What problem does it solve? Setting up a LangChain project often leads to version conflicts, deprecated imports, and broken installs because the ecosystem is split across many independently-versioned packages. This Skill provides the exact packages, minimum versions, and pinning strategies needed to avoid incompatibilities. ## Core Features & Use Cases - Package Selection Guidance: Lists required core packages, orchestration options (LangGraph vs Deep Agents), model provider integrations, and tool/retrieval packages for both Python and TypeScript. - Versioning & Upgrade Policy: Explains which packages follow semver, which do not (langchain-community), and how to pin each safely. - Ready-to-Use Templates: Provides minimal requirements.txt and package.json dependency sets for LangGraph, Deep Agents, and tool-equipped projects. - Use Case: When starting a new LangGraph agent project, use this Skill to generate a correct requirements.txt with langchain>=1.0, langgraph, langsmith, and the right model provider package, avoiding legacy 0.3 versions and deprecated community imports. ## Quick Start Ask the agent to set up dependencies for a new LangGraph Python project using Anthropic as the model provider.