langsmith-code-evalCreates code-based evaluators for LangSmith-traced agents. Use when building custom evaluation logic, testing tool usage patterns, or scoring agent outputs programmatically. Triggers on requests to evaluate agents, create evaluators, or run experiments…langsmith-fetchFetches LangSmith traces for debugging agent behavior. Use when troubleshooting agent issues, reviewing conversation history, or investigating tool calls.
仓库浏览
langchain-ai · 仓库与代表性 skills - 第 2 页
按仓库查看 15 个 GitHub 仓库中的 115 个已收集 skills。