Give your agents
Skills runtime

import { createAgent } from "langchain";
import { HumanMessage } from "@langchain/core/messages";
import { Bluebag } from "@bluebag/langchain";

const bluebag = new Bluebag({
  apiKey: process.env.BLUEBAG_API_KEY,
});

const config = await bluebag.enhance({
  model: "openai:gpt-4o",
  tools: [yourCustomTool],
  systemMessage: "You are a helpful assistant.",
  messages: [new HumanMessage("Analyze this document")],
});

const agent = createAgent({
  model: config.model,
  tools: config.tools,
  systemPrompt: config.systemMessage,
});

const result = await agent.invoke({ messages: config.messages });

# Install the CLI
npm install -g @bluebag/cli

# Authenticate (one time)
bluebag auth

# Pull existing skills from your project
bluebag pull

# Create a new skill locally
mkdir skills/code-review
cat > skills/code-review/SKILL.md << 'EOF'
---
name: code-review
description: Reviews code for best practices
---

# Code Review

Review the provided code for:
1. Security vulnerabilities
2. Performance issues
3. Best practice violations
EOF

# Push to BlueBag (versioned automatically)
bluebag push