# research_analyst

The research_analyst Claude Code subagent turns a research question and supplied sources into a structured report. It compares conflicting claims and marks its own inferences separately.

- 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/research_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-research-analyst

## What it does

The subagent produces a Markdown report from a research question and its supporting material. It groups findings by claim or theme, links claims to source identifiers from the context, and describes disagreements, uncertainty, and limits in the evidence. The report also sets out the research scope, conclusions, and proportionate recommendations.

It must label its inferences and avoid inventing citations, quotations, dates, or access to sources. Lower-quality and secondary evidence receives less weight. The inputs are a research question with its decision context and desired depth, plus material such as retrieved pages, papers, reports, notes, or structured evidence.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/research_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/research_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/research_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/research_analyst.md

## When to use it
- turn source material into a report for a research question
- compare conflicting claims across sources
- link findings to source identifiers
- separate source statements from the agent’s inferences

## Example prompts
- Write a research report on how X affects Y using the supplied material.
- Compare the claims in these papers and point out where they disagree.
- Summarize the evidence and label your own inferences.

## Similar
- [deep-research](https://affpapa.org/en/nevibecode/skills/petekp-deep-research.md) — skill · 196 installs
- [Research Report Generator — Multi-Source Analysis](https://affpapa.org/en/nevibecode/mcp/research-report-generator-multi-source-analysis.md) — MCP server · 5001 installs
- [research-methodology](https://affpapa.org/en/nevibecode/skills/research-methodology.md) — skill · ★ 1125 repo stars
- [tavily-research](https://affpapa.org/en/nevibecode/skills/tavily-ai-tavily-research.md) — skill · 25100 installs
- [deep-reading-analyst](https://affpapa.org/en/nevibecode/skills/deep-reading-analyst.md) — skill · ★ 286 repo stars
- [research-analyst](https://affpapa.org/en/nevibecode/skills/research-analyst.md) — skill · 206 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
