INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/langchain-ai/langchain-skills/main/config/skills/langchain-middleware/SKILL.mdRegistry
github (via claudemarketplaces.com)