LangChain 助手
- 作者仓库星标 0
- 作者更新于 实时读取
- 作者仓库 skills-registry
- 领域
- 运维部署
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @tomevault-io · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需手动接入
- 是否需要外部 API Key
- 需要 · OpenAI / Anthropic
- 兼容的系统
- Docker
- 底层运行要求
- Python · Docker
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- 读取环境变量
- 网络行为
- 允许外网请求
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
---
name: langchain-agents-workflow
description: Use when starting work on any LangChain / LangGraph / DeepAgents project. Entry point for the de…
category: 运维部署
runtime: Python / Docker
---
# langchain-agents-workflow 输出预览
## PART A: 任务判断
- 适用问题：部署、CI、环境检查、发布或运维排障。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“Version floors this bundle assumes / You have two complementary tools / When to load which skill”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于部署、CI、环境检查、发布或运维排障，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“Version floors this bundle assumes / You have two complementary tools / When to load which skill”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、读取环境变量、会按任务需要访问外部网络、需要准备 OpenAI / Anthropic API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、读取环境变量；会按任务需要访问外部网络；需要准备 OpenAI / Anthropic API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 先确认触发方式
原文没有稳定的斜杠命令要求。安装验证后通常全局生效，直接在对话里点名这个 Skill 并描述任务即可。
给清楚输入和边界
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、写入/修改文件、读取环境变量。
小样例验证后再放大
先用一个小任务确认它会围绕“Version floors this bundle assumes / You have two complementary tools / When to load which skill”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
复核后再交付
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: langchain-agents-workflow
description: Use when starting work on any LangChain / LangGraph / DeepAgents project. Entry point for the de…
category: 运维部署
source: tomevault-io/skills-registry
---
# langchain-agents-workflow
## 什么时候使用
- 把部署运维方向的常用动作沉淀成 Agent 可调用的技能 适合处理部署、CI、发布、回滚、环境检查和运维排障，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤…
- 面向部署、CI、环境检查、发布或运维排障，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Version floors this bundle assumes / You have two complementary tools / When to load which skill」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件、读取环境变量；会按任务需要访问外部网络；需要准备 OpenAI / Anthropic API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。 证据边界与执行链路
作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "langchain-agents-workflow" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Version floors this bundle assumes / You have two complementary tools / When to load which skill
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> Python / Docker | 读取文件、写入/修改文件、读取环境变量 | 会按任务需要访问外部网络
安全层 -> 需要准备 OpenAI / Anthropic API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}LangChain Agents Workflow
This skill is the entry point — read it first, then load the more specific skill for the step you're on.
Version floors this bundle assumes
langchain >= 1.2(v1 series — middleware-firstcreate_agent)langgraph >= 1.1,langgraph-cli >= 0.4deepagents >= 0.5.3(async sub-agents, structured sub-agent responses, filesystem permissions;model=Nonedeprecated)langsmith >= 0.7(pytest plugin + new evaluator API)langchain-anthropic >= 1.4,langchain-openai >= 1.0
If a project pins anything below these floors, suggest the bump before writing code — the API shapes in this bundle assume the v1+ surface.
You have two complementary tools
This skill bundle pairs with the mcpdoc MCP server. The two have distinct roles; use both.
mcpdoc (MCP server) |
This skill bundle | |
|---|---|---|
| Purpose | Live API reference | Opinionated playbook |
| Content | Whatever's on docs.langchain.com right now |
How to think about LangChain projects |
| When to use | "What's the signature of SummarizationMiddleware?" / "What kwargs does create_agent take?" / "What import path for X?" |
"What's the production middleware stack?" / "How do I wire Cloud Run + Secret Manager + Postgres checkpointer together?" / "Which mistakes does an agent typically make here?" |
| How to use | Call fetch_docs(url) or list_doc_sources() |
Load skills based on description triggers |
| Drift risk | Zero — always live | Owner updates as ecosystem evolves; some rot tolerated |
Rule of thumb: when you need an exact API detail, fetch from mcpdoc. When you need to make a design decision, load a skill. When in doubt, do both.
When to load which skill
| Goal | Skill |
|---|---|
| Start a new agent project | langchain-agents-scaffold |
| Build a modern agent (most cases) | langchain-agents-middleware ← first; uses create_agent(...) with middleware |
| Add nodes/edges/tools to a custom LangGraph | langchain-agents-langgraph-code |
| Customize a DeepAgent | langchain-agents-deepagents-code |
| Build a non-agentic LCEL pipeline (chains, RAG) | langchain-agents-langchain-code |
| Write or run evals; unit/integration test agents | langchain-agents-langsmith-evals |
| Deploy + productionise | langchain-agents-deploy |
| Debug / read traces / OTEL | langchain-agents-observability |
Mental model
Three layers in the modern stack:
create_agent(model, tools, middleware=...)— the v1 default for building agents. Middleware is how you add retries, fallbacks, summarization, HITL, PII handling, call limits. Read the middleware skill for the production stack.- Raw LangGraph (
StateGraph) — drop down whencreate_agentisn't enough (multi-graph workflows, custom state, parallel branches). Read langgraph-code. - DeepAgents —
create_deep_agent(...)iscreate_agent(...)pre-loaded withFilesystemMiddleware+SubAgentMiddleware+TodoListMiddleware. Read deepagents-code.
For non-agentic flows (RAG, classification), use plain LCEL chains — middleware does not apply to chains.
Common commands by lifecycle stage
| Stage | Command(s) |
|---|---|
| Scaffold a LangGraph project | langgraph new my-agent --template react-agent |
| Scaffold a DeepAgent / chain | No scaffolder — write a small agent.py (see scaffold skill) |
| Install deps | pip install -e . or uv sync |
| Iterate on a graph | langgraph dev |
| Run an agent ad hoc | python -c "from agent.agent import agent; print(agent.invoke({'messages': [...] }))" |
| Run evals | python evals/run.py |
| Unit-test agents (no API calls) | pytest with LLMToolEmulator middleware |
| Deploy to LangSmith Cloud | langgraph build -t my-agent && langgraph deploy |
| Deploy to Cloud Run | gcloud run deploy my-agent --source . |
| Deploy as a Docker image | docker build && docker run --env-file .env |
Hard rules
- Look up exact APIs via
mcpdoc, don't guess. Ifmcpdocisn't configured, ask the user to set it up (see this repo's README) before you write LangChain code. - Always check what's already installed before suggesting
pip install—pip show langchain langgraph deepagents langsmith. - Never print
.envcontents — refer to keys by name only. - For ANY production agent, add the production middleware stack (call limits, retries, fallback, summarization). Copy-paste-ready in the middleware skill.
- Run smoke evals before any deploy. Not enforced — you must do it.
- Read the project structure first (
ls,tree -L 2) before assuming layout.
Required environment variables (most projects)
LANGSMITH_API_KEY— for tracing and evals.LANGSMITH_TRACING=true— enables trace capture.LANGSMITH_PROJECT— trace bucket name.- One of
OPENAI_API_KEY,ANTHROPIC_API_KEY, etc.
If any are missing when needed, fail fast with a clear message that names the missing variable.
Source: cwijayasundara/agent_cli_langchain — distributed by TomeVault.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核