langfuse-dataset-management

Name: langfuse-dataset-management
Availability: InStock
Author: mberto10

Create Langfuse datasets and add traces for regression testing.

Updated Aug 27, 2026

Search Tags:#regression testing #langfuse #dataset #data curation #experiment validation #trace management

Ready to run

npx skills add https://github.com/mberto10/mberto-compound --skill langfuse-dataset-management

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: langfuse-dataset-management
Source: https://github.com/mberto10/mberto-compound/tree/main/plugins/langfuse-analyzer/skills/dataset-management
Command: npx skills add https://github.com/mberto10/mberto-compound --skill langfuse-dataset-management

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the process of creating and managing datasets within Langfuse, enabling efficient experiment validation and regression testing by curating production traces.

Core Features & Use Cases

Dataset Creation: Easily create new datasets with descriptive names and metadata.
Trace Management: Add individual traces or batches of traces to datasets, specifying expected outcomes.
Dataset Inspection: List existing datasets and retrieve their items for review.
Use Case: Automatically build a regression test set by adding all traces with a score below 7.0 from the last 24 hours into a dataset named checkout_regressions.

Quick Start

Use the langfuse-dataset-management skill to create a new dataset named api_v2_golden_set with the description Verified high-quality outputs for baseline.

Frequently Asked Questions about langfuse-dataset-management

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

FAQPage Schema

How do I create regression testing datasets from production traces in Langfuse?▼

To create a regression testing dataset, you curate production traces into structured test sets. You can create new datasets with descriptive names and add individual traces or batches while specifying expected scores and outputs for quality assurance.

Can I batch add traces to a Langfuse dataset for experiment validation?▼

Yes, you can batch add traces to a Langfuse dataset for experiment validation by loading traces from files. This allows you to specify expected outcomes and efficiently build structured test sets for quality assurance.

What is the best way to curate low-scoring production traces into a test set?▼

The best way to curate low-scoring production traces is to filter traces below a specific score threshold, such as 7.0, from a recent time window and add them to a named dataset. This facilitates automated regression test set creation.

Does Langfuse dataset management support listing existing datasets and retrieving items?▼

Yes, Langfuse dataset management supports listing existing datasets and retrieving their items for review. This dataset inspection capability allows you to verify the contents and quality of your structured test sets.

How do I specify expected outputs when adding traces to a Langfuse dataset?▼

When adding individual traces or batches from files to a Langfuse dataset, you can specify expected scores and outputs. This ensures your curated production traces have defined outcomes for accurate experiment validation and regression testing.