Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Data Scientist (DuckDB/Polars)

Analyzes CSV, Parquet and JSON data at maximum speed by intelligently routing between DuckDB and Polars — never pandas.

Data & AnalyticsIntermediate★ 67,531⑂ 5,507AI score 9/10Last updated: Aug 9, 2026

What it does

  • Applies a decision tree to pick the faster engine per operation: Polars for filter/sort/transform/window functions, DuckDB for joins, heavy aggregations and complex SQL, hybrid pipelines for mixed work.
  • Uses Arrow zero-copy handoffs (.pl()) and lazy scans (scan_csv, scan_parquet) to keep memory low, plus streaming / out-of-core paths for datasets larger than RAM.
  • Runs everything through uv run --with ..., so no global installs; numpy and pyarrow are always included and pandas is deliberately excluded.
  • Ships a scripts/quick-query.py CLI for schema inspection, --describe stats, quick filters and ad-hoc SQL, and adds matplotlib charts for EDA, trends and distributions.

Who it's for

  • Analysts and engineers wrangling multi-million-row CSV/Parquet logs.
  • Anyone hitting out-of-memory errors or frustrated by slow pandas scripts.
  • SQL-comfortable users who want idiomatic Polars/DuckDB patterns to learn from.

Examples

  1. "What's in orders.parquet?" → schema, row count and summary statistics in one pass.
  2. "Show the last 30 days of revenue by category" → DuckDB aggregation plus a matplotlib trend line.
  3. "Join orders.csv with customers.csv, keep amounts over 100, then total by region" → hybrid pipeline: DuckDB join → Polars filter → DuckDB aggregate.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the packages/shared-skills/skills/data-scientist folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/data-scientist/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent && mkdir -p ~/.claude/skills && cp -r /tmp/oh-my-openagent/packages/shared-skills/skills/data-scientist ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (Git Bash or PowerShell on Windows).
  2. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r oh-my-openagent/packages/shared-skills/skills/data-scientist ~/.claude/skills/
  5. If uv is missing, run the bundled setup script: bash ~/.claude/skills/data-scientist/scripts/setup-uv.sh (native Windows: setup-uv.ps1).
  6. Confirm with uv --version.
  7. Restart Claude Code and try a prompt like "analyze this CSV file" — the skill activates automatically.
  8. Excel files aren't read directly, so export them to CSV or Parquet first.
View source on GitHub ↗License: NOASSERTION