Langchain Fundamentals

If you're building LangChain agents, this cuts through the API confusion and focuses on create_agent(), which is what actually works in production. It covers the middleware patterns you'll need for human-in-the-loop workflows and error handling, plus proper tool definition with the @tool decorator. The examples show real patterns like state persistence with MemorySaver and structured output validation. Most LangChain tutorials still reference deprecated agent classes, so this keeps you on the current approach that won't break in six months.

skills.sh installs: 18.2K
GitHub stars: 1.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add langchain-ai/langchain-skills --skill langchain-fundamentals --agent claude-code

Installs into .claude/skills of the current project.

Files

Build production agents using `create_agent()`, middleware patterns, and the `@tool` decorator / `tool()` function. When creating LangChain agents, you MUST use create_agent(), with middleware for custom flows. All other alternatives are outdated.

<create_agent>

Creating Agents with create_agent

create_agent() is the recommended way to build agents. It handles the agent loop, tool execution, and state management.

Agent Configuration Options

Parameter	Purpose	Example
`model`	LLM to use	`"anthropic:claude-sonnet-4-5"` or model instance
`tools`	List of tools	`[search, calculator]`
`system_prompt` / `systemPrompt`	Agent instructions	`"You are a helpful assistant"`
`checkpointer`	State persistence	`MemorySaver()`
`middleware`	Processing hooks	`[HumanInTheLoopMiddleware]` (Python) / `[humanInTheLoopMiddleware({...})]` (TypeScript)
</create_agent>

from langchain.agents import create_agent
from langchain_core.tools import tool

@tool
def get_weather(location: str) -> str:
    """Get current weather for a location.

SKILL.md on GitHub