skills.rest
infantesromeroadrian
infantesromeroadrianCOMMUNITY
Explore all skills by this author →
Website𝕏@infantes_adrianGitHub

observability-llm-call-tracing

Monitor and log LLM API call latency, token usage, costs, and errors.

Updated Jun 21, 2026
Search Tags:#machine learning#error logging#cost analysis#performance monitoring#LLM tracing
One-click install
npx skills add https://github.com/infantesromeroadrian/arca-agent --skill observability-llm-call-tracing
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: observability-llm-call-tracing
Source: https://github.com/infantesromeroadrian/arca-agent/tree/main/template/skills/observability-llm-call-tracing
Command: npx skills add https://github.com/infantesromeroadrian/arca-agent --skill observability-llm-call-tracing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires langfuse, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of monitoring and analyzing calls to Language Learning Models (LLMs) by providing detailed metrics and logging, enabling users to understand and optimize their LLM interactions.

Core Features & Use Cases

  • LLM API Call Tracing: Track the latency, tokens, and costs associated with each LLM call.
  • Error and Cost Analysis: Identify issues and optimize costs associated with LLM calls.
  • Use Case: For a machine learning engineer who needs to ensure their LLM calls are efficient and within budget, this Skill will provide a comprehensive view of each call's performance.

Quick Start

Instrument your LLM calls using the observability-llm-call-tracing skill.

Frequently Asked Questions about observability-llm-call-tracing

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I trace LLM API calls for latency and token usage?▼

To trace LLM API calls for latency and token usage, you can instrument your machine learning workflows to monitor and log execution details. This provides comprehensive metrics for each interaction to ensure performance efficiency.

What is LLM tracing and when do I need it for machine learning workflows?▼

LLM tracing is the process of monitoring and logging execution details of Language Learning Model interactions. You need it in machine learning workflows to understand performance bottlenecks and analyze call metrics.

Does LLM tracing work with Langfuse for error logging?▼

Yes, LLM tracing requires Langfuse as a dependency to support error logging. It captures error contexts alongside performance metrics to help identify issues within your machine learning workflows.

What's the best way to analyze LLM call costs and identify budget issues?▼

The best way to analyze LLM call costs is to use a tracing skill that logs execution details and calculates expenses per call. This identifies budget issues by providing a comprehensive view of cost efficiency.

Why does my LLM API call tracing not capture error contexts properly?▼

LLM API call tracing may fail to capture error contexts if your machine learning workflow is not properly instrumented. Ensuring Langfuse is configured correctly will help log detailed error contexts for analysis.

Related Skills

Explore More Software Engineering Skills→
jurislmjurislm

langfuse

Manage Langfuse prompts, traces, observations, and scores via MCP.

Official
Intermediate
Zack2626-okZack2626-ok

querying-mlflow-metrics

Fetches and analyzes MLflow performance metrics including token usage, latency, and trace counts.

Community
Advanced
Axel-DaMageAxel-DaMage
2

monitoring-expert

Configure Prometheus and Grafana monitoring, alerting, and tracing systems.

Community
Advanced
nexus-labs-automationnexus-labs-automation
7

llm-call-tracing

Trace LLM API calls to capture model, latency, tokens, cost, and success status.

Official
Advanced