What metrics does this Langfuse skill track?

It tracks total traces, generations, LLM call latency (histograms), token usage, USD cost estimation, error counts, and SDK flush health.

Do I need an external metrics server to use this?

Yes, this skill is designed to work with Prometheus (or compatible backends) for scraping data and Grafana for visualization.

Can I calculate costs for specific AI models?

Yes, the skill includes a model pricing map that allows you to track and alert on projected daily LLM costs in USD.

Does this work with Next.js applications?

Absolutely. It includes specific implementation steps for exposing metrics via Next.js API routes as well as Express.js.

Langfuse Observability

Name: Langfuse Observability
Author: jeremylongshore

byjeremylongshore

•

1,243

•

Analytics & Monitoring

Implements comprehensive monitoring, metrics, and alerting for Langfuse LLM operations using Prometheus and Grafana.

This skill enables developers to integrate robust observability into their LLM-powered applications by providing a pre-configured instrumentation layer for the Langfuse SDK. It facilitates the tracking of critical metrics such as token usage, costs, latencies, and error rates, while offering ready-to-use Prometheus configurations and Grafana dashboard templates to visualize application health and performance in real-time. It is essential for teams looking to maintain production-grade reliability and cost control over their AI features.

Key Features

01Custom Prometheus metrics for traces, generations, and token costs

02Instrumented TypeScript wrapper for automatic Langfuse telemetry

03Pre-configured Grafana dashboard JSON for LLM performance visualization

04Production-ready AlertManager rules for error rates and latency spikes

05Metrics endpoint implementation for Next.js and Express environments

061,243 GitHub stars

Use Cases

01Debugging performance bottlenecks and high-latency generation pipelines

02Monitoring production LLM application costs and token consumption in real-time

03Setting up proactive alerts for high LLM error rates or service disruptions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jeremylongshore/claude-code-plugins-plus-skills langfuse-observability

For use in Claude.ai and ChatGPT

Download Skill

Key Features

01Custom Prometheus metrics for traces, generations, and token costs

02Instrumented TypeScript wrapper for automatic Langfuse telemetry

03Pre-configured Grafana dashboard JSON for LLM performance visualization

04Production-ready AlertManager rules for error rates and latency spikes

05Metrics endpoint implementation for Next.js and Express environments

061,243 GitHub stars

Use Cases

01Debugging performance bottlenecks and high-latency generation pipelines

02Monitoring production LLM application costs and token consumption in real-time

03Setting up proactive alerts for high LLM error rates or service disruptions

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jeremylongshore/claude-code-plugins-plus-skills langfuse-observability

For use in Claude.ai and ChatGPT

Download Skill