# langchain-orchestration

A LangChain reference skill for your coding agent: chains, agents, memory, RAG and orchestration. Useful when the agent writes LangChain code and should stick to working patterns.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 451 installs · ★ 62
- Author: manutej
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/manutej/luxor-claude-marketplace/tree/HEAD/plugins/luxor-ai-integration/skills/langchain-orchestration/SKILL.md
- Updated: 2026-06-13
- HTML: https://affpapa.org/en/nevibecode/skills/langchain-orchestration

## What it does

The skill hands your agent a LangChain reference: LCEL, the Runnable interface, sequential chains, map-reduce, routers, conditional branches, agents, memory systems, RAG patterns, callbacks, streaming and error handling. The examples are Python, built on `ChatPromptTemplate`, `RunnablePassthrough`, `RunnableParallel`, `RunnableBranch` and `ChatOpenAI`.

It expects Python 3.8+ and these packages installed: `langchain>=0.1.0`, `langchain-core>=0.1.0`, `langchain-community>=0.0.20`. You also need an OpenAI key or credentials for another LLM provider, plus a vector store — FAISS, Chroma or Pinecone. Skip the key or the store and the RAG and model-call examples will not run.

The skill installs into Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode. The file lands at a path like `.cursor/skills/langchain-orchestration/SKILL.md` or `~/.claude/skills/langchain-orchestration/SKILL.md`, and the agent reads it whenever LangChain comes up.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill langchain-orchestration -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/langchain-orchestration/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/langchain-orchestration/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill langchain-orchestration -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/langchain-orchestration/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill langchain-orchestration -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/langchain-orchestration/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install manutej/luxor-claude-marketplace langchain-orchestration
```

2. **Manually: put the files in place**
- File: `.github/skills/langchain-orchestration/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill langchain-orchestration -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/manutej/luxor-claude-marketplace --path plugins/luxor-ai-integration/skills/langchain-orchestration
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/langchain-orchestration/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add manutej/luxor-claude-marketplace --skill langchain-orchestration -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/manutej/luxor-claude-marketplace/tree/HEAD/plugins/luxor-ai-integration/skills/langchain-orchestration/SKILL.md

## When to use it
- wire a prompt, model and parser into one LCEL chain
- route queries to different handlers with a router
- run map-reduce over several texts in parallel
- add memory and RAG to a chat agent
- set up streaming and callbacks for monitoring

## Example prompts
- Build an LCEL chain with a prompt, ChatOpenAI and StrOutputParser
- Make a router that sends technical questions to a separate chain
- Add a RAG pattern with Chroma and memory to the agent

## Similar
- [langchain-development](https://affpapa.org/en/nevibecode/skills/langchain-development.md) — skill · 681 installs
- [langchain-architecture](https://affpapa.org/en/nevibecode/skills/langchain-architecture.md) — skill · 13150 installs
- [langchain-python](https://affpapa.org/en/nevibecode/rules/langchain-python.md) — rule · ★ 40418
- [langchain-rag](https://affpapa.org/en/nevibecode/skills/langchain-rag.md) — skill · 17500 installs
- [langchain-dev-guide](https://affpapa.org/en/nevibecode/skills/langchain-dev-guide.md) — skill · 836 installs
- [langchain-fundamentals](https://affpapa.org/en/nevibecode/skills/langchain-fundamentals.md) — skill · 17400 installs

From the same set: [manutej/luxor-claude-marketplace](https://affpapa.org/en/nevibecode/by/manutej/luxor-claude-marketplace.md) — 31 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md