LangChain 助手

AI 智能社区

作者仓库星标 0
作者仓库 skills-registry

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

方法与流程

Step 1: Pick framework：If unsure which framework to use, read framework-selection first: → ~/.skills-library/langchain/framework-selection/SKILL.md (163 lines)
Step 2: Load the relevant sub-skill(s)：原文以此为独立章节。
LangGraph (stateful graphs, complex workflows)：When · Read StateGraph, nodes, edges, Command, Send, streaming · ~/.skills-library/langchain/langgraph-fundamentals/SKILL.md (811 lines) interrupt(), approval workflows, error handling tiers · ~/.skills-library/langchain/langgraph-human-in-the-loop/SKILL.md…

适用与边界

当前原文没有单列适用场景。
Rules：Read the sub-skill file with the Read tool — it contains full API reference and examples For multi-concern tasks, read multiple files (e.g. langgraph-fundamentals + langgraph-persistence) Never guess APIs from memory — always read the file first

原文中的明确线索

要点：「framework-selection」、「Do NOT load all sub-skills.」、「--- > Source: andres-ortizl/dotfiles — distributed by TomeVault.」
文件与命令：~/.skills-library/langchain/framework-selection/SKILL.md、~/.skills-library/langchain/langchain-fundamentals/SKILL.md、~/.skills-library/langchain/langchain-middleware/SKILL.md、~/.skills-library/langchain/langchain-rag/SKILL.md、~/.skills-library/langchain/langchain-dependencies/SKILL.md、~/.skills-library/langchain/langgraph-fundamentals/SKILL.md、~/.skills-library/langchain/langgraph-human-in-the-loop/SKILL.md、~/.skills-library/langchain/langgraph-persistence/SKILL.md

流狐整理：以上内容来自当前 SKILL.md 的章节与原词；未补写作者没有声明的工具、兼容性或能力。

LangChain / LangGraph / Deep Agents — Skill Router

Do NOT load all sub-skills. Read ONLY the file(s) relevant to the current task.

Step 1: Pick framework

If unsure which framework to use, read framework-selection first: → ~/.skills-library/langchain/framework-selection/SKILL.md (163 lines)

Step 2: Load the relevant sub-skill(s)

LangChain (simple agents, tool calling)

When	Read
Creating agents, defining tools, basic agent loop	`~/.skills-library/langchain/langchain-fundamentals/SKILL.md` (394 lines)
Human-in-the-loop approval, custom middleware, structured output	`~/.skills-library/langchain/langchain-middleware/SKILL.md` (388 lines)
RAG: document loaders, splitters, embeddings, vector stores	`~/.skills-library/langchain/langchain-rag/SKILL.md` (517 lines)
Package versions, installation, dependency management	`~/.skills-library/langchain/langchain-dependencies/SKILL.md` (419 lines)

LangGraph (stateful graphs, complex workflows)

When	Read
StateGraph, nodes, edges, Command, Send, streaming	`~/.skills-library/langchain/langgraph-fundamentals/SKILL.md` (811 lines)
interrupt(), approval workflows, error handling tiers	`~/.skills-library/langchain/langgraph-human-in-the-loop/SKILL.md` (532 lines)
Checkpointers, thread_id, time travel, Store, subgraph persistence	`~/.skills-library/langchain/langgraph-persistence/SKILL.md` (560 lines)

Deep Agents (hierarchical agent systems)

When	Read
create_deep_agent(), harness architecture, SKILL.md format	`~/.skills-library/langchain/deep-agents-core/SKILL.md` (423 lines)
SubAgentMiddleware, TodoList planning, HITL interrupts	`~/.skills-library/langchain/deep-agents-orchestration/SKILL.md` (471 lines)
StateBackend, StoreBackend, FilesystemMiddleware, CompositeBackend	`~/.skills-library/langchain/deep-agents-memory/SKILL.md` (301 lines)

~/.skills-library/langchain is a symlink to the langchain-skills submodule — don't hardcode the submodule path, use this alias so the skill stays portable if the submodule moves.

Rules

Read the sub-skill file with the Read tool — it contains full API reference and examples
For multi-concern tasks, read multiple files (e.g. langgraph-fundamentals + langgraph-persistence)
Never guess APIs from memory — always read the file first

Source: andres-ortizl/dotfiles — distributed by TomeVault.

流狐档案作者与许可取自来源；运行、权限和网络为流狐检测或估算

流狐分类: AI 智能
作者声明 Agent: 未找到明确声明；不据此推断已兼容或已测试
静态检查: 88 / 100 · 启发式扫描，不代表运行安全
作者 / 版本 / 许可: @tomevault-io · 未声明 license
流狐 Token 估算: 低消耗
流狐接入估算: 即装即用
是否需要外部 API Key: 未发现要求
检测到的系统要求: 未声明
底层运行要求: 未声明
检测到的文件与系统行为: 只读
检测到的网络行为: 仅限本地
安装命令数: 无（仅作为资料）

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。

输出预览 langchain-stack.preview

作者没有在当前 SKILL.md 中定义固定输出样例。

SKILL.md SKILL.md

# LangChain / LangGraph / Deep Agents — Skill Router

Do NOT load all sub-skills. Read ONLY the file(s) relevant to the current task.

## Step 1: Pick framework

If unsure which framework to use, read **framework-selection** first:
→ `~/.skills-library/langchain/framework-selection/SKILL.md` (163 lines)

## Step 2: Load the relevant sub-skill(s)

### LangChain (simple agents, tool calling)

| When | Read |
|---|---|
| Creating agents, defining tools, basic agent loop | `~/.skills-library/langchain/langchain-fundamentals/SKILL.md` (394 lines) |
| Human-in-the-loop approval, custom middleware, structured output | `~/.skills-library/langchain/langchain-middleware/SKILL.md` (388 lines) |
| RAG: document loaders, splitters, embeddings, vector stores | `~/.skills-library/langchain/langchain-rag/SKILL.md` (517 lines) |
| Package versions, installation, dependency management | `~/.skills-library/langchain/langchain-dependencies/SKILL.md` (419 lines) |

### LangGraph (stateful graphs, complex workflows)

| When | Read |
|---|---|
| StateGraph, nodes, edges, Command, Send, streaming | `~/.skills-library/langchain/langgraph-fundamentals/SKILL.md` (811 lines) |
| interrupt(), approval workflows, error handling tiers | `~/.skills-library/langchain/langgraph-human-in-the-loop/SKILL.md` (532 lines) |
| Checkpointers, thread_id, time travel, Store, subgraph persistence | `~/.skills-library/langchain/langgraph-persistence/SKILL.md` (560 lines) |

### Deep Agents (hierarchical agent systems)

| When | Read |
|---|---|
| create_deep_agent(), harness architecture, SKILL.md format | `~/.skills-library/langchain/deep-agents-core/SKILL.md` (423 lines) |
| SubAgentMiddleware, TodoList planning, HITL interrupts | `~/.skills-library/langchain/deep-agents-orchestration/SKILL.md` (471 lines) |

…

证据边界与执行链路

作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。

章节    -> Step 1: Pick framework → Step 2: Load the relevant sub-skill(s) → LangChain (simple agents, tool calling) → LangGraph (stateful graphs, complex workflows) → Deep Agents (hierarchical agent systems) → Rules
要点    -> framework-selection · Do NOT load all sub-skills. · --- > Source: [andres-ortizl/dotfiles](https://github.com/andres-ortizl/dotfiles) — distributed by [TomeVault](https://tomevault.io).
文件/命令 -> ~/.skills-library/langchain/framework-selection/SKILL.md · ~/.skills-library/langchain/langchain-fundamentals/SKILL.md · ~/.skills-library/langchain/langchain-middleware/SKILL.md · ~/.skills-library/langchain/langchain-rag/SKILL.md · ~/.skills-library/langchain/langchain-dependencies/SKILL.md · ~/.skills-library/langchain/langgraph-fundamentals/SKILL.md · ~/.skills-library/langchain/langgraph-human-in-the-loop/SKILL.md · ~/.skills-library/langchain/langgraph-persistence/SKILL.md
内容 SHA-256 -> 04e6f1a1169c