Dataset Discovery Skill

Overview

Search multiple ML dataset sources (HuggingFace Hub, OpenML, GitHub, Semantic Scholar) and return a ranked, deduplicated list of relevant datasets.

Agent Workflow

Phase 1: SCOPE

Clarify the user's needs before searching:

• Research task: What problem or domain? (e.g., "sentiment analysis", "medical image segmentation")
• Modality: image / text / tabular / audio / any
• Size preference: small (< 10K rows), medium (10K–1M), large (> 1M), any
• License preference: permissive (MIT/Apache/CC-BY), any, or specific

Phase 2: SEARCH

Run the search script with the user's query: