VLLM Serving

by Prism-Shadow

VLLM Serving is an AI Engineering skill for Claude Code, published by Prism-Shadow in penguin-harness.

1.5K stars150 forkson Prism-Shadow/penguin-harnessAdded 2026/08/19+21% in starsRepository updated 2026/08/19

View source on GitHub Download repo ZIP

agentagentic-aiaibuild-toolclaude-codedeepseekdeepseek-harnessdesktopharnessllmrsiself-evolving

Install in seconds

Install VLLM Serving

Copy VLLM Serving into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Prism-Shadow/penguin-harness/tree/main/packages/skills/skills/vllm ~/.claude/skills/vllm

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Prism-Shadow/penguin-harness.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: packages/skills/skills/vllm/SKILL.md in Prism-Shadow/penguin-harness
Installs to: ~/.claude/skills/vllm
Collection: One of 21 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What VLLM Serving does

VLLM Serving deploys and serves open-weight LLMs on local GPUs with vLLM behind an OpenAI-compatible endpoint, ready for chat and agent workloads. Use it when you need high-throughput GPU inference with tool calling for agent harnesses like PenguinHarness.

VLLM Serving is cataloged under AI Engineering on DirSkills. VLLM Serving comes from a repository tagged agent, agentic-ai, ai, build-tool and claude-code.

Documentation

README

Excerpt

vLLM Serving

vLLM serves open-weight LLMs on local GPUs with high-throughput inference behind an OpenAI-compatible API, ready for chat and agent workloads.

Before you start

If the user's message only invokes this skill (e.g. "use vllm skill") without a concrete request, ask the user what they want. Do not run any command until the goal is clear.

Ask the user which model to serve; if they have no preference, recommend the small default Qwen/Qwen3.5-0.8B. Also ask what context length the workload needs.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about VLLM Serving

What else does Prism-Shadow publish alongside VLLM Serving?
VLLM Serving is one of 21 skills that DirSkills catalogs from Prism-Shadow/penguin-harness, the repository it ships in. Its siblings there include Agent Creation, Agent Evaluation and Agent Optimization. Each one is a separate skill with its own page in this directory, installs the same way VLLM Serving does, and is maintained by Prism-Shadow in that same repository. The rest of the collection is listed on the Prism-Shadow/penguin-harness page.
How does VLLM Serving compare to other AI Engineering skills?
VLLM Serving ranks #996 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of VLLM Serving against them. Open each page to compare what they document and how they install.