{
  "markdown": "# vLLM Skills\n\nA 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.\n\n## Overview\n\nThis 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.\n\n## Skills Index\n\n| Skill | Description |\n|-------|-------------|\n| [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. |\n| [vllm-deploy-k8s](plugins/vllm-skills/skills/vllm-deploy-k8s/) | Deploy vLLM to Kubernetes with GPU support, health probes, and OpenAI-compatible API endpoint. |\n| [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. |\n| [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. |\n| [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. |\n| [vllm-bench-serve](plugins/vllm-skills/skills/vllm-bench-serve/) | Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. |\n\n## Installation\n\n### Plugin Marketplace (Recommended)\n\nInstall directly from the plugin marketplace in Claude Code:\n\n```shell\n/plugin marketplace add vllm-project/vllm-skills\n/plugin install vllm-skills@vllm-skills\n```\n\n### Manual Install\n\nClone the repository and copy skills to your Claude Code skills directory:\n\n```bash\ngit clone https://github.com/vllm-project/vllm-skills.git\ncd vllm-skills\n```\n\nCopy to global skill folder:\n\n```bash\ncp -r plugins/vllm-skills/skills/vllm-deploy-simple ~/.claude/skills/\n```\n\nOr copy to the project skill folder:\n\n```bash\ncp -r plugins/vllm-skills/skills/vllm-deploy-simple .claude/skills/\n```\n\n## Usage\n\nOnce installed, use the skills with slash commands or natural language:\n\n```\n/vllm-deploy-simple\n```\n\n```\nDeploy vLLM with Qwen2.5-1.5B-Instruct on port 8000\n```\n\n```\nInstall and start a vLLM server using the vllm-deploy-simple skill\n```\n\n## Supported Models\n\nSee [vLLM documentation](https://docs.vllm.ai/en/stable/models/supported_models.html) for the full list.\n\n## Contributing\n\nThis project follows the [anthropics/skills](https://github.com/anthropics/skills) template. When adding new skills:\n\n1. Create a new directory under `plugins/vllm-skills/skills/` (e.g., `plugins/vllm-skills/skills/your-skill/`)\n2. Add a `SKILL.md` file with YAML frontmatter:\n   ```yaml\n   ---\n   name: your-skill\n   description: Brief description of what this skill does\n   ---\n   ```\n3. Add optional `scripts/`, `references/`, and `assets/` directories\n4. Update this README with your skill documentation\n\n## License\n\nLicensed under the Apache License 2.0. See [LICENSE](LICENSE).\n\n## Resources\n\n- [vLLM Documentation](https://docs.vllm.ai/)\n- [vLLM GitHub](https://github.com/vllm-project/vllm)\n- [OpenAI API Reference](https://platform.openai.com/docs/api-reference)\n- [anthropics/skills Template](https://github.com/anthropics/skills)\n",
  "bytes": 3598,
  "sha": "dcf148c276c29e533bae579a84dd688825832ff059bd19266b4da766bce4c8a2",
  "repo_slug": "vllm-project/vllm-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/skl_vllm_project_vllm_skills_vllm_deploy_doc_21aa522f/readme"
}