Multi-Language Project Analysis with PMAT
关于
This skill analyzes multi-language codebases using PMAT to assess cross-language integration, architecture, and quality. It supports 25+ languages and provides unified quality metrics and best-practice violations across the entire project. Use it when working with polyglot projects to understand language distribution and compare ecosystem quality.
快速安装
Claude Code
推荐npx skills add mattnigh/skills_collection -a claude-code/plugin add https://github.com/mattnigh/skills_collectiongit clone https://github.com/mattnigh/skills_collection.git ~/.claude/skills/Multi-Language Project Analysis with PMAT在 Claude Code 中复制并粘贴此命令以安装该技能
GitHub 仓库
Frequently asked questions
What is the Multi-Language Project Analysis with PMAT skill?
Multi-Language Project Analysis with PMAT is a Claude Skill by mattnigh. Skills package instructions and resources that Claude loads on demand, so Claude can perform Multi-Language Project Analysis with PMAT-related tasks without extra prompting.
How do I install Multi-Language Project Analysis with PMAT?
Use the install commands on this page: add Multi-Language Project Analysis with PMAT to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does Multi-Language Project Analysis with PMAT belong to?
Multi-Language Project Analysis with PMAT is in the Meta category, tagged ai and mcp.
Is Multi-Language Project Analysis with PMAT free to use?
Yes. Multi-Language Project Analysis with PMAT is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具，可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计，提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持，涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流，可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件，用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式，适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架，特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术，在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时，能实现极速生成。如果你正在构建智能体或多轮对话系统，并追求远超vLLM的推理性能，SGLang是理想选择。