shen-shanshan
UserA curated collection of Claude Code agent skills that accelerate the entire vLLM development lifecycle.
Categories
Indexed Skills (13)
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
vllm-benchmark-result-analysis
Compare vLLM serving benchmark outputs before and after a code change. Parses plain-text vLLM benchmark output (the "Serving Benchmark Result" block), computes per-metric percentage changes with improvement/regression markers, generates a Markdown report with a full metrics table and a key-changes summary, and saves it to ./outputs/. Use when the user pastes or provides vLLM benchmark output and asks to compare, summarize, or analyze performance differences between two runs (e.g., "before this PR" vs "after this PR", or any before/after wording).
vllm-dev-task-discovery
Analyze contribution opportunities in the vllm-project/vllm repository for community developers. Given a module, feature, or model area, this skill collects information from open issues, recent PRs, GitHub discussions, code TODOs/FIXMEs, roadmap labels, and maintainer activity to generate a structured Markdown report of actionable tasks (feature development, model support, performance optimization, bug fixes, documentation, refactoring). Each task includes difficulty, prerequisite knowledge, related maintainers/contributors, urgency, and importance ratings. Use when the user wants to find contribution opportunities in vllm, understand what tasks are available in a specific area, or get a developer demand analysis. Triggered by requests like "我想了解vllm的多模态模块中还有哪些可以贡献的事情", "帮我分析vllm XXX模块的社区需求", "整理vllm中XXX相关的task", "vllm contribution opportunities in XXX", "what can I work on in vllm's XXX area", "vllm developer demand analysis for XXX".
vllm-feature-design
Design and implement vLLM features. Given user requirements (feature description, related PRs, reference materials), produces (1) core code implementation — NO test cases — and (2) a rich Markdown design document saved to the current project root. Use when the user asks to design a vLLM feature, implement a vLLM feature, architect a component for vLLM, generate a design doc for vLLM, or requests a feature design for ML inference systems. Triggered by phrases like "帮我设计vLLM的xxx功能", "design a vLLM feature for ...", "implement vLLM xxx", "generate a design doc for vLLM xxx", "vLLM feature design".
vllm-feature-tutorial
Generate comprehensive Chinese technical tutorial documents for vLLM features and modules. Produces deep-dive code walkthrough documents with Mermaid architecture/flow diagrams, comparison tables, code snippets, and performance analysis. Output is saved as Markdown to the skill's outputs/ directory. TRIGGER when: user asks to learn about a vLLM feature, module, or subsystem (e.g., "我想了解 vllm 中的 xxx", "帮我生成 vllm xxx 的教程", "generate a tutorial for vllm's xxx feature", "vllm xxx 特性分析"). DO NOT TRIGGER when: user asks about non-vLLM projects, or asks for simple Q&A without requesting a tutorial document.
vllm-model-tutorial
Generate comprehensive Chinese technical tutorial documents for specific vLLM models (e.g., Qwen3-VL, DeepSeek-V3, Llama 4, InternVL3, etc.). Produces deep-dive model walkthrough documents with Mermaid architecture diagrams, comparison tables, input preprocessing flows, forward pass analysis, ViT computation (for VLMs), vLLM code implementation analysis, and technical principle explanations (MoE, MLA, Gated Attention, ViT, DiT, etc.). Output is saved as Markdown to the skill's outputs/ directory. TRIGGER when: user asks to learn about a specific vLLM model (e.g., "我想了解 vllm 中的 Qwen3-VL", "帮我生成 Qwen3-VL 的模型教程", "generate a model tutorial for InternVL3 in vllm", "vllm 中的 DeepSeek-V3 是怎么实现的", "写一个 Llama 4 的vllm教程"). DO NOT TRIGGER when: user asks about non-vLLM models, general LLM questions without requesting a tutorial, or asks about vLLM features/modules rather than specific models.
vllm-pr-desc-generator
Generate a vLLM-style PR description (Purpose / Test Plan / Test Result) from a GitHub PR's code changes. Use when the user provides a vLLM PR link or number and asks to generate, write, or draft a PR description. Triggered by requests like "帮我生成PR描述", "generate PR description for vllm PR 12345", "帮我写vllm PR的描述", "draft a PR desc for https://github.com/vllm-project/vllm/pull/12345".
vllm-pr-summary
Fetch and analyze a Pull Request from the vllm-project/vllm GitHub repository, then generate a comprehensive Markdown report covering PR overview, code change analysis (with Mermaid architecture/flow diagrams), technical principles, discussion highlights, and risk assessment. Use when the user provides a vllm PR number and asks to summarize, analyze, review, or understand it. Triggered by requests like "帮我分析vllm的PR 12345", "总结一下vllm PR 10000", "vllm PR 9999 做了什么", "analyze vllm PR 12345".
vllm-rfc-generator
Generate a vLLM-style RFC (Request for Comments) document based on user input. Use when the user wants to create an RFC for a major architectural change or design decision in vLLM. Triggered by requests like "帮我生成一个vLLM RFC", "create a vLLM RFC for ...", "写一个RFC关于...", "生成RFC文档".
vllm-rocm-pr-review
Review AMD/ROCm-related pull requests from the vllm-project/vllm GitHub repository and produce a concise Chinese review report covering motivation, code-change summary, severity-sorted and type-categorized review findings, existing discussion, and a verdict. Use when the user provides a vllm PR number or link and asks to review it, especially for ROCm/AMD/aiter/mori related changes. Triggered by requests like "review vllm PR 12345", "帮我review vllm的PR 12345", "vllm rocm PR review", "review这个rocm PR".
vllm-technical-blog-writer
Write or complete Chinese vLLM technical blog posts in the author's established Zhihu style. Use when the user provides a vLLM feature, model, architecture, optimization, or other topic and asks for a full blog post, or provides an existing Markdown outline/draft plus references and asks to research current vllm-project/vllm code and finish the missing sections. Produces concise technical diagrams and stores each new article with its images under this skill's outputs directory.
vllm-test-generator
Generate test cases for the vllm-project/vllm repository (https://github.com/vllm-project/vllm). Use this skill when the user wants to write unit tests or integration/e2e tests for vllm code, functions, classes, or features. Triggered by requests like "帮我写XXX的测试用例", "生成XXX的单元测试", "为XXX功能写测试", "generate tests for XXX in vllm", "write a test for XXX vllm function". Do NOT use for vllm-ascend — use vllm-ascend-ut-generator instead.
vllm-multimodal-open-issue-analyzer
Fetch and organize multimodal-related open issues from vllm-project/vllm. Categorizes issues by problem type (Bug, Feature Request, Performance, CUDA Graph, EPD disaggregation, Prefix Caching, ViT/visual encoder, Video, Audio/Speech, specific VL models, etc.) and generates a structured Markdown report saved to the skill's ./outputs directory. Use when the user wants to collect, search, analyze, or summarize open issues related to multimodal features or models in the vllm repository. Triggered by requests like "搜集vllm中多模态相关的issue", "整理vllm的多模态open issue", "查一下vllm有哪些多模态问题还没解决", "帮我分析vllm多模态issue", "vllm multimodal open issues report".
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.