llm

Run prompts, chats, embeddings, and schema extractions against multiple LLM providers via CLI.

Updated Dec 9, 2025
One-click install
npx skills add https://github.com/SecKatie/kmtools --skill llm-seckatie
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm
Source: https://github.com/SecKatie/kmtools/tree/main/llm
Command: npx skills add https://github.com/SecKatie/kmtools --skill llm-seckatie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides unified, turnkey access to multiple large language models via a single CLI, enabling consistent prompts, model selection, and workflow automation.

Core Features & Use Cases

  • Runs prompts, chats, embeddings, and schema extractions against OpenAI, Anthropic, Gemini, Llama, and plugin-backed models.
  • Supports plugin-based model extensions, templates, and conversation logging for reproducible workflows.
  • Use cases include rapid prototyping, automated QA prompts, and building CLI-driven AI tooling for software projects.

Quick Start

Install the llm tool, configure an API key, and start interacting with LLMs from the command line.

Frequently Asked Questions about llm

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

FAQPage Schema
How do I run prompts against multiple large language models from the command line?

You can run prompts against multiple large language models from the command line by using a unified CLI that connects to OpenAI, Anthropic, and Gemini via plugins. This enables consistent model selection and workflow automation directly from your terminal.

Can I use CLI-driven AI tooling to generate embeddings and extract schemas?

Yes, CLI-driven AI tooling supports generating embeddings and performing schema extractions. It operates across OpenAI, Anthropic, and Gemini models, allowing you to process text inputs and extract structured data formats within your software projects.

Does this command line LLM tool support conversation logging for reproducible workflows?

Yes, the command line LLM tool supports conversation logging to ensure reproducible workflows. It records prompts and chat interactions, enabling you to track automated QA prompts and replicate CLI-driven AI tooling results.

What is the best way to access Llama and other models without writing separate API integrations?

The best way to access Llama and other models without separate API integrations is using a plugin-based CLI. It provides turnkey access to local and remote environments, applying templates and tool usage across multiple large language models seamlessly.

Are plugin-based model extensions required to automate prompts across different providers?

Plugin-based model extensions are utilized to enable automated QA prompts across different providers like OpenAI and Anthropic. They allow the CLI to interact with various large language models, supporting rapid prototyping without changing your core commands.