Skip to content
Back to search

vllm-skills

Agent skills for vLLM

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vllm-project--vllm-skills/badge.svg)](/listings/vllm-project--vllm-skills)

HTML

<a href="/listings/vllm-project--vllm-skills"><img src="/api/listings/vllm-project--vllm-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Plugin Marketplace (Recommended)

Install directly from the plugin marketplace in Claude Code:

/plugin marketplace add vllm-project/vllm-skills
/plugin install vllm-skills@vllm-skills

Manual Install

Clone the repository and copy skills to your Claude Code skills directory:

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

Copy to global skill folder:

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

Or copy to the project skill folder:

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

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 15 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "vllm-skills",
  3. "owner": {
  4. "name": "vLLM Project",
  5. "url": "https://github.com/vllm-project"
  6. },
  7. "plugins": [
  8. {
  9. "name": "vllm-skills",
  10. "source": "./plugins/vllm-skills",
  11. "description": "Skills for deploying and benchmarking vLLM with Claude Code",
  12. "version": "1.0.0"
  13. }
  14. ]
  15. }
README.md · README · 96 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # vLLM Skills
  2. A collection of skills for deploying and benchmarking vLLM. This project follows the [anthropics/skills](https://github.com/anthropics/skills) template format and is installable as a Claude Code plugin marketplace.
  3. ## Overview
  4. This repository provides modular, reusable agent skills required to operate and benchmark vLLM, following the Anthropics `SKILL.md` specification. Each skill is a self-contained directory implementing automation, scripts, and metadata for a specific operational task.
  5. ## Skills Index
  6. | Skill | Description |
  7. |-------|-------------|
  8. | [vllm-deploy-docker](plugins/vllm-skills/skills/vllm-deploy-docker/) | Deploy vLLM using Docker (pre-built images or build-from-source) with NVIDIA GPU support and run the OpenAI-compatible server. |
  9. | [vllm-deploy-k8s](plugins/vllm-skills/skills/vllm-deploy-k8s/) | Deploy vLLM to Kubernetes with GPU support, health probes, and OpenAI-compatible API endpoint. |
  10. | [vllm-deploy-simple](plugins/vllm-skills/skills/vllm-deploy-simple/) | Quick install and deploy vLLM, start serving with a simple LLM, and test OpenAI API. |
  11. | [vllm-prefix-cache-bench](plugins/vllm-skills/skills/vllm-prefix-cache-bench/) | Benchmark the efficiency of vLLM automatic prefix caching using fixed prompts, real datasets, or synthetic prefix/suffix patterns. |
  12. | [vllm-bench-random-synthetic](plugins/vllm-skills/skills/vllm-bench-random-synthetic/) | Run vLLM performance benchmark using synthetic random data to measure throughput, TTFT, TPOT, and other key performance metrics without downloading external datasets. |
  13. | [vllm-bench-serve](plugins/vllm-skills/skills/vllm-bench-serve/) | Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. |
  14. ## Installation
  15. ### Plugin Marketplace (Recommended)
  16. Install directly from the plugin marketplace in Claude Code:
  17. ```shell
  18. /plugin marketplace add vllm-project/vllm-skills
  19. /plugin install vllm-skills@vllm-skills
  20. ```
  21. ### Manual Install
  22. Clone the repository and copy skills to your Claude Code skills directory:
  23. ```bash
  24. git clone https://github.com/vllm-project/vllm-skills.git
  25. cd vllm-skills
  26. ```
  27. Copy to global skill folder:
  28. ```bash
  29. cp -r plugins/vllm-skills/skills/vllm-deploy-simple ~/.claude/skills/
  30. ```
  31. Or copy to the project skill folder:
  32. ```bash
  33. cp -r plugins/vllm-skills/skills/vllm-deploy-simple .claude/skills/
  34. ```
  35. ## Usage
  36. Once installed, use the skills with slash commands or natural language:
  37. ```
  38. /vllm-deploy-simple
  39. ```
  40. ```
  41. Deploy vLLM with Qwen2.5-1.5B-Instruct on port 8000
  42. ```
  43. ```
  44. Install and start a vLLM server using the vllm-deploy-simple skill
  45. ```
  46. ## Supported Models
  47. See [vLLM documentation](https://docs.vllm.ai/en/stable/models/supported_models.html) for the full list.
  48. ## Contributing
  49. This project follows the [anthropics/skills](https://github.com/anthropics/skills) template. When adding new skills:
  50. 1. Create a new directory under `plugins/vllm-skills/skills/` (e.g., `plugins/vllm-skills/skills/your-skill/`)
  51. 2. Add a `SKILL.md` file with YAML frontmatter:
  52. ```yaml
  53. ---
  54. name: your-skill
  55. description: Brief description of what this skill does
  56. ---
  57. ```
  58. 3. Add optional `scripts/`, `references/`, and `assets/` directories
  59. 4. Update this README with your skill documentation
  60. ## License
  61. Licensed under the Apache License 2.0. See [LICENSE](LICENSE).
  62. ## Resources
  63. - [vLLM Documentation](https://docs.vllm.ai/)
  64. - [vLLM GitHub](https://github.com/vllm-project/vllm)
  65. - [OpenAI API Reference](https://platform.openai.com/docs/api-reference)
  66. - [anthropics/skills Template](https://github.com/anthropics/skills)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.