# data-scientist

data-scientist analyzes metrics, constructs advanced SQL workflows, and optimizes BigQuery queries to control data scanning costs.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 1357 repo stars
- Author: qdhenry
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/data-ai/data-scientist.md
- Updated: 2026-03-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/qdhenry-data-scientist

## What it does

This subagent acts as an analytical partner for data exploration. Before generating queries, it asks clarifying questions about vague metrics or time ranges so you avoid wasting cloud compute. When working with BigQuery, it targets table partitioning, window functions, and query plan efficiency.

Under the hood, the agent runs on the `sonnet` model and uses several MCP tools. It relies on `sequential-thinking` for structured multi-step investigations and `context7` to pull current documentation on statistical libraries. If table maintenance or bulk operations are required, it can call the `bq` CLI directly.

Specialized deep-reasoning steps will fail silently if the required `context7` and `sequential-thinking` MCP servers are missing from your setup.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/data-scientist.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/data-scientist.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/data-scientist.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/data-ai/data-scientist.md

## When to use it
- tune slow BigQuery SQL statements to reduce processing expenses
- clarify ambiguous tracking metrics before running heavy database queries
- build multi-step data pipelines and design ETL table schemas
- transform raw analytical aggregates into actionable business takeaways

## Example prompts
- Review this BigQuery query and optimize partitioning to cut down scan expenses.
- Compare sales cohorts across regions and summarize retention patterns.
- Outline an ETL pipeline to aggregate daily user sessions from raw event tables.

## Similar
- [Data Scientist](https://affpapa.org/en/nevibecode/prompts/data-scientist.md) — prompt · ★ 178201 repo stars
- [bigquery-data-analytics](https://affpapa.org/en/nevibecode/plugins/bigquery-data-analytics.md) — plugin · ★ 53 repo stars
- [data-analytics](https://affpapa.org/en/nevibecode/plugins/data-analytics.md) — plugin · ★ 8052 repo stars
- [data-science-expert](https://affpapa.org/en/nevibecode/skills/data-science-expert.md) — skill · 594 installs
- [data-science](https://affpapa.org/en/nevibecode/skills/data-science.md) — skill · 189 installs
- [data-warehouse-experimentation](https://affpapa.org/en/nevibecode/skills/data-warehouse-experimentation.md) — skill · 283 installs

## Other versions with the same name
- [data-scientist · voltagent](https://affpapa.org/en/nevibecode/agents/voltagent-community-data-scientist.md) — 3342 installs
- [data-scientist · wshobson](https://affpapa.org/en/nevibecode/agents/data-scientist.md) — 3342 installs
- [data-scientist · voltagent](https://affpapa.org/en/nevibecode/agents/voltagent-data-scientist.md) — ★ 6505 repo stars

From the same set: [qdhenry/claude-command-suite](https://affpapa.org/en/nevibecode/by/qdhenry/claude-command-suite.md) — 112 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
