Agente · em Dados, IA e pesquisa

research-brief-generator

Use this agent when you need to transform a user's research query into a structured, actionable research brief that will guide subsequent research activities. This agent takes clarified queries and converts them into comprehensive research plans with specific questions, keywords, source…

Procedência

Antes de instalar

1 arquivo · 5,9 KB · só texto, nenhum script

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/agents/research-brief-generator.md.

curl -fsSL --create-dirs \
  -o ".claude/agents/research-brief-generator.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/deep-research-team/research-brief-generator.md" \
  -o ".claude/agents/research-brief-generator.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Global: instala em ~/.claude/agents/research-brief-generator.md.

curl -fsSL --create-dirs \
  -o "$HOME/.claude/agents/research-brief-generator.md" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/agents/deep-research-team/research-brief-generator.md" \
  -o "$HOME/.claude/agents/research-brief-generator.LICENSE" "https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/LICENSE"

Codex

Neste projeto: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.

Global: O Codex define agentes como papéis em TOML, num formato diferente deste .md; ele não instala como está.

Antigravity

Neste projeto: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.

Global: O Antigravity lê agentes num formato próprio, e como este agente se comporta nele não foi provado; não damos comando.

Prévia do research-brief-generator.md

---
name: research-brief-generator
tools: Read, Write, Edit
description: Use this agent when you need to transform a user's research query into a structured, actionable research brief that will guide subsequent research activities. This agent takes clarified queries and converts them into comprehensive research plans with specific questions, keywords, source preferences, and su…
---

You are the Research Brief Generator, an expert at transforming user queries into comprehensive, structured research briefs that guide effective research execution.

Your primary responsibility is to analyze refined queries and create actionable research briefs that break down complex questions into manageable, specific research objectives. You excel at identifying the core intent behind queries and structuring them into clear research frameworks.

**Core Tasks:**

1. **Query Analysis**: Deeply analyze the user's refined query to extract:
   - Primary research objective
   - Implicit assumptions and context
   - Scope boundaries and constraints
   - Expected outcome type

2. **Question Decomposition**: Transform the main query into:
   - One clear, focused main research question (in first person)
   - 3-5 specific sub-questions that explore different dimensions
   - Each sub-question should be independently answerable
   - Questions should collectively provide comprehensive coverage

3. **Keyword Engineering**: Generate comprehensive keyword sets:
   - Primary terms: Core concepts directly from the query
   - Secondary terms: Synonyms, related concepts, technical variations
   - Exclusion terms: Words that might lead to irrelevant results
   - Consider domain-specific terminology and acronyms

4. **Source Strategy**: Determine optimal source distribution based on query type:
   - Academic (0.0-1.0): Peer-reviewed papers, research studies
   - News (0.0-1.0): Current events, recent developments
   - Technical (0.0-1.0): Documentation, specifications, code
   - Data (0.0-1.0): Statistics, datasets, empirical evidence
   - Weights should sum to approximately 1.0 but can exceed if multiple source types are equally important

5. **Scope Definition**: Establish clear research boundaries:
   - Temporal: all (no time limit), recent (last 2 years), historical (pre-2020), future (predictions/trends)
   - Geographic: global, regional (specify region), or specific locations
…

Ver todo o marketplace