vLLM Skills

A collection of skills for deploying and invoking vLLM. This project follows the anthropics/skills template format.

Overview

This repository provides modular, reusable agent skills required to operate and invoke vLLM, following the Anthropics SKILL.md specification. Each skill is a self-contained directory implementing automation, scripts, and metadata for a specific operational task.

All skills adhere to the Anthropics skills template and can be copied into a Claude Code skills directory for use.

Skills Index

Skill	Description
vllm-deploy-docker	Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server.
vllm-deploy-simple	Quick install and deploy vLLM, start serving with a simple LLM, and test OpenAI API.
vllm-prefix-cache-bench	Benchmark the efficiency of vLLM automatic prefix caching using fixed prompts, real datasets, or synthetic prefix/suffix patterns.

Skills Example

vllm-deploy-simple

Deploy vLLM as an online service with OpenAI-compatible API locally.

Features:

• Auto detect hardware type and install vllm
• Local deployment with vllm serve
• Test and management utilities

Quick Start for Claude Code:

1. Clone the repository

   git clone https://github.com/vllm-project/vllm-skills.git
   cd vllm-skills

2. Copy skills needed to your Claude Code skills directory

   Copy the skills to global skill folder:

   cp -r skills/vllm-deploy-simple ~/.claude/skills/

   Or copy to the project skill folder:

   cp -r skills/vllm-deploy-simple .claude/skills/

3. Use the skills (with sample user prompts):

   Once installed, you can use the skill in Claude Code like:

   /vllm-deploy-simple
   

   Or with natural language:

   Deploy vLLM with Qwen2.5-1.5B-Instruct on port 8000
   

   Install and start a vLLM server using the vllm-deploy-simple skill
   

   Set up vLLM in a virtual environment at current folder with Qwen2.5-1.5B-Instruct
   

Supported Models

See vLLM documentation for the full list.

Contributing

This project follows the anthropics/skills template. When adding new skills:

1. Create a new directory under skills/ (e.g., skills/your-skill/)
2. Add a SKILL.md file with YAML frontmatter:

   ---
   name: your-skill
   description: Brief description of what this skill does
   ---

3. Add optional scripts/, references/, and assets/ directories
4. Update this README with your skill documentation

License

Licensed under the Apache License 2.0. See LICENSE.

Resources

• vLLM Documentation
• vLLM GitHub
• OpenAI API Reference
• anthropics/skills Template