Langgraph Project Setup

What it does

When your agent uses it

• Create a new LangGraph project
• Set up langgraph.json for deployment
• Configure environment variables for LLM providers
• Initialize project structure for agents

Example prompts

• “/langgraph-project-setup”

Requirements

• Python 3
• Node.js
• Docker
• A credential in OPENAI_API_KEY
• A credential in ANTHROPIC_API_KEY

Workflow steps

8 steps, taken from the step headings in SKILL.md.

1. 1Choose Project Pattern
2. 2Initialize Project
3. 3Install Dependencies
4. 4Configure Environment Variables
5. 5Implement Agent Logic
6. 6Configure langgraph.json
7. 7Start Development Server
8. 8Connect to LangGraph Studio

What it can do on your machine

Read from SKILL.md and the folder at commit a2d4a10. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 4 files in scripts/ (Python and JavaScript), which the agent can run.

  Shell commands in SKILL.md call:

  • uv
  • python3
  • node
  • pip
  • npm
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • smith.langchain.com

  Also links to:

  • docs.langchain.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPENAI_API_KEY
  • ANTHROPIC_API_KEY
  • LANGSMITH_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Langgraph Project Setup loads about 2.4k tokens when it runs, and up to ~7.3k if it reads all its reference files. Until then it costs about 138 tokens; SKILL.md has 513 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~138

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~7.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:86

  - `.env` template

• NoteMentions a .env fileSKILL.md:130

  Edit `.env` file directly:

• NoteMentions a .env fileSKILL.md:174

  "env": ".env",

• NoteMentions a .env fileSKILL.md:335

  - Check `.env` file exists in project root

• NoteMentions a .env fileSKILL.md:336

  - Verify `"env": ".env"` in langgraph.json

• NoteMentions a .env fileSKILL.md:337

  - Ensure no quotes around values in .env

• NoteMentions a .env fileSKILL.md:400

  run scripts/setup_providers.py [--output .env]

• NoteMentions a .env fileSKILL.md:403

  on3 scripts/setup_providers.py [--output .env]

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from soba-labs/langchain-agent-skills at commit a2d4a10, republished under its MIT licence (© soba-labs). 513 words, ~2,407 tokens.

name

langgraph-project-setup

description

Initialize and configure LangGraph projects with proper structure, langgraph.json configuration, environment variables, and dependency management. Use when users want to (1) create a new LangGraph project, (2) set up langgraph.json for deployment, (3) configure environment variables for LLM providers, (4) initialize project structure for agents, (5) set up local development with LangGraph Studio, (6) configure dependencies (pyproject.toml, requirements.txt, package.json), or (7) troubleshoot project configuration issues.

# Initialize new project
uv run scripts/init_langgraph_project.py my-agent

# Fallback if uv not available
python3 scripts/init_langgraph_project.py my-agent

# Or with options
uv run scripts/init_langgraph_project.py my-agent \
  --pattern multiagent \
  --python-version 3.12

# Fallback if uv not available
python3 scripts/init_langgraph_project.py my-agent \
  --pattern multiagent \
  --python-version 3.12

# Initialize new project
node scripts/init_langgraph_project.js my-agent

# TypeScript project
node scripts/init_langgraph_project.js my-agent --typescript

# Multi-agent pattern
node scripts/init_langgraph_project.js my-agent \
  --pattern multiagent \
  --typescript

# Python - simple
uv run scripts/init_langgraph_project.py my-agent

# Fallback if uv not available
python3 scripts/init_langgraph_project.py my-agent

# Python - multi-agent
uv run scripts/init_langgraph_project.py my-agent --pattern multiagent

# Fallback if uv not available
python3 scripts/init_langgraph_project.py my-agent --pattern multiagent

# JavaScript/TypeScript - simple
node scripts/init_langgraph_project.js my-agent --typescript

# JavaScript/TypeScript - multi-agent
node scripts/init_langgraph_project.js my-agent --pattern multiagent --typescript

cd my-agent
uv venv --python 3.12
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e '.[dev]'

# Fallback if uv not available
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -e '.[dev]'

cd my-agent
npm install  # or: yarn install / pnpm install

uv run scripts/setup_providers.py

# Required: Choose at least one LLM provider
OPENAI_API_KEY=sk-...
# or
ANTHROPIC_API_KEY=sk-ant-...

# Optional: Enable tracing
LANGSMITH_API_KEY=lsv2_...
LANGSMITH_TRACING=true
LANGSMITH_PROJECT=my-project

{
  "dependencies": ["."],
  "graphs": {
    "agent": "./my_agent/agent.py:graph"
  },
  "env": ".env",
  "python_version": "3.11"
}

langgraph dev

langgraph up

https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024

langgraph dev --tunnel

uv run scripts/validate_langgraph_config.py

# Start server
langgraph dev

# In another terminal, test with curl
curl -X POST http://localhost:2024/invoke \
  -H "Content-Type: application/json" \
  -d '{"input": {"messages": [{"role": "user", "content": "Hello"}]}}'

# pyproject.toml
[project.optional-dependencies]
openai = ["langchain-openai>=1.1.0"]

# agent.py
from langchain_openai import ChatOpenAI

model = ChatOpenAI(model="gpt-4o-mini")

# pyproject.toml
[project.optional-dependencies]
anthropic = ["langchain-anthropic>=1.1.0"]

# agent.py
from langchain_anthropic import ChatAnthropic

model = ChatAnthropic(model="claude-haiku-4-5-20251001")

// package.json
{
  "dependencies": {
    "@langchain/openai": "^1.1.0"
  }
}

// agent.ts
import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({ model: "gpt-4o-mini" });

# Python
uv pip install -e '.[dev]'

# Fallback if uv not available
pip install -e '.[dev]'

# JavaScript
npm install

uv run scripts/init_langgraph_project.py <name> [--pattern simple|multiagent] [--python-version 3.11|3.12|3.13]

# Fallback if uv not available
python3 scripts/init_langgraph_project.py <name> [--pattern simple|multiagent] [--python-version 3.11|3.12|3.13]

node scripts/init_langgraph_project.js <name> [--pattern simple|multiagent] [--typescript]

uv run scripts/validate_langgraph_config.py [path/to/langgraph.json]

# Fallback if uv not available
python3 scripts/validate_langgraph_config.py [path/to/langgraph.json]

uv run scripts/setup_providers.py [--output .env]

# Fallback if uv not available
python3 scripts/setup_providers.py [--output .env]

© soba-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (scripts, references, assets) in skills/langgraph-project-setup of soba-labs/langchain-agent-skills.

• SKILL.md
• assets/templates/.env.example
• assets/templates/package.json
• assets/templates/pyproject.toml
• references/deployment-targets.md
• references/javascript-project-structure.md
• references/langgraph-json-schema.md
• references/provider-configuration.md
• references/python-project-structure.md
• scripts/init_langgraph_project.js
• scripts/init_langgraph_project.py
• scripts/setup_providers.py
• scripts/validate_langgraph_config.py

Open the folder on GitHubat commit a2d4a10