llm-cli

Consolidate access to multiple LLM providers via the llm CLI.

Updated Apr 16, 2026

Search Tags:#cli #llm #multimodal #model-selection #provider-agnostic #file-processing #config-persistence

Ready to run

npx skills add https://github.com/KISHOR403/claude-skills --skill llm-cli-kishor403

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: llm-cli
Source: https://github.com/KISHOR403/claude-skills/tree/main/llm-cli
Command: npx skills add https://github.com/KISHOR403/claude-skills --skill llm-cli-kishor403

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The LLM CLI Skill unifies access to multiple LLM providers (OpenAI, Anthropic, Google Gemini, Ollama) through a single command interface, enabling seamless processing of text and multimedia inputs.

Core Features & Use Cases

Supports non-interactive prompts and interactive conversations via the llm CLI.
Automatically detects providers from environment keys, maintains a last-used model, and handles 25+ file types including text, code, PDFs, and media.
Provides a flexible model registry with aliases and provider mappings to simplify model selection and usage in real-world workflows.

Quick Start

Install the llm CLI, run /llm --setup to detect providers, then start processing text or files with a chosen model.

Frequently Asked Questions about llm-cli

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

FAQPage Schema

How do I use a single CLI to process files with multiple LLM providers?▼

A single CLI can process files with multiple LLM providers by consolidating access to OpenAI, Anthropic, Google Gemini, and Ollama. It detects providers via environment keys and handles 25+ file types including text, code, PDFs, and media.

Can I run interactive chats and non-interactive prompts with different LLM models?▼

You can run interactive chats and non-interactive prompts with different LLM models using the execution engine. It supports model selection with aliases and maintains a persistent JSON config to remember your last-used model choices.

What do I need to set up before processing multimedia inputs with an LLM CLI?▼

Before processing multimedia inputs, you need to install the llm CLI and run the setup command to detect providers from your environment keys. This configures provider mappings and prepares the system for text and file-input handling.

How does provider detection work when accessing multiple LLMs from the command line?▼

Provider detection works by checking for specific environment keys when you run the setup command. It automatically identifies available LLM providers and registers them in a persistent configuration for seamless command-line access.

Does the llm CLI support processing PDFs and code files alongside text?▼

The llm CLI supports processing PDFs and code files alongside text and media. It handles 25+ file formats through flexible input handling, accepting data from stdin, files, or inline sources for multimodal processing.