🛍️ 更多精选好物 ›
📊 公开数据一览
| 📦 榜单安装量 | 11.3K |
| ⭐ GitHub Stars | 1,075（fork 85） |
| 🗓️ 最近推送 | 2026-07-30 |
| 🌱 项目创建 | 2026-01-22 |
| 💻 语言 / License | TypeScript · 未标注 |
| 🐛 开放Issue | 3 |
📝 工具简介
早期开发中的agent技能包，用于构建基于LangChain、LangGraph和Deep Agents的应用。
📖 怎么用
安装命令和 langchain 其他 skill 一样：`npx skills add langchain-ai/langchain-skills --skill '*' --yes` 装当前项目，加 `--global` 全局装。指定 Claude Code 用：`npx skills add langchain-ai/langchain-skills --agent claude-code --skill '*' --yes --global`。插件方式：`/plugin marketplace add langchain-ai/langchain-skills` 和 `/plugin install langchain-skills@langchain-skills`。脚本安装：`./install.sh` 当前目录，`./install.sh ~/my-project` 指定项目，`./install.sh --global` 全局。README未说明具体使用步骤。
📋 迷你测评
早期技能包，专注LangChain中间层逻辑。亮点是跟Deep Agents配合，适合调代理间的数据流转。目前文档还不全。
📄 README 要点
这也是LangChain官方的Agent技能包系列之一，专注于中间件相关的开发。和同系列的其他包一样，支持Claude Code、Cursor、Windsurf等编码助手，通过npx skills命令安装，可以装到当前项目或全局，也能作为Claude Code插件直接使用。项目还在早期开发阶段，API和内容可能会调整。如果你在用LangChain做中间件开发，比如处理请求转发、数据转换、日志记录这些，装这个技能包能让AI编码助手更懂LangChain中间件的写法，帮你写出更规范的代码。
查看英文原文
LangChain Skills ⚠️ — This project is in early development. APIs and skill content may change. Agent skills for building agents with LangChain, LangGraph, and Deep Agents. For LangSmith specific trace and dataset workflows, use langsmith skills. Supported Coding Agents These skills can be installed via npx skills for any agent that supports the Agent Skills specification, including Claude Code, Cursor, Windsurf, and more. Installation Quick Install Using npx skills : Local (current project): [安装/使用命令见下方] Global (all projects): [安装/使用命令见下方] To link skills to a specific agent (e.g. Claude Code): [安装/使用命令见下方] Claude Code Plugin Install directly as a Claude Code plugin: [安装/使用命令见下方] Install Script (Claude Code & Deep Agents CLI only) Alternatively, clone the repo and use the install script: [安装/使用命令见下方] Flag / Argument Description DIRECTORY Target project directory (default: current directory, ignored with global ) claude Install for Claude Code (default) deepagents Install for Deep Agents CLI global , g Install globally instead of current directory force , f Overwrite skills with same names as this package yes , y Skip confirmation prompts Usage After installation, set your API keys: [安装/使用命令见下方] Then run your coding agent from the directory where you installed (for local installs) or from anywhere (for global installs). Eval Engineering To install only the eval engineering skill: [安装/使用命令见下方] Or ask Codex: “Install the eval engineering skill from langchain ai/langchain skills .” Eval tasks require Harbor. Run Harbor locally with Docker or use a supported cloud environment. Then ask your coding agent: [安装/使用命令见下方] Available Skills (21) Getting Started ecosystem primer Start here primer: framework selection (LangChain vs LangGraph vs Deep Agents), env setup, and which skill to load next langchain dependencies Full package version and dependency management reference (Python + TypeScript) Quickstarts (local) Thin wrappers around the official Mintlify quickstarts — ask for
💬 评论（0）
交流使用体验、避坑建议；违规内容将被删除