# data_analyst

data_analyst — a subagent for Claude Code turns structured data and query results into reproducible findings. It checks units, missing values, and metric denominators before drawing conclusions.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 776 repo stars
- Author: AgenticOrgLab
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/AgenticOrgLab/ExecOrchestra/tree/HEAD/execorchestra/Pool/resources/agents/data_analyst.md
- Updated: 2026-11-12
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/agenticorglab-data-analyst

## What it does

The subagent analyzes tables, CSV or JSON content, and query results to produce findings that can be checked again. It takes an analysis question and data context, such as a schema, definitions, and collection limits.

Its response contains a concise conclusion, metrics with units and definitions, evidence-based observations, limitations, and follow-up analysis steps. It gives formulas and denominators for derived metrics, and separates correlation from causation. Missing observations are not silently filled in.

The result is one valid JSON object with no Markdown fences. The Claude Code agent file goes at `.claude/agents/data_analyst.md`.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/data_analyst.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_analyst.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_analyst.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/AgenticOrgLab/ExecOrchestra/tree/HEAD/execorchestra/Pool/resources/agents/data_analyst.md

## When to use it
- check units and missing values in a table
- calculate metrics with their formulas and denominators
- separate correlation from causal claims
- record data limitations and uncertainty

## Example prompts
- Analyze these query results and describe how conversion changed.
- Compare `sales.csv` by region and return metrics with their formulas.
- Check these data for missing values and limitations, then return findings as JSON.

## Similar
- [data-analyst](https://affpapa.org/en/nevibecode/agents/data-analyst.md) — subagent · 837 installs
- [Yahoo Finance MCP — Equity Fundamentals & Analyst Data](https://affpapa.org/en/nevibecode/mcp/yahoo-finance-mcp-equity-fundamentals-analyst-data.md) — MCP server · 3787 installs
- [business-analyst](https://affpapa.org/en/nevibecode/agents/voltagent-community-business-analyst.md) — subagent · 3855 installs
- [competitive-intelligence-analyst](https://affpapa.org/en/nevibecode/agents/competitive-intelligence-analyst.md) — subagent · 1561 installs
- [quant-analyst](https://affpapa.org/en/nevibecode/agents/quant-analyst.md) — subagent · 1366 installs
- [marketing-attribution-analyst](https://affpapa.org/en/nevibecode/agents/marketing-attribution-analyst.md) — subagent · 1115 installs

From the same set: [agenticorglab/execorchestra](https://affpapa.org/en/nevibecode/by/agenticorglab/execorchestra.md) — 24 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
