composiohq avatar

Langsmith Fetch

When your LangChain or LangGraph agent does something weird and you need to know why, this fetches execution traces straight from LangSmith Studio into your terminal. You get pretty-printed summaries of what tools fired, where errors happened, token usage, and execution timing. The skill walks you through common debugging scenarios like "why did it call the wrong tool" or "memory isn't working" with specific grep commands and analysis patterns. You'll need the langsmith-fetch CLI installed and your API keys set up, but once configured it's faster than clicking through the web UI when you just want to see what broke in the last five minutes. The structured workflows for error detection and performance analysis are genuinely useful if you're running agentic systems in production.

skills.sh installs
4.4K
GitHub stars
79.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add composiohq/awesome-claude-skills --skill langsmith-fetch --agent claude-code

Installs into .claude/skills of the current project.

Files

LangSmith Fetch - Agent Debugging Skill

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

When to Use This Skill

Automatically activate when user mentions:

  • 🐛 "Debug my agent" or "What went wrong?"
  • 🔍 "Show me recent traces" or "What happened?"
  • ❌ "Check for errors" or "Why did it fail?"
  • 💾 "Analyze memory operations" or "Check LTM"
  • 📊 "Review agent performance" or "Check token usage"
  • 🔧 "What tools were called?" or "Show execution flow"

Prerequisites

1. Install langsmith-fetch

pip install langsmith-fetch

2. Set Environment Variables

export LANGSMITH_API_KEY="your_langsmith_api_key"
export LANGSMITH_PROJECT="your_project_name"

Verify setup:

echo $LANGSMITH_API_KEY
echo $LANGSMITH_PROJECT

Core Workflows

Workflow 1: Quick Debug Recent Activity

When user asks: "What just happened?" or "Debug my agent"

Execute:

langsmith-fetch traces --last-n-minutes 5 --limit 5 --format pretty

Sponsors

Details

Repository
github.com/composiohq/awesome-claude-skills
Categories
AI & Agent Building, Debugging, CLI & Terminal

More from composiohq/awesome-claude-skills

All 32
1gokapso avatarautomate-whatsappgokapso/agent-skillsBuild WhatsApp automations with Kapso workflows: configure WhatsApp triggers, edit workflow graphs, manage executions, deploy functions, search workflow Logs, a4.4Kskills.sh installs
2grafana avatarml-aigrafana/skillsTurn on AI + ML features in Grafana Cloud — Grafana Assistant (NL → PromQL/LogQL/TraceQL, dashboard build, incident investigation, MCP integration), Dynamic Ale4.4Kskills.sh installs
3softaworks avatarwriting-clearly-and-conciselysoftaworks/agent-toolkitUse when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for c4.4Kskills.sh installs
4wordpress avatarwpdswordpress/agent-skillsUse when building UIs leveraging the WordPress Design System (WPDS) and its components, tokens, patterns, etc.4.3Kskills.sh installs
5amelnagdy avatartest-guardamelnagdy/guard-skillsReview generated or changed test code against universal testing rules before it ships. Best used reactively after an agent writes, edits, generates, or refactor4.3Kskills.sh installs
6dpearson2699 avatarapple-on-device-aidpearson2699/swift-ios-skillsBuild private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp. Use when choosing an Apple-local model r4.2Kskills.sh installs