calling-llms

Send chat completions to LLM providers using model prefix routing.

26|2|Updated Jun 8, 2026
One-click install
npx skills add https://github.com/xberg-io/plugins --skill calling-llms
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: calling-llms
Source: https://github.com/xberg-io/plugins/tree/main/plugins/liter-llm/.cursor-plugin/skills/calling-llms
Command: npx skills add https://github.com/xberg-io/plugins --skill calling-llms

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires liter_llm, and includes scripts (resource) components.

What problem does it solve?

The Skill unit addresses the complexity of sending chat completions to multiple language learning model providers and routing them appropriately.

Core Features & Use Cases

  • Provider Routing: Direct chat completions to a specific LLM provider using a model string prefix.
  • Chat Completion Requests: Generate ChatCompletionRequest objects to interact with different models.
  • Model Hint: Optional model hint to avoid provider prefixes for requests.
  • Use Case: Use the Skill to interact with different language models and leverage the capabilities of various LLM providers for various tasks.

Quick Start

Create a client for OpenAI GPT-4o with a model hint, then send a message request using client.chat(request).

Frequently Asked Questions about calling-llms

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I route chat completions to different LLM providers?

Route chat completions to different LLM providers by specifying a model string prefix. The Skill uses this prefix to direct the ChatCompletionRequest to the correct provider using the liter_llm library for client creation.

What is the best way to manage multi-provider LLM integrations?

Manage multi-provider LLM integrations by using a routing layer that handles ChatCompletionRequests across 143 providers. This approach centralizes client creation and message dispatching without writing provider-specific logic.

Can I send chat completion requests without specifying a provider prefix?

Yes, you can send chat completion requests without a provider prefix by using an optional model hint. This avoids the need to manually prepend provider routing strings to your model requests.

Does the Skill require the liter_llm library for LLM integration?

Yes, the Skill requires the liter_llm library for LLM integration. It depends on liter_llm internally to handle client creation and manage the ChatCompletionRequest objects sent to various language models.

How does model prefix routing work for language learning models?

Model prefix routing works by parsing the model string in your chat request to identify the target provider. The Skill then uses this prefix to route the interaction to the correct language learning model API.