langchain-ai/lca-skills

langsmith-code-eval

Creates 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…

لغة النص الأصلي: الإنجليزية

langsmith-fetch

Fetches LangSmith traces for debugging agent behavior. Use when troubleshooting agent issues, reviewing conversation history, or investigating tool calls.

لغة النص الأصلي: الإنجليزية