How do I install the Dataset Discovery skill?

Run npx skillmds@latest add gabrielmoreira/dataset-discovery in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dataset Discovery safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dataset Discovery?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dataset Discovery free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Dataset Discovery?

gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dataset Discovery by gabrielmoreira

Name: Dataset Discovery
Rating: 4.2 (5 reviews)
Author: gabrielmoreira

Dataset Discovery

Multi-source ML dataset discovery. Search HuggingFace Hub, OpenML, GitHub, and paper cross-references for datasets relevant to a research task. Use when asked to "find datasets for", "search ML datasets", "what datasets exist for", or "discover training data for".

gabrielmoreira Updated Sep 21, 2026 17 repo stars

File contents

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:

python3 scripts/search_ml_datasets.py search --query "<query>" --sources huggingface,openml,github,papers --max 30

Options:

--sources: Comma-separated list from huggingface, openml, github, papers. Default: all four.
--max: Maximum results to return after dedup + ranking. Default: 30.
--modality: Filter by modality (image, text, tabular, audio).
--workspace: Output directory. Default: ./datasets/discovery/

Optionally also call HF MCP tool hub_repo_search with repo_types: ["dataset"] for semantic search to supplement results.

Phase 3: PRESENT

Show results as a markdown table:

Name	Source	Downloads	Size	License	Tags	URL

Sort by relevance score (highest first).

Phase 4: DETAIL

When the user wants more info on a specific dataset:

python3 scripts/search_ml_datasets.py detail --dataset-id "huggingface:stanfordnlp/imdb" --workspace ./datasets/discovery/

Writes metadata.json and README.md to {workspace}/datasets/{source}_{slug}/.

Phase 5: PULL

When the user wants to preview data:

python3 scripts/search_ml_datasets.py pull --dataset-id "huggingface:stanfordnlp/imdb" --sample-rows 20 --workspace ./datasets/discovery/

Writes sample.jsonl to {workspace}/datasets/{source}_{slug}/.

For full dataset download, confirm with the user first, then use huggingface-cli download or equivalent.

Workspace Layout

{workspace}/                         # default: ./datasets/discovery/
  search-{YYYY-MM-DD}.json           # search results log
  datasets/
    {source}_{slug}/
      metadata.json                  # detailed metadata
      README.md                      # human-readable summary
      sample.jsonl                   # sample rows

Dependencies

Python 3.8+
requests (stdlib-adjacent, universally available)
gh CLI (for GitHub source only)
No other packages required

---name: dataset-discoverydescription: Multi-source ML dataset discovery. Search HuggingFace Hub, OpenML, GitHub, and paper cross-references for datasets relevant to a research task. Use when asked to "find datasets for", "search ML datasets", "what datasets exist for", or "discover training data for".---# Dataset Discovery Skill## OverviewSearch multiple ML dataset sources (HuggingFace Hub, OpenML, GitHub, Semantic Scholar) and return a ranked, deduplicated list of relevant datasets.## Agent Workflow### Phase 1: SCOPEClarify 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: SEARCHRun the search script with the user's query:```bashpython3 scripts/search_ml_datasets.py search --query "<query>" --sources huggingface,openml,github,papers --max 30```Options:- `--sources`: Comma-separated list from `huggingface`, `openml`, `github`, `papers`. Default: all four.- `--max`: Maximum results to return after dedup + ranking. Default: 30.- `--modality`: Filter by modality (`image`, `text`, `tabular`, `audio`).- `--workspace`: Output directory. Default: `./datasets/discovery/`Optionally also call HF MCP tool `hub_repo_search` with `repo_types: ["dataset"]` for semantic search to supplement results.### Phase 3: PRESENTShow results as a markdown table:| Name | Source | Downloads | Size | License | Tags | URL ||------|--------|-----------|------|---------|------|-----|Sort by relevance score (highest first).### Phase 4: DETAILWhen the user wants more info on a specific dataset:```bashpython3 scripts/search_ml_datasets.py detail --dataset-id "huggingface:stanfordnlp/imdb" --workspace ./datasets/discovery/```Writes `metadata.json` and `README.md` to `{workspace}/datasets/{source}_{slug}/`.### Phase 5: PULLWhen the user wants to preview data:```bashpython3 scripts/search_ml_datasets.py pull --dataset-id "huggingface:stanfordnlp/imdb" --sample-rows 20 --workspace ./datasets/discovery/```Writes `sample.jsonl` to `{workspace}/datasets/{source}_{slug}/`.For full dataset download, confirm with the user first, then use `huggingface-cli download` or equivalent.## Workspace Layout```{workspace}/ # default: ./datasets/discovery/ search-{YYYY-MM-DD}.json # search results log datasets/ {source}_{slug}/ metadata.json # detailed metadata README.md # human-readable summary sample.jsonl # sample rows```## Dependencies- Python 3.8+- `requests` (stdlib-adjacent, universally available)- `gh` CLI (for GitHub source only)- No other packages required

Frequently asked questions