Llm Router
Provides LLMs guidance and assistance for building AI and machine learning applications.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add llm-router npx -- -y @trustedskills/llm-router
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"llm-router": {
"command": "npx",
"args": [
"-y",
"@trustedskills/llm-router"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The Llm Router skill enables AI agents to route requests to different LLM providers using SwiftOpenAI-CLI's agent mode. It automatically configures the CLI to use a specified provider (OpenAI, Grok, Groq, DeepSeek, or OpenRouter), ensures the tool is installed and up-to-date, and then executes one-shot agentic tasks. This simplifies the process of leveraging various LLMs without manual configuration for each request.
When to use it
- When you need to quickly switch between different LLM providers (e.g., Grok, OpenAI, DeepSeek) within an AI agent workflow.
- For experimenting with different models and evaluating their performance on specific tasks.
- To leverage the capabilities of specialized models available through providers like Groq or OpenRouter.
- When you need to execute one-shot agentic tasks using a particular LLM provider.
Key capabilities
- Automatic installation and updating of SwiftOpenAI-CLI.
- Configuration for multiple LLM providers: OpenAI, Grok, Groq, DeepSeek, and OpenRouter.
- API key verification with clear instructions for setup (environment variables or config file).
- Agent mode execution with features like one-shot task completion, tool calling, MCP integration support, conversation memory, and multiple output formats.
Example prompts
- "Use Grok to explain quantum computing."
- "Configure the agent to use DeepSeek Reasoner and then summarize this article."
- “Use OpenAI GPT-5 to generate a poem about cats.”
Tips & gotchas
- Requires SwiftOpenAI-CLI to be installed. The skill will attempt to install it, but ensure you have the necessary permissions.
- API keys are required for each provider and must be configured correctly before tasks can be executed. The script provides clear instructions if an API key is missing.
- Supported models vary by provider; refer to the provider's documentation for available options.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.