deep-research

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Gemini Deep Research Skill

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

运行可自主规划、搜索、阅读并将信息整合为全面报告的研究任务。

Requirements

要求

Python 3.8+
httpx:
```
pip install -r requirements.txt
```
GEMINI_API_KEY environment variable

Python 3.8+
httpx：执行
```
pip install -r requirements.txt
```
安装
需配置GEMINI_API_KEY环境变量

Setup

配置步骤

Get a Gemini API key from Google AI Studio
Set the environment variable:
bash
```
export GEMINI_API_KEY=your-api-key-here
```
Or create a
```
.env
```
file in the skill directory.

从Google AI Studio获取Gemini API密钥
设置环境变量：
bash
```
export GEMINI_API_KEY=your-api-key-here
```
或在技能目录下创建
```
.env
```
文件。

Usage

使用方法

Start a research task

启动研究任务

bash

python3 scripts/research.py --query "Research the history of Kubernetes"

bash

python3 scripts/research.py --query "Research the history of Kubernetes"

With structured output format

指定结构化输出格式

bash

python3 scripts/research.py --query "Compare Python web frameworks" \
  --format "1. Executive Summary\n2. Comparison Table\n3. Recommendations"

bash

python3 scripts/research.py --query "Compare Python web frameworks" \
  --format "1. Executive Summary\n2. Comparison Table\n3. Recommendations"

Stream progress in real-time

实时流式查看进度

bash

python3 scripts/research.py --query "Analyze EV battery market" --stream

bash

python3 scripts/research.py --query "Analyze EV battery market" --stream

Start without waiting

启动任务后无需等待

bash

python3 scripts/research.py --query "Research topic" --no-wait

bash

python3 scripts/research.py --query "Research topic" --no-wait

Check status of running research

查看运行中任务的状态

bash

python3 scripts/research.py --status <interaction_id>

bash

python3 scripts/research.py --status <interaction_id>

Wait for completion

等待任务完成

bash

python3 scripts/research.py --wait <interaction_id>

bash

python3 scripts/research.py --wait <interaction_id>

Continue from previous research

基于已有研究继续跟进

bash

python3 scripts/research.py --query "Elaborate on point 2" --continue <interaction_id>

bash

python3 scripts/research.py --query "Elaborate on point 2" --continue <interaction_id>

List recent research

列出近期研究任务

bash

python3 scripts/research.py --list

bash

python3 scripts/research.py --list

Output Formats

输出格式

Default: Human-readable markdown report
JSON (
```
--json
```
): Structured data for programmatic use
Raw (
```
--raw
```
): Unprocessed API response

默认格式：易读的Markdown报告
JSON（
```
--json
```
参数）：适用于程序化调用的结构化数据
原始格式（
```
--raw
```
参数）：未处理的API响应

Cost & Time

成本与耗时

Metric	Value
Time	2-10 minutes per task
Cost	$2-5 per task (varies by complexity)
Token usage	~250k-900k input, ~60k-80k output

指标	数值
耗时	每任务2-10分钟
成本	每任务2-5美元（随复杂度变化）
Token使用量	输入约25万-90万Token，输出约6万-8万Token

Best Use Cases

最佳适用场景

Market analysis and competitive landscaping
Technical literature reviews
Due diligence research
Historical research and timelines
Comparative analysis (frameworks, products, technologies)

市场分析与竞品格局分析
技术文献综述
尽职调查研究
历史研究与时间线梳理
对比分析（框架、产品、技术）

Workflow

工作流程

User requests research → Run
```
--query "..."
```
Inform user of estimated time (2-10 minutes)
Monitor with
```
--stream
```
or poll with
```
--status
```
Return formatted results
Use
```
--continue
```
for follow-up questions

用户发起研究请求 → 执行
```
--query "..."
```
命令
告知用户预估耗时（2-10分钟）
使用
```
--stream
```
参数实时监控，或用
```
--status
```
参数轮询状态
返回格式化结果
使用
```
--continue
```
参数跟进后续问题

Exit Codes

退出码

0: Success
1: Error (API error, config issue, timeout)
130: Cancelled by user (Ctrl+C)

0：执行成功
1：执行错误（API错误、配置问题、超时）
130：用户取消（Ctrl+C）