assistants It connects AI assistants to external tools and data sources through a standardized interface.

How do I install AI Skills?

Follow the installation instructions on the AI Skills GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with AI Skills?

AI Skills works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is AI Skills free to use?

Yes, AI Skills is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "ai-skills": { "command": "npx", "args": ["-y", "ai-skills"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use AI Skills?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides