L
Langchain Ai技能
ego lite browser
赞助ego lite 是AI代理运行网页自动化时最快的浏览器,可与Codex或Claude Code共享您的登录状态,零成本,零配置。
Alpha Vantage MCP Server
赞助获取金融市场数据:实时和历史股票、ETF、期权、外汇、加密货币、大宗商品、基本面、技术指标等
api-docs
langchain-ai
OpenAPI 文档与 REST API 设计模式
official
arxiv-search
langchain-ai
Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look…
official
arxiv-search
langchain-ai
Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields
official
arxiv-search
langchain-ai
通过主题搜索arXiv上的预印本和学术论文,并获取摘要。基于查询的搜索涵盖物理学、数学、计算机科学、生物学、统计学及相关领域。可配置结果数量限制(默认10篇论文),结果按相关性排序。返回每篇匹配论文的标题和摘要。需要安装arxiv Python包;若未安装,请通过pip安装。
official
arxiv-search
langchain-ai
在物理学、数学、计算机科学、定量生物学及相关领域的arXiv预印本库中搜索论文
official
blog-post
langchain-ai
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to…
official
blog-post
langchain-ai
长篇幅博客文章撰写,包含研究委托、结构化内容模板和AI生成的封面图片。在写作前将研究任务委托给子代理,并将发现结果以Markdown格式存储以供参考和上下文参考。强制采用五部分文章结构:钩子、背景、主要内容(3-5个部分)、实际应用和带行动号召的结论。通过涵盖主题、风格、构图、色彩和光线的详细提示生成SEO优化的封面图片。将文章输出至...
official
code-review
langchain-ai
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
official
code-review
langchain-ai
对变更进行结构化代码审查,检查正确性、风格、测试及潜在问题。
official
coding-prefs
langchain-ai
Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives…
official
coding-prefs
langchain-ai
在做出非平凡的样式决策前,先从 /memory/coding-prefs.md 读取用户的编码偏好,并在用户给出新偏好时追加记录。
official
competitor-analysis
langchain-ai
Analyze competitors in a given market segment. Trigger on: competitive landscape, competitor analysis, market comparison, competitive positioning.
official
competitor-analysis
langchain-ai
当被要求分析竞争对手时:
official
cudf-analytics
langchain-ai
Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical…
official
cudf-analytics
langchain-ai
用于在数据集、CSV或表格数据上执行GPU加速的数据分析,使用NVIDIA cuDF。当任务涉及分组聚合、统计…时触发。
official
cuml-machine-learning
langchain-ai
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality…
official
cuml-machine-learning
langchain-ai
使用NVIDIA cuML在表格数据上进行GPU加速的机器学习。当任务涉及分类、回归、聚类、降维…时触发。
official
data-visualization
langchain-ai
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating…
official
data-visualization
langchain-ai
用于创建出版级图表和多面板分析摘要。当任务涉及数据可视化、结果绘图、创建……时触发。
official
database-migrations
langchain-ai
数据库迁移模式与模式版本控制
official
Deep Agents Memory & Filesystem
langchain-ai
deep-agents-memory-&-filesystem — 一个可安装的AI代理技能,由langchain-ai/langchain-skills发布。
official
deep-agents
langchain-ai
Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution. Use for complex, multi-step tasks that need…
official
deep-agents
langchain-ai
使用规划、上下文管理、子代理委派和沙盒执行来构建功能完备的代理。适用于需要…的复杂多步骤任务。
official
deep-agents-core
langchain-ai
在构建任何Deep Agents应用程序时调用此技能。涵盖create_deep_agent()、harness架构、SKILL.md格式及配置选项。
official
deep-agents-core
langchain-ai
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
official
deep-agents-core
langchain-ai
用于构建多步骤智能体的基础框架,内置规划、记忆和技能委派功能。提供六种核心中间件选项:任务规划、文件系统上下文管理、子智能体委派、持久化记忆、人工审批工作流以及按需技能加载。包含三个始终可用的内置工具:用于任务追踪的write_todos、文件系统操作(ls、read_file、write_file、edit_file、glob、grep)以及用于生成专用子智能体的task。支持...
official
deep-agents-core
langchain-ai
在构建任何Deep Agents应用程序时调用此技能。涵盖create_deep_agent()、harness架构、SKILL.md格式及配置选项。
official
deep-agents-memory
langchain-ai
为Deep Agents提供可插拔的内存与文件后端,支持临时、持久化和混合路由选项。四种后端类型:StateBackend(线程作用域,临时)、StoreBackend(跨会话持久化)、FilesystemBackend(本地开发时真实磁盘访问)和CompositeBackend(将不同路径路由到不同后端)。FilesystemMiddleware提供六种文件操作工具:ls、read_file、write_file、edit_file、glob、grep。CompositeBackend使用最长前缀匹配进行路由...
official
deep-agents-memory
langchain-ai
Pluggable memory and file backends for Deep Agents with ephemeral, persistent, and hybrid routing options. Four backend types: StateBackend (thread-scoped, ephemeral), StoreBackend (cross-session persistent), FilesystemBackend (real disk access for local dev), and CompositeBackend (route different paths to different backends) FilesystemMiddleware provides six file operation tools: ls , read_file , write_file , edit_file , glob , grep CompositeBackend uses longest-prefix matching to route...
official
deep-agents-memory
langchain-ai
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent),…
official
deep-agents-memory
langchain-ai
当您的Deep Agent需要记忆、持久化或文件系统访问时,调用此技能。涵盖StateBackend(临时)、StoreBackend(持久化)…
official
deep-agents-orchestration
langchain-ai
编排子代理,规划多步骤任务,并对敏感操作要求人工审批。通过任务工具将工作委派给专业子代理;自定义子代理支持独立的工具集和系统提示,而默认的“通用”子代理继承主代理配置。使用write_todos规划并跟踪复杂工作流,将任务组织为待处理、进行中和已完成状态;需要thread_id以实现跨调用的持久化。实现...
official
deep-agents-orchestration
langchain-ai
在 Deep Agents 中使用子代理、任务规划或人工审批时调用此技能。涵盖 SubAgentMiddleware、用于规划的 TodoList 以及 HITL 中断。
official
deep-agents-orchestration
langchain-ai
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
official
deep-agents-orchestration
langchain-ai
INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL interrupts.
official
deepagents-python-quickstart
langchain-ai
Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants…
official
deepagents-thread-inspector
langchain-ai
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for…
official
deepagents-typescript-quickstart
langchain-ai
Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when the user…
official
docker-patterns
langchain-ai
Docker容器化与多阶段构建的最佳实践
official
docs-code-samples
langchain-ai
Use this skill when migrating inline code samples from LangChain docs (MDX files) into external, testable code files that are extracted by this repo’s snippet…
official
docs-code-samples
langchain-ai
在将LangChain文档(MDX文件)中的内联代码示例迁移到该仓库的代码片段提取工具所提取的外部可测试代码文件时,使用此技能。
official
ecosystem-primer
langchain-ai
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting…
official
ecosystem-primer
langchain-ai
INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required starting…
official
ecosystem-primer
langchain-ai
在任何LangChain / LangGraph / Deep Agents代理构建项目中,在查阅其他技能或编写任何代理代码之前,请先调用此技能。必须从…开始
official
ecosystem-primer
langchain-ai
在任何LangChain / LangGraph / Deep Agents代理构建项目中,在咨询其他技能或编写任何代理代码之前,请首先调用此技能。必须从…开始。
official
eval-engineering
langchain-ai
Iteratively inspect an agent repository and optional user-provided traces, interview the user, and create, run, and audit Harbor evals one at a time. Use for…
official
eval-writer
langchain-ai
为 deepagentsjs 单体仓库创建新的评估套件。处理数据集设计、测试用例脚手架、评分逻辑、vitest 配置以及 LangSmith…
official
file-organizer
langchain-ai
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating…
official
file-organizer
langchain-ai
智能地整理您电脑中的文件和文件夹,通过理解上下文、查找重复项、建议更优结构并自动执行…
official
framework-selection
langchain-ai
INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the…
official
framework-selection
langchain-ai
LangChain、LangGraph和Deep Agents分层架构的框架选择指南。分层框架中,LangChain提供基础原语,LangGraph增加编排与控制流,Deep Agents添加规划、记忆、文件管理和技能委派。决策表根据任务复杂度指导框架选择:LangChain适用于单一用途代理,LangGraph适用于自定义控制流和循环,Deep Agents适用于多步骤规划和持久会话...
official
framework-selection
langchain-ai
在任何LangChain/LangGraph/Deep Agents项目开始时,在编写任何代理代码之前调用此技能。确定哪个框架层适合……
official
gpu-document-processing
langchain-ai
Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user…
official
gpu-document-processing
langchain-ai
在处理大型PDF、文档集合或批量文本提取任务时使用,这些任务受益于GPU加速处理。当用户…时触发。
official
langchain
langchain-ai
使用预构建的架构和集成,为任何模型或工具构建智能体。适用于创建工具调用智能体、切换模型提供商或添加…
official
langchain
langchain-ai
Build agents with a prebuilt architecture and integrations for any model or tool. Use when creating tool-calling agents, switching model providers, or adding…
official
LangChain Agent Starter Kit
langchain-ai
任何LangChain、Deep Agents或LangGraph开源代理项目都请始终从这里开始。这是所有LangChain开源代理项目的必要起点…
official
LangChain Middleware & HITL
langchain-ai
langchain-middleware-&-hitl — 一个可安装的AI代理技能,由langchain-ai/langchain-skills发布。
official
LangChain RAG Pipeline
langchain-ai
在构建任何检索增强生成(RAG)系统时调用此技能。涵盖文档加载器、递归字符文本分割器、嵌入(OpenAI)等。
official
LangChain Structured Output & HITL
langchain-ai
langchain-structured-output-&-hitl — 一个可安装的AI代理技能,由langchain-ai/langchain-skills发布。
official
langchain-agents
langchain-ai
Build LangChain agents with modern patterns. Covers create_agent, LangGraph, and context management.
official
langchain-agents
langchain-ai
针对任何涉及LangChain产品(LangChain、LangGraph、LangSmith SDK)的编码问题使用此技能。涵盖代理开发模式、原语、…
official
langchain-dependencies
langchain-ai
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph,…
official
langchain-dependencies
langchain-ai
INVOKE THIS SKILL when setting up a new project or when asked about package versions, installation, or dependency management for LangChain, LangGraph,…
official
langchain-dependencies
langchain-ai
LangChain生态系统包版本、依赖关系以及Python和TypeScript的安装指南。所有新项目请基于LangChain 1.0 LTS启动;0.3版本为仅维护的旧版。始终与其他包一起显式安装langchain-core。选择一个编排层:LangGraph用于细粒度图控制,或Deep Agents用于内置规划和记忆功能。保守锁定langchain-community的精确次要版本(例如>=0.4.0,<0.5.0),因为它不...
official
langchain-dependencies
langchain-ai
在设置新项目或询问LangChain、LangGraph等的包版本、安装或依赖管理时,调用此技能。
official
langchain-fundamentals
langchain-ai
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
official
langchain-fundamentals
langchain-ai
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
official
langchain-fundamentals
langchain-ai
使用create_agent()、工具和中间件模式构建生产级LangChain代理。通过create_agent()配置模型、工具列表和系统提示;利用checkpointer和thread_id设置状态持久化,实现跨调用的对话记忆。通过@tool装饰器(Python)或tool()函数(TypeScript)定义工具,并附带清晰描述,使代理知晓调用时机。添加HumanInTheLoopMiddleware等中间件实现审批流程、自定义错误处理和人机协同...
official
langchain-fundamentals
langchain-ai
使用create_agent创建LangChain代理,定义工具,并利用中间件实现人工介入和错误处理。
official
langchain-middleware
langchain-ai
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of…
official
langchain-middleware
langchain-ai
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of…
official
langchain-middleware
langchain-ai
面向LangChain智能体的人机协同审批、自定义中间件及结构化输出模式。HumanInTheLoopMiddleware可在危险工具调用前暂停执行,允许人类审批、编辑参数或附带反馈拒绝。基于工具的中断策略支持按风险等级配置不同审批规则,需依赖检查点与thread_id实现状态持久化。命令恢复模式可在人类决策后继续执行,支持编辑工具参数...
official
langchain-middleware
langchain-ai
当需要人工介入审批、自定义中间件或结构化输出时,调用此技能。涵盖用于人工审批的HumanInTheLoopMiddleware…
official
langchain-oss-primer
langchain-ai
任何LangChain、Deep Agents或LangGraph代理构建项目都请始终从这里开始。在选择其他技能或编写任何内容之前,这是必需的起点。
official
langchain-oss-primer
langchain-ai
ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project. Required starting point before choosing other skills or writing any…
official
langchain-python-quickstart
langchain-ai
Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent…
official
langchain-rag
langchain-ai
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI),…
official
langchain-rag
langchain-ai
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI),…
official
langchain-rag
langchain-ai
完整的RAG流水线,支持文档导入、嵌入、检索以及基于LLM的响应生成。兼容多种文档加载器(PDF、网页、目录)和持久化向量存储(Chroma、FAISS、Pinecone),可配置块大小和重叠度以优化上下文保留。包含相似性搜索、MMR(最大边际相关性)检索和元数据过滤,平衡结果的相关性与多样性。与OpenAI嵌入协同工作,并实现无缝集成...
official
langchain-rag
langchain-ai
langchain-rag — 一个可安装的AI代理技能,由langchain-ai/skills-benchmarks发布。
official
langchain-typescript-quickstart
langchain-ai
Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent…
official
langgraph
langchain-ai
使用LangGraph构建有状态、持久的代理工作流。当你需要自定义基于图的控制流、人机协同、持久化或多代理时使用…
official
langgraph
langchain-ai
Build stateful, durable agent workflows with LangGraph. Use when you need custom graph-based control flow, human-in-the-loop, persistence, or multi-agent…
official
LangGraph Execution Control
langchain-ai
调用此技能以处理LangGraph工作流、并行执行、中断或流式传输。涵盖用于扇出的Send API、用于人机交互的interrupt()等。
official
LangGraph Persistence & Memory
langchain-ai
langgraph-persistence-&-memory — 一个可安装的AI代理技能,由langchain-ai/langchain-skills发布。
official
langgraph-cli
langchain-ai
INVOKE THIS SKILL when using the langgraph CLI to scaffold, develop, build, or deploy LangGraph applications. Covers langgraph new, dev, build, up, deploy, and…
official
langgraph-cli
langchain-ai
当使用 langgraph CLI 来搭建、开发、构建或部署 LangGraph 应用时,调用此技能。涵盖 langgraph new、dev、build、up、deploy 等命令。
official
langgraph-docs
langchain-ai
访问LangGraph文档,构建有状态代理和多代理工作流。获取官方LangGraph Python文档,涵盖状态机、基于图的代理设计以及人机协同模式。根据查询类型优先提供相关文档:实现指南解答操作问题,概念页面讲解理论,教程提供端到端示例,API参考提供技术细节。自动选择2–4个最相关的文档URL并检索其内容以回答...
official
langgraph-docs
langchain-ai
获取并引用LangGraph Python文档,以构建有状态代理、创建多代理工作流以及实现人机协同模式。使用…
official
langgraph-docs
langchain-ai
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use…
official
langgraph-docs
langchain-ai
Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.
official
langgraph-docs
langchain-ai
Fetches and references LangGraph Python documentation to build stateful agents, create multi-agent workflows, and implement human-in-the-loop patterns. Use…
official
langgraph-docs
langchain-ai
针对与LangGraph相关的请求,使用此技能获取相关文档,以提供准确、最新的指导。
official
langgraph-fundamentals
langchain-ai
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
official
langgraph-fundamentals
langchain-ai
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
official
langgraph-fundamentals
langchain-ai
用于构建有状态、多步骤代理工作流的有向图框架,支持细粒度控制。包含带类型状态模式的StateGraph、用于累积列表/值的归约器,以及返回部分状态更新的节点;静态边用于固定流程,条件边用于分支,Command用于结合状态更新与动态路由;Send API用于向工作节点进行扇出并行处理,并通过归约器聚合结果;支持单次执行的Invoke模式以及流模式(值、更新...)
official
langgraph-fundamentals
langchain-ai
编写任何LangGraph代码时调用此技能。涵盖StateGraph、状态模式、节点、边、Command、Send、invoke、流式处理及错误处理。
official
langgraph-human-in-the-loop
langchain-ai
暂停图执行以进行人工审查、批准或验证,随后根据其输入恢复执行。需要三个组件:检查点存储器(InMemorySaver 或 PostgresSaver)、配置中的线程 ID 以及 JSON 可序列化的中断负载。interrupt(value) 暂停执行并展示数据;Command(resume=value) 恢复执行并将该值返回给暂停的节点。恢复时,interrupt() 之前的所有代码会重新执行,因此副作用必须具有幂等性(使用 upsert 而非 insert)。支持审批工作流,...
official
langgraph-human-in-the-loop
langchain-ai
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...),…
official
langgraph-human-in-the-loop
langchain-ai
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...),…
official
langgraph-human-in-the-loop
langchain-ai
在实现人工介入模式、暂停等待审批或处理LangGraph中的错误时调用此技能。涵盖interrupt()、Command(resume=...)、…
official
langgraph-persistence
langchain-ai
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping.…
official
langgraph-persistence
langchain-ai
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping.…
official
langgraph-persistence
langchain-ai
持久化图执行,支持线程级检查点、状态历史记录及跨线程长期记忆。提供三种检查点保存器选项:InMemorySaver用于测试,SqliteSaver用于本地开发,PostgresSaver用于生产环境;始终在配置中传递thread_id以启用持久化功能。可通过get_state_history()浏览并重放历史检查点,通过更新过去节点的状态分支执行,或在恢复前手动修改状态。Store API提供跨线程用户记忆...
official
langgraph-persistence
langchain-ai
当你的LangGraph需要持久化状态、记住对话、穿越历史或配置子图检查点作用域时,调用此技能。
official
langgraph-python-quickstart
langchain-ai
Scaffold a minimal local LangGraph agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent…
official
langgraph-typescript-quickstart
langchain-ai
Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangGraph agent…
official
langsmith
langchain-ai
使用LangSmith追踪、评估和部署AI代理及大语言模型应用。适用于添加可观测性、运行评估、设计提示词或…
official
langsmith
langchain-ai
Trace, evaluate, and deploy AI agents and LLM applications with LangSmith. Use when adding observability, running evaluations, engineering prompts, or…
official
LangSmith Datasets
langchain-ai
当从追踪创建评估数据集或将数据集上传到LangSmith或查询数据集时,调用此技能。涵盖数据集类型(final_response,…)
official
LangSmith Evaluators
langchain-ai
在构建LangSmith评估管道时调用此技能。涵盖三个核心组件:(1) 创建评估器——LLM作为评判者、自定义代码;(2)…
official
Langsmith Traces
langchain-ai
当使用LangSmith追踪或查询追踪时调用此技能。涵盖为应用程序添加追踪以及查询/导出追踪数据。包含…
official
langsmith-code-eval
langchain-ai
为LangSmith追踪的智能体创建基于代码的评估器。在构建自定义评估逻辑、测试工具使用模式或对智能体输出进行评分时使用…
official
langsmith-dataset
langchain-ai
创建、管理评估数据集并上传至LangSmith,用于测试和验证。支持四种数据集类型:final_response(完整对话)、single_step(单节点行为)、trajectory(工具调用序列)和RAG(问题/片段/答案/引用)。提供CLI命令管理数据集生命周期:创建、列出、获取、删除、导出以及从本地JSON文件上传。支持基于SDK的Python和JavaScript数据集创建,可编程添加示例。示例管理...
official
langsmith-dataset
langchain-ai
INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response,…
official
langsmith-dataset
langchain-ai
INVOKE THIS SKILL when creating evaluation datasets, uploading datasets to LangSmith, or managing existing datasets. Covers dataset types (final_response,…
official
langsmith-dataset
langchain-ai
当从追踪创建评估数据集、上传数据集到LangSmith或查询数据集时调用此技能。涵盖数据集类型(final_response、…)
official
langsmith-dataset
langchain-ai
当创建评估数据集、将数据集上传到LangSmith或管理现有数据集时,调用此技能。涵盖数据集类型(final_response,…)
official
langsmith-evaluator
langchain-ai
在构建LangSmith评估管道时调用此技能。涵盖三个核心组件:(1) 创建评估器——LLM作为评判、自定义代码;(2)…
official
langsmith-evaluator
langchain-ai
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2)…
official
langsmith-evaluator
langchain-ai
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2)…
official
langsmith-evaluator
langchain-ai
使用LLM作为评判器和自定义代码评估器,为LangSmith构建评估管道。三大核心组件:创建评估器(LLM作为评判器或自定义代码)、定义运行函数以捕获智能体输出和轨迹、本地运行评估或通过上传的评估器自动运行。支持离线评估器(将运行输出与数据集示例进行比较)和在线评估器(对生产运行进行实时质量检查)。需要LangSmith API密钥和项目...
official
langsmith-evaluator
langchain-ai
在构建LangSmith评估管道时调用此技能。涵盖三个核心组件:(1) 创建评估器——LLM作为评判、自定义代码;(2)…
official
langsmith-fetch
langchain-ai
获取LangSmith追踪记录以调试代理行为。在排查代理问题、查看对话历史或调查工具调用时使用。
official
langsmith-online-eval-engineering
langchain-ai
Iteratively inspect traces, interview the user, and create LangSmith online evaluators one at a time. Use specifically for creating online evaluators for use…
official
langsmith-trace
langchain-ai
为LangChain/LangGraph应用添加追踪功能,并通过CLI查询追踪数据以进行调试和数据集生成。通过环境变量自动追踪LangChain/LangGraph应用;通过@traceable装饰器和wrap_openai()手动追踪Python和TypeScript中的其他框架。使用langsmith CLI查询追踪(完整执行树)或运行(单个节点),支持按时间、延迟、错误、标签和自定义元数据过滤。将追踪导出为保留层级结构的JSONL文件;...
official
langsmith-trace
langchain-ai
INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the…
official
langsmith-trace
langchain-ai
当使用LangSmith追踪或查询追踪时调用此技能。涵盖为应用程序添加追踪以及查询/导出追踪数据。包含…
official
langsmith-trace
langchain-ai
INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the…
official
langsmith-trace
langchain-ai
INVOKE THIS SKILL when working with LangSmith tracing OR querying traces. Covers adding tracing to applications and querying/exporting trace data. Uses the…
official
langsmith-trace
langchain-ai
当使用LangSmith追踪或查询追踪时调用此技能。涵盖为应用程序添加追踪以及查询/导出追踪数据。使用…
official
langsmith-trace
langchain-ai
当使用LangSmith追踪或查询追踪时调用此技能。涵盖为应用程序添加追踪以及查询/导出追踪数据。使用…
official
lca-deepagents
langchain-ai
Active, Socratic teacher for the LangChain Academy Deep Agents course — drives the student through the curriculum with a calibrated interaction density,…
official
linkedin-post
langchain-ai
Write a LinkedIn post based on research findings or a given topic. Use this skill when asked to create LinkedIn content, professional posts, or thought…
official
linkedin-post
langchain-ai
根据研究结果或给定主题撰写一篇领英帖子。当被要求创建领英内容、专业帖子或思想……时使用此技能。
official
managed-deep-agents
langchain-ai
INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith with the mda CLI. Walks a user through their first agent end to end —…
official
managed-deep-agents
langchain-ai
在使用 mda CLI 于 LangSmith 中构建、测试或部署 Managed Deep Agents 时调用此技能。涵盖代码优先、基于文件的项目布局;…
official
mermaid-diagrams
langchain-ai
Embed Mermaid diagrams in generated wiki pages. Use whenever documenting a runtime or request flow, a call sequence, a state machine or lifecycle, a data model…
official
pandas-patterns
langchain-ai
用于数据分析和可视化的常见pandas和matplotlib模式
official
pandas-patterns
langchain-ai
Common pandas and matplotlib patterns for data analysis and visualization
official
planning
langchain-ai
Break down a coding task into a structured implementation plan with clear steps, file identification, and risk assessment.
official
planning
langchain-ai
将编码任务分解为结构化的实施计划,包含清晰的步骤、文件识别和风险评估。
official
query-writing
langchain-ai
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database,…
official
query-writing
langchain-ai
编写并执行SQL查询,涵盖从简单的SELECT语句到复杂的多表JOIN、聚合和子查询。当用户要求查询数据库时使用…
official
react-components
langchain-ai
使用Hooks和TypeScript的现代React组件模式
official
remember
langchain-ai
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback —…
official
remember
langchain-ai
回顾当前对话并捕捉有价值的知识——最佳实践、编码规范、架构决策、工作流程和用户反馈——…
official
schema-exploration
langchain-ai
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about…
official
schema-exploration
langchain-ai
列出数据库中的表,描述列和数据类型,识别外键关系,并映射实体关系。当用户询问关于……时使用。
official
skill-creator
langchain-ai
创建有效技能的指南,通过专业知识、工作流程或工具集成来扩展代理能力。当用户……时使用此技能。
official
skill-creator
langchain-ai
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user…
official
skill-creator
langchain-ai
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user…
official
skill-creator
langchain-ai
创建有效技能的指南,通过专业知识、工作流程或工具集成来扩展智能体能力。当用户……时使用此技能。
official
social-media
langchain-ai
根据研究内容起草特定平台的社交媒体帖子,并生成配套图片。支持领英帖子(1300字符,专业语气)和推特/X话题(每条推文280字符,采用1/🧵格式)。需在撰写前将研究任务委托给子代理,随后阅读研究结果以确保准确性和相关性。使用generate_social_image工具自动生成引人注目的社交图片,采用粗体高对比度构图,针对小屏幕进行优化...
official
social-media
langchain-ai
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write…
official
swarm
langchain-ai
Dispatches many independent items in parallel: create a table, fan out to subagents, aggregate results. One row = one unit of work.
official
swarm
langchain-ai
以有界并发方式将一批任务并行分派给子代理。返回一个包含 {total, completed, failed, results[]} 的摘要对象——可迭代…
official
swarm
langchain-ai
并行分发多个独立项:创建表格,分发给子代理,聚合结果。一行等于一个工作单元。
official
testing-patterns
langchain-ai
单元测试和集成测试的最佳实践
official
web-research
langchain-ai
用于处理与网络研究相关的请求;它提供了一种结构化的方法来进行全面的网络研究
official
web-research
langchain-ai
Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents. Use when the user asks to research a topic…
official
web-research
langchain-ai
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research
official
web-research
langchain-ai
通过将任务委派给子代理、综合研究结果并生成带引用的报告,协调多来源网络研究。将研究问题拆分为2-5个不同的子主题,创建研究计划文件,并并行启动最多3个子代理进行高效调查。每个子代理针对每个子主题执行3-5次网络搜索,并将包含关键事实、引用和来源URL的研究结果写入本地文件。通过读取本地研究结果文件、整合跨子主题的见解来综合结果,并...
official
write-connector
langchain-ai
Add a new built-in OpenWiki source connector. Use when a user asks to create or implement an OpenWiki connector.
official
write-timestamp
langchain-ai
当用户希望通过沙箱内的捆绑脚本将当前日期和时间写入文件时使用。
official
write-timestamp
langchain-ai
Use when the user wants the current date and time written to a file via the bundled script inside the sandbox.
official