# research-brief-generator

Turns a vague research query into a structured brief: one main question, sub-questions, keywords and success criteria.

- subagent · `type=agent` · Claude Code · 962 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/deep-research-team/research-brief-generator.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/research-brief-generator

## What it does

The subagent breaks a refined query into parts and returns a JSON research plan. Inside are a first-person main question, three to five sub-questions, keyword sets (primary, secondary, exclusion), source preferences with weights from 0.0 to 1.0, scope limits and success criteria.

Scope is set by time, geography and depth — `recent`, `global`, `detailed`, for instance. Source weights follow the query type: a technical topic leans on documentation, a news topic on fresh coverage. The agent's tools are plain: `Read`, `Write`, `Edit`.

It works on an already clarified query, so tighten the wording first. Feed it something raw and the brief comes back with junk sub-questions. That is a reason to rewrite the original phrasing rather than run the agent again.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent deep-research-team/research-brief-generator
```

2. **Manually: put the files in place**
- File: `.claude/agents/research-brief-generator.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-brief-generator.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-brief-generator.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/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/deep-research-team/research-brief-generator.md

## When to use it
- split a vague query into answerable sub-questions
- pick keywords and exclusion terms for a search
- weight source types for the task at hand
- set time and geographic bounds for research
- define criteria that show the answer is complete

## Example prompts
- build a research brief on the impact of AI on diagnostics
- break the quantum computing in drug discovery query into sub-questions
- make a brief with keywords and source weights for this topic

## Similar
- [motion-brief-writer](https://affpapa.org/en/nevibecode/skills/motion-brief-writer.md) — skill · 1500 installs
- [firecrawl-deep-research](https://affpapa.org/en/nevibecode/skills/firecrawl-deep-research.md) — skill · 35400 installs
- [firecrawl-research-index](https://affpapa.org/en/nevibecode/skills/firecrawl-research-index.md) — skill · 24400 installs
- [tavily-research](https://affpapa.org/en/nevibecode/skills/tavily-research.md) — skill · 22000 installs
- [parallel-deep-research](https://affpapa.org/en/nevibecode/skills/parallel-deep-research.md) — skill · 15600 installs
- [deep-research](https://affpapa.org/en/nevibecode/skills/199-biotechnologies-deep-research.md) — skill · 10200 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 238 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