langchain
Build production-ready LLM applications with chains, agents, memory, tools, and RAG pipelines using the LangChain framework
npx skills add majiayu000/claude-skill-registry --skill langchain-vamseeachanta-digitalmodel --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Instructs the agent to build production-ready LLM-powered applications using LangChain components such as chains, agents, memory, tools, and RAG pipelines. It includes guidance on installing the LangChain ecosystem, prerequisites for core features like vector stores and document processing, and examples of basic chain construction, multi-step analysis chains, React-style agents with tools, and memory-backed conversations. It also details a complete RAG pipeline and related utilities.
How it works
The skill provides concrete code snippets and installation commands to set up LangChain and its ecosystem. It outlines:
- Basic chain creation (simple chain and multi-step analysis chain) using LangChain components and Python snippets.
- An example React-style agent with tools, including example tools like calculate_mooring_tension, get_wave_data, and search_engineering_database, and how to assemble an agent executor with error handling.
- Conversation memory options: a Conversation Buffer Memory example and a Summary Memory example for long chats, including usage patterns for session-based histories and memory wrapping.
- A complete RAG pipeline example that loads documents, creates embeddings, stores in a vector store, and queries with a retrieval-augmented generation workflow.
The material emphasizes how to install dependencies, define prompts, compose chains, manage memory, and integrate tools within a Python environment.
When to use it
Use for building complex LLM applications needing multiple LangChain components, tool-enabled agents with autonomous decisions, retrieval-augmented generation, multi-provider LLM support, memory for conversations, document processing, and streaming responses.
What it can touch
The skill references handling tools and integration with external components (e.g., Read, Write, Bash, Grep) and a selection of LangChain modules for chains, agents, memory, and RAG. It implies using Python platforms and specific libraries such as langchain, langchain-openai, langchain-core, chromadb, faiss-cpu, unstructured, pypdf, docx2txt, and duckduckgo-search. It also shows usage of tools defined with @tool and integration with a ReAct-based agent from a hub prompt.
Caveats
The material includes simulated data in some tool examples (e.g., get_wave_data and search_engineering_database return mocked results) and may require replacing with real API calls or data sources. It instructs on environment variable setup for OPENAI_API_KEY and, in some cases, ANTHROPIC_API_KEY. It does not guarantee production-grade behavior beyond examples.
# LangChain Skill > Build production-ready LLM-powered applications with chains, agents, memory, and RAG pipelines. ## Quick Start ```bash # Install LangChain ecosystem pip install langchain langchain-openai langchain-community langchain-core # Install vector store dependencies pip install chromadb faiss-cpu # Install document loaders pip install unstructured pypdf docx2txt # Set API key export OPENAI_API_KEY="your-api-key" ``` ## When to Use This Skill **USE when:** - Building complex LLM applications with multiple components - Need agents that can use tools and make autonomous decisions - Implementing RAG (Retrieval Augmented Generation) systems - Integrating with various LLM providers (OpenAI, Anthropic, local models) - Building chatbots with conversation memory - Processing and querying document collections - Need streaming responses for real-time applications - Orchestrating multi-step reasoning workflows **DON'T USE when:** - Simple single-prompt LLM calls (use direct API) - Optimizing prompts programmatically (use DSPy instead) - Building UI-focused chat applications (use Streamlit/Gradio directly) - Need minimal dependencies and maximum control - Performance-critical applic
- Quick Start
- When to Use This Skill
- Prerequisites
- Core Capabilities
- 1. Basic Chain Composition
- 2. Agent with Tools
- 3. Conversation Memory
- 4. RAG (Retrieval Augmented Generation)
- 5. Document Processing
- 6. Streaming Responses
- Complete Examples
- Example 1: Engineering Documentation Assistant
- Example 2: Multi-Tool Research Agent
- Integration Patterns
Install LangChain ecosystem pip install langchain langchain-openai langchain-community langchain-core Install vector store dependencies pip install chromadb faiss-cpu Install document loaders pip install unstructured pypdf docx2txt Set API key export OPENAI_API_KEY="your-api-key" Core installation pip install langchain>=0.2.0 langchain-openai>=0.1.0 langchain-core>=0.2.0
What does the langchain skill do?
Build production-ready LLM applications with chains, agents, memory, tools, and RAG pipelines using the LangChain framework
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill langchain-vamseeachanta-digitalmodel --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.