For exploratory data analysis, the strongest fits are the Python dataframe and visualization libraries and an in-process analytical SQL engine: pandas-style work via Polars 9 and Dask 3, SQL exploration with DuckDB 8, and plotting with Matplotlib 5 and SciPy for statistical routines 6. Hugging Face 2 is relevant if the data lives in its dataset hub.
- 1
- 2
- 3
Daskdask.orgverified and signed
A parallel Python computing library whose DataFrames use pandas under the hood, so existing pandas exploration code scales out 3.
+2 community tools built for it
for agents: pandas · pydata · numpy
- 4
- 5
SciPyscipy.orgwebsite read, tools not yet checked
A Python library of statistical and numerical algorithms that supports the statistical tests and summaries used in exploratory analysis 6.
+2 community tools built for it
Sources
- 2Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 3Dask | Scale the Python tools you lovedask.org · read 2026-10-29
- 5Matplotlib — Visualization with Pythonmatplotlib.org · read 2026-10-29
- 6SciPyscipy.org · read 2026-10-29
- 8An analytical SQL database management system – DuckDBduckdb.org · read 2026-10-29
- 9Polars — DataFrames for the new erapola.rs · read 2026-10-29
For agents: the 10 actions behind this answer
aws-data-analytics · aws-data-analytics verified and signed
Data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena.
huggingface-datasets · huggingface-datasets verified and signed
Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
pandas · dask verified and signed
playwright-explore-website · playwright-explore-website verified and signed
Website exploration for testing using Playwright MCP
kwargs · cycler verified and signed
· SciPy website read, tools not yet checked
Why SciPy? Fundamental algorithms. Broadly applicable. Foundational. Interoperable. Performant. Open source.
literature · firecrawl-py verified and signed
s3-explore · s3-explore verified and signed
Explore and query data on S3, Cloudflare R2, GCS, MinIO, or any S3-compatible storage. Use when the user mentions an s3://, r2://, gs://, or gcs:// URL, asks "what's in this bucket", wants to list remote files, preview remote Parquet/CSV/JSON, or query data on object storage without downloading it.
dataframe · polars verified and signed
chdb-sql · chdb-sql verified and signed
Use when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB — embedded ClickHouse SQL in Python with 1000+ function
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.