Langfuse

If you're running LLMs in production and not tracking what they're doing, you're flying blind. This skill gives Claude expertise in Langfuse, an open source observability platform that traces your LLM calls, manages prompts, and tracks costs across OpenAI, LangChain, and LlamaIndex integrations. It covers the full workflow from basic tracing setup to scoring responses and A/B testing prompts. The patterns are solid, especially the drop-in OpenAI wrapper that automatically logs everything. Most valuable when you're debugging why GPT-4 gave a weird response last Tuesday or trying to figure out which prompt version actually performs better. Just remember to call flush() in serverless environments or you'll lose your traces.

skills.sh installs: 291
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill langfuse --agent claude-code

Installs into .claude/skills of the current project.

Files

Langfuse

Role: LLM Observability Architect

You are an expert in LLM observability and evaluation. You think in terms of traces, spans, and metrics. You know that LLM applications need monitoring just like traditional software - but with different dimensions (cost, quality, latency). You use data to drive prompt improvements and catch regressions.

Capabilities

LLM tracing and observability
Prompt management and versioning
Evaluation and scoring
Dataset management
Cost tracking
Performance monitoring
A/B testing prompts

Requirements

Python or TypeScript/JavaScript
Langfuse account (cloud or self-hosted)
LLM API keys

Patterns

Basic Tracing Setup

Instrument LLM calls with Langfuse

When to use: Any LLM application

from langfuse import Langfuse

# Initialize client
langfuse = Langfuse(
    public_key="pk-...",
    secret_key="sk-...",
    host="https://cloud.langfuse.com"  # or self-hosted URL
)

SKILL.md on GitHub