Searches Kaggle, Hugging Face, and GitHub for raw datasets to convert into seed data when a user has a domain but no documents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lightningrod-python-sdk:public-dataset-explorationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
User has a domain (e.g. "sports forecasting", "medical Q&A") but no documents. Explore public marketplaces for raw datasets that can become seeds.
User has a domain (e.g. "sports forecasting", "medical Q&A") but no documents. Explore public marketplaces for raw datasets that can become seeds.
Look for:
Avoid:
Download a small subset first (e.g. first 10 files, or head of CSV). Validate pipeline before full download.
npx claudepluginhub lightning-rod-labs/lightningrod-python-sdk --plugin lightningrod-python-sdkCreate, configure, and update datasets on Hugging Face Hub with SQL-based querying, streaming row updates, and multi-format template support.
Find and evaluate research datasets for any scientific question. Maps questions to study designs and searches 30+ repositories including GEO, UK Biobank, and NHANES.
Read-only Hugging Face Dataset Viewer API workflows: validate datasets, list splits, preview rows, paginate, search text, filter, get parquet URLs, size, and statistics.