langfuse-agent-eval-setup

Community

Set up agent evaluation pipeline.

Authormberto10
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the setup of an evaluation pipeline for an agent, streamlining the process of assessing agent performance and quality.

Core Features & Use Cases

  • Agent Flow Discovery: Automatically analyzes an agent's codebase to understand its execution flow, LLM calls, and tool usage.
  • Quality Dimension Definition: Helps in identifying and defining relevant quality dimensions for evaluation based on prompts and logic.
  • Langfuse Asset Creation: Integrates with Langfuse to create datasets, judge prompts, and generate local evaluation configurations.
  • Use Case: A developer wants to evaluate a new customer support agent. This Skill will help them discover the agent's logic, define what "good" customer support looks like (e.g., accuracy, helpfulness), create a dataset of customer interactions, and set up a configuration to run evaluations in Langfuse.

Quick Start

Use the langfuse-agent-eval-setup skill to begin setting up an evaluation for the 'customer-support-agent'.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: langfuse-agent-eval-setup
Download link: https://github.com/mberto10/mberto-compound/archive/main.zip#langfuse-agent-eval-setup

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.