langchain-middlewareby LangChainOfficialDevelopmentGitHub stars: 1.3k
LangChain Middleware skill: what it does and how to install it
Covers LangChain middleware: human approval of risky tool calls, custom middleware and structured output.
Install
$ npx skills add langchain-ai/langchain-skills --skill langchain-middlewareRun it in a terminal. If your agent is already running, start a new session so it picks the skill up.
About this skill
Covers LangChain middleware: human approval of risky tool calls, custom middleware and structured output.
Similar skills
- Verification Before CompletionRequires the agent to run verification commands and confirm the output before it claims that work is complete or passing.
- Claude APIReference for the Claude API and Anthropic SDKs: model ids, pricing, parameters, streaming, tool use, MCP, caching and model migration.
- CavecrewTells Claude Code when to delegate to the cavecrew subagents for locating code, small edits and diff review, keeping output compressed.