data-scientist · qdhenry — Claude Code subagent: what it does, how to install
data-scientist analyzes metrics, constructs advanced SQL workflows, and optimizes BigQuery queries to control data scanning costs.
no license ★ 1,357 updated 2026-03-01
.claude/agents/data-scientist.mdWhat data-scientist 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.
What it helps with
- 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 for the agent
- 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.
How to install data-scientist
Manually: put the files in place
.claude/agents/data-scientist.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/data-scientist.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/data-scientist.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about data-scientist
How do I install data-scientist in Claude Code?
Place the agent markdown file into your project at .claude/agents/data-scientist.md.
What does the data-scientist subagent do?
It handles SQL query development, optimizes cloud warehouse performance in BigQuery, and extracts business insights from raw data.
Does data-scientist require extra MCP servers?
Yes, the agent config includes tools from context7 for documentation lookup and sequential-thinking for structured analytical workflows.
Similar subagents
All subagents for Data and databases →data-scientist by other authors comes first.