Does this skill require external software?

Yes, you must have the langsmith-fetch CLI installed via pip and have your LANGSMITH_API_KEY and LANGSMITH_PROJECT environment variables configured.

What output formats are supported?

The skill supports 'pretty' format for human-readable terminal output, 'json' for detailed data analysis, and 'raw' for piping into other command-line tools.

What is the LangSmith Fetch Claude Skill?

It is a specialized capability for Claude Code that allows you to interact with LangSmith Studio to retrieve, analyze, and debug execution traces for AI agents.

How do I identify why my agent is slow?

You can use the 'Performance Issues' workflow to export traces with metadata, allowing the skill to analyze tool call latencies and identify bottlenecks.

Can I use this for LangGraph agents?

Absolutely. This skill is designed to work with both standard LangChain implementations and complex LangGraph state machines.

LangSmith Fetch

Name: LangSmith Fetch
Author: ComposioHQ

byComposioHQ

•

22,944

Analíticas y Monitorización

Debugs LangChain and LangGraph agents by fetching and analyzing execution traces directly from LangSmith Studio.

Acerca de

LangSmith Fetch is a specialized debugging skill designed to streamline the analysis of LangChain and LangGraph agents. It allows developers to retrieve recent execution traces, investigate tool calls, check memory operations, and analyze performance metrics without leaving the terminal. By integrating directly with LangSmith Studio via the CLI, it provides actionable insights into agent failures, token usage, and complex execution flows, making it an essential tool for developers building and optimizing production-grade AI agent workflows.

Características Principales

Debug Long-Term Memory (LTM) and state operations
Fetch and analyze recent execution traces
Deep dive into specific tool calls and results
22,944 GitHub stars
Export full debug sessions for team collaboration
Monitor token usage and execution latency

Casos de Uso

Optimizing LLM costs by reviewing token usage per trace
Identifying the root cause of agent execution errors
Analyzing why an agent selected a specific tool or reasoning path

Acerca de

Características Principales

Debug Long-Term Memory (LTM) and state operations
Fetch and analyze recent execution traces
Deep dive into specific tool calls and results
22,944 GitHub stars
Export full debug sessions for team collaboration
Monitor token usage and execution latency

Casos de Uso

Optimizing LLM costs by reviewing token usage per trace
Identifying the root cause of agent execution errors
Analyzing why an agent selected a specific tool or reasoning path