Langchain

This is your go-to for building LLM applications that need more structure than raw API calls. It covers both LangChain's LCEL pipe syntax for composing chains and LangGraph for stateful agent workflows. The examples are practical: RAG pipelines with vector stores, structured output parsing with Pydantic models, and actual agent graphs with tools and conditional routing. The memory and streaming sections show you how to handle conversations and token-by-token responses. If you're wiring up retrieval systems or multi-step agents, this gets you past the boilerplate fast. LangSmith tracing integration is a nice touch for debugging complex chains.

skills.sh installs: 169
GitHub stars: 296
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

LangChain & LangGraph

Build sophisticated LLM applications with composable chains and agent graphs.

Quick Start

pip install langchain langchain-openai langchain-anthropic langgraph

from langchain_anthropic import ChatAnthropic
from langchain_core.prompts import ChatPromptTemplate

# Simple chain
llm = ChatAnthropic(model="claude-3-sonnet-20240229")
prompt = ChatPromptTemplate.from_template("Explain {topic} in simple terms.")
chain = prompt | llm

response = chain.invoke({"topic": "quantum computing"})

LCEL (LangChain Expression Language)

Compose chains with the pipe operator:

from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough

# Chain with parsing
chain = (
    {"topic": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

result = chain.invoke("machine learning")

RAG Pipeline

from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough

SKILL.md on GitHub