Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LigphiDonk/Oh-my--papernpx agentmods add skills/ligphidonk/oh-my--paper/dataset-discoveryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ligphidonk/oh-my--paper/dataset-discovery)<a href="https://agentmods.dev/skills/ligphidonk/oh-my--paper/dataset-discovery"><img src="https://agentmods.dev/badge/skills/ligphidonk/oh-my--paper/dataset-discovery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ligphidonk/oh-my--paper/dataset-discovery"><img src="https://agentmods.dev/badge/skills/ligphidonk/oh-my--paper/dataset-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00010 | $0.01221 |
| Opus 5 | $0.00005 | $0.00611 |
| Sonnet 5 | $0.00002 | $0.00244 |
| Haiku 4.5 | $0.00001 | $0.00122 |
Grade A, and why
dataset-discovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dataset-discovery
Canonical Summary
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 "dis...
Trigger Rules
Use this skill when the user request matches its research workflow scope. Prefer the bundled resources instead of recreating templates or reference material. Keep outputs traceable to project files, citations, scripts, or upstream evidence.
Resource Use Rules
- Treat
scripts/as optional helpers. Run them only when their dependencies are available, keep outputs in the project workspace, and explain a manual fallback if execution is blocked.
Execution Contract
- Resolve every relative path from this skill directory first.
- Prefer inspection before mutation when invoking bundled scripts.
- If a required runtime, CLI, credential, or API is unavailable, explain the blocker and continue with the best manual fallback instead of silently skipping the step.
- Do not write generated artifacts back into the skill directory; save them inside the active project workspace.
Upstream Instructions
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 fromhuggingface,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/
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 138 lines · 10 tokens per session scan A 4e3ab041badc
dataset-discovery is a skill published in the GitHub repository LigphiDonk/Oh-my--paper (722 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 1,221 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
polars
Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1-100GB datasets, ETL pipelines, faster pandas replacement. For larger-than-RAM data use dask or vaex.
hugging-face-datasets
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…
markitdown
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
vaex
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large…