Implement techniques from DSGym: A Holistic Framework for Evaluating and Training Data Science Agents. Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings
Scanned 9/9/2026
Install to Claude Code
npx -y skills add ADu2021/skillXiv --skill dsgym-a-holistic-framework-for-evaluating-and-trai --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Dsgym A Holistic Framework For Evaluating And Trai?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/adu2021-dsgym-a-holistic-framework-for-evaluating-and-trai)More formats (shields.io, HTML) on the badges page.
---
name: dsgym-a-holistic-framework-for-evaluating-and-trai
title: "DSGym: A Holistic Framework for Evaluating and Training Data Science Agents"
version: 0.0.2
engine: skillxiv-v0.0.2-claude-opus-4.6
license: MIT
url: "https://arxiv.org/abs/2601.16344"
keywords: ["agent", "training", "benchmark", "framework"]
description: "Implement techniques from DSGym: A Holistic Framework for Evaluating and Training Data Science Agents. Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings"
---
## Overview
This skill implements concepts from the research paper [[2601.16344](https://arxiv.org/abs/2601.16344)].
## When to Use
- When you need to implement techniques described in this paper
- When working on problems that this research addresses
- When you want to understand the core concepts and methodology
## When NOT to Use
- This skill provides research-level insights; production implementations may require additional engineering
- Some concepts may require significant tuning for specific use cases
- Always evaluate applicability to your specific problem domain
## Key Concepts
The paper addresses: Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings. Yet existing data science benchmarks fall short due to fragmented evaluation interfaces that make cross-benchmark comparison difficult, narrow task coverage and a lack of...
For detailed methodology and implementation details, refer to the [full paper](https://arxiv.org/html/2601.16344).
Is this your skill, or is something wrong with this listing? . Author removals are honored within 72 hours.
No comments yet. Be the first to comment!