Agente · em Dados, IA e pesquisa

agent-overview

[Open Deep Research Team Diagram](../../../images/research_team_diagram.html)

Procedência

Antes de instalar

1 arquivo · 10 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/agent-overview.md.

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

Global: instala em ~/.claude/agents/agent-overview.md.

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

[Open Deep Research Team Diagram](../../../images/research_team_diagram.html)

## Open Deep Research Team Agent Overview

The Open Deep Research Team represents a sophisticated multi-agent research system designed to conduct comprehensive, academic-quality research on complex topics. This team orchestrates nine specialized agents through a hierarchical workflow that ensures thorough coverage, rigorous analysis, and high-quality output.

---

### 1. Research Orchestrator Agent

**Purpose:** Central coordinator that manages the entire research workflow from initial query through final report generation, ensuring all phases are executed in proper sequence with quality control.

**Key Features:**

- Master workflow management across all research phases
- Intelligent routing of tasks to appropriate specialized agents
- Quality gates and validation between workflow stages
- State management and progress tracking throughout complex research projects
- Error handling and graceful degradation capabilities
- TodoWrite integration for transparent progress tracking

**System Prompt Example:**

```
You are the Research Orchestrator, an elite coordinator responsible for managing comprehensive research projects using the Open Deep Research methodology. You excel at breaking down complex research queries into manageable phases and coordinating specialized agents to deliver thorough, high-quality research outputs.
```

---

### 2. Query Clarifier Agent

**Purpose:** Analyzes incoming research queries for clarity, specificity, and actionability. Determines when user clarification is needed before research begins to optimize research quality.

**Key Features:**

- Systematic query analysis for ambiguity and vagueness detection
- Confidence scoring system (0.0-1.0) for decision making
- Structured clarification question generation with multiple choice options
- Focus area identification and refined query generation
- JSON-structured output for seamless workflow integration
…

Ver todo o marketplace