OthmanAdi

Langsmith Fetch Skill — AI skill for Claude Code

AI community

🔍 AI observability skill for Claude Code.

How to install Langsmith Fetch Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open OthmanAdi/langsmith-fetch-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Langsmith Fetch Skill does

🔍 AI observability skill for Claude Code. Debug LangChain/LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal.

Alternatives in AI

  • Qiaomu Markdown Proxy — Fetch any URL as clean Markdown via proxy services (r.jina.ai / defuddle.md) or built-in scripts 426 ★
  • Multi Agent AI System — Building a Multi-Agent AI System with LangGraph and LangSmith 374 ★
  • Debug Skill — Give your AI agent a real debugger — breakpoints, stepping, variable inspection, and stack traces via CLI 218 ★

README

langsmith-fetch

🔍 LangSmith Fetch Skill for Claude Code

**AI observability & debugging skill for Claude!**

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio directly in your terminal using Claude Code.

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Claude Code](https://img.shields.io/badge/Claude-Code-blue)](https://code.claude.com) [![LangSmith](https://img.shields.io/badge/LangSmith-Fetch-green)](https://github.com/langchain-ai/langsmith-fetch)


🎯 What It Does

This Claude Code skill teaches Claude how to debug your LangChain and LangGraph agents by automatically fetching and analyzing execution traces from LangSmith Studio.

**Just ask Claude:**

  • "Debug my agent"
  • "What went wrong?"
  • "Show me recent traces"
  • "Why is my agent slow?"

Claude will automatically fetch traces, analyze execution patterns, identify errors, and provide actionable insights!


✨ Features

  • 🐛 Automatic Debugging - Claude fetches and analyzes traces autonomously
  • 🔍 Error Detection - Identifies failures and root causes
  • 📊 Performance Analysis - Tracks execution time and token usage
  • 💾 Memory Operations - Checks LTM recall/store operations
  • 🛠️ Tool Call Analysis - Reviews which tools were called and why
  • 📁 Session Export - Saves debugging sessions for later review
  • 🤝 Multi-Agent Support - Debugs orchestration decisions

🚀 Quick Start

1. Install Prerequisites

# Install langsmith-fetch CLI
pip install langsmith-fetch

2. Configure Environment

# Set your LangSmith credentials
export LANGSMITH_API_KEY="your_langsmith_api_key"
export LANGSMITH_PROJECT="your_project_name"

Get your API key from: https://smith.langchain.com/

3. Install the Skill

npx skills add OthmanAdi/langsmith-fetch-skill