Token导航 LogoToken导航TokenDH.com
研究检索external-servicegithub未标认证来源可访问许可证需确认审计提醒

build-langchain-ts-app构建 LangChain TS 应用

Agent Skill

build-langchain-ts-app 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

360

周安装

15

GitHub Stars

5

下载量

120
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:build-langchain-ts-app(构建 LangChain TS 应用)
来源仓库:https://github.com/yigitkonur/skills-by-yigitkonur
仓库路径:skills/build-langchain-ts-app
安装命令:
npx skills add https://github.com/yigitkonur/skills-by-yigitkonur --skill build-langchain-ts-app
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/yigitkonur/skills-by-yigitkonur --skill build-langchain-ts-app

简介

使用 LangChain.js v1 与 LangGraph 构建 TypeScript 智能体应用。

  • 优先采用 createAgent 基础模式,逐步叠加复杂功能。
  • 支持流式输出、RAG 管道与多智能体协作架构。
  • 若涉及 Python 或简单聊天机器人,建议使用更轻量方案。
  • build-langchain-ts-app 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Build LangChain TypeScript App

Build with LangChain.js v1 and LangGraph in TypeScript. Prefer the smallest working pattern (createAgent) first, then add complexity only when required.

Trigger boundary

Use this skill when work involves LangChain.js/LangGraph TypeScript design or implementation:

  • Tool-calling agents
  • RAG pipelines
  • Streaming and structured output
  • LangGraph stateful workflows
  • MCP integration
  • Memory/checkpointer design
  • Multi-agent orchestration

Do not use this skill for:

  • Python LangChain code
  • Simple single-provider chatbot work where provider SDK alone is enough

Non-negotiable rules

  1. TypeScript-only, LangChain v1 APIs only.
  2. Start simple: createAgent before StateGraph.
  3. Use real project functions as tools; never use eval-style shortcuts.
  4. Choose model/provider explicitly before adding middleware, memory, or RAG.
  5. Keep code incremental: get one path working end-to-end, then extend.

Fast decision tree

What are you building?
├── Basic tool-calling assistant (1-5 tools, low state)
│   └─► createAgent path (references/getting-started.md, references/agents.md)
├── Stateful loops, interrupts, custom routing
│   └─► LangGraph StateGraph path (references/langgraph.md, references/langgraph-execution.md)
├── Retrieval over documents
│   └─► RAG path (references/rag.md)
├── Strict JSON output contract
│   └─► Structured output path (references/structured-output.md)
├── UI token/event streaming
│   └─► Streaming path (references/streaming.md)
├── Multi-agent coordinator/swarm
│   └─► Multi-agent path (references/multi-agent.md)
└── External tools via MCP
    └─► MCP path (references/mcp.md)

Baseline setup

npm install langchain @langchain/core @langchain/langgraph zod
npm install @langchain/openai
# Optional:
npm install @langchain/openrouter @langchain/mcp-adapters

Required runtime: Node.js 20+ and TypeScript 5+.

Provider keys:

  • OpenAI: OPENAI_API_KEY
  • OpenRouter: OPENROUTER_API_KEY

For exact startup scaffolding (file layout + first run command), read references/getting-started.md.

Minimal implementation workflow

  1. Pick provider/model

- Use references/models.md and references/providers.md for feature and compatibility checks.

  1. Pick agent architecture

- Start with createAgent; move to LangGraph only if you need state graphs/interrupts.

  1. Define tools and schemas

- Tool contracts must be explicit and testable (references/tools.md).

  1. Add reliability layers

- Middleware, retries, fallbacks, guardrails (references/middleware-catalog.md, references/middleware-patterns.md).

  1. Add memory/streaming/structured output as needed

- Use dedicated references instead of ad-hoc patterns.

  1. Instrument and test

- Add tracing/evaluation early (references/observability-tracing.md, references/observability-evaluation.md).

Default path (recommended): createAgent

Use this as the initial architecture for most tasks:

  • createAgent for orchestration
  • Zod schemas for tool input contracts
  • checkpointer only when thread persistence is required
  • toolStrategy for structured output portability

Deep dive: references/agents.md.

Escalation path: StateGraph

Switch to StateGraph only if one or more are true:

  • You need explicit graph nodes/edges and branching
  • You need interrupt/resume with human approval
  • You need durable/replayable execution semantics
  • You need complex multi-step state transitions

Deep dives: references/langgraph.md, references/langgraph-execution.md, references/human-in-the-loop.md.

Common anti-patterns

Reject these and route to fixes:

  • Legacy v0 imports (langchain/chains, deprecated APIs)
  • providerStrategy with OpenRouter multi-model paths
  • In-memory persistence choices for production
  • Deeply nested tool schemas without clear constraints
  • Streaming assumptions that conflict with structured output behavior

Canonical fixes: references/common-errors.md, references/structured-output.md, references/streaming.md.

Reference routing

Reference routing

DocumentWhat it containsLoad when
references/getting-started.mdFirst runnable paths with exact package subsets, env vars, file names, and run commandsStarting a new LangChain TS app or unblocking the first working run
references/agents.mdcreateAgent full parameter reference, 9 overloads, model config, structured output, streaming modes, ReAct lifecycleBuilding an agent with createAgent
references/models.md15+ provider configs, 14 content block types, fakeModel API, model selection guideChoosing or configuring chat models
references/providers.md24+ providers, feature matrix, initChatModel universal interface, provider-specific setupSetting up providers or comparing capabilities
references/tools.mdtool() factory, schema design, 35+ built-in tools, type hierarchy, error handling, 9 known issuesDesigning or debugging tools
references/structured-output.mdwithStructuredOutput, providerStrategy vs toolStrategy, parser catalog, provider-specific bugsExtracting structured data from models
references/streaming.md8 LangGraph stream modes, 17 event types, streamEvents v2, Vercel AI SDK, Next.js, ExpressStreaming responses to UI
references/memory-checkpointers.mdMemorySaver, PostgresSaver, RedisSaver, trimMessages, summarization, thread managementThread-scoped conversation memory
references/memory-stores.mdBaseStore API, InMemoryStore, PostgresStore, caching, GDPR compliance, legacy migrationLong-term memory, caching, compliance
references/middleware-catalog.mdAll 14 built-in middleware with signatures, 6 hook types, execution orderUsing built-in middleware
references/middleware-patterns.mdcreateMiddleware API, guardrails, PII filtering, runtime context, composition rulesCustom middleware and guardrails
references/mcp.mdMultiServerMCPClient, stdio/SSE/HTTP transports, OAuth, tool discovery, lifecycle managementIntegrating MCP servers
references/human-in-the-loop.mdinterrupt() API, Command resume, RBAC, async approval, useStream UI, tool confirmationAdding human approval to workflows
references/multi-agent.md4 architecture patterns, handoffs, routing strategies, SubAgent interface, τ-bench benchmarksCoordinating multiple agents
references/rag.mdDocument loaders, text splitters, embeddings (13+ providers), vector stores (17), retriever types, RAGAS metricsBuilding RAG pipelines
references/langgraph.mdStateGraph, 4 channel types, Graph vs Functional API, Command/Send, subgraphs, conditional routingBuilding custom graphs
references/langgraph-execution.mdCheckpointer architecture, thread management, state serialization, parallel execution, time travelLangGraph persistence and execution
references/knowledge-agents.mdSQL agent safety, voice pipelines, multi-KB routing, query validationBuilding knowledge-domain agents
references/deployment-local.mdLangGraph Studio, CLI commands, langgraph.json schema, local dev server, Agent Chat UILocal development and Studio
references/deployment-production.mdDocker, Cloud, self-hosted servers, Generative UI, CI/CD, pricing, scalingProduction deployment
references/observability-tracing.mdLangSmith setup, 19 callback types, tracing, cost tracking, dashboards, alertsTracing and monitoring
references/observability-evaluation.mdLangSmith evaluation, datasets, LLM-as-judge, OpenTelemetry, third-party tools, pricingTesting and evaluation
references/common-errors.mdError catalog by category, antipatterns, v0→v1 migration, provider-specific gotchasDebugging errors or reviewing code

Guardrails

  • Do not use Python-only guidance in a TypeScript implementation.
  • Do not add complexity before a minimal path runs successfully.
  • Do not use outdated v0 APIs.
  • Do not assume provider feature parity; verify with references/providers.md.
  • Do not rely on in-memory persistence components in production workflows.
  • Do not ship without tracing/error visibility.

Scope boundaries

This skill covers LangChain.js and LangGraph.js in TypeScript only. It does not cover:

  • Python LangChain (different APIs and patterns)
  • LangServe (Python-only)
  • Embeddings via OpenRouter (use OpenAI directly)
  • Database-specific setup beyond connection patterns (PostgresSaver, SqliteSaver need separate install)

适合场景

01

调用多模型

02

代码和文本生成

03

Agent 推理流程

04

OpenRouter 模型接入

能力概览

能力 1

统一调用多种 LLM

能力 2

支持 Claude、Gemini、Kimi 等模型

能力 3

适合聊天、代码和推理任务

能力 4

可作为 Agent 模型调用入口

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.5%
按下载量换算45

Claude

29.73%
按下载量换算36

Cursor

19.75%
按下载量换算24

Gemini CLI

10.35%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills