Back to Details

deep-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Deep Research

深度研究

Use this skill to conduct deep, autonomous research tasks that require planning, searching, reading, and synthesizing information.
This skill uses the Gemini Deep Research Agent (
deep-research-pro-preview-12-2025
) via the Interactions API.
使用该Skill开展需要规划、搜索、阅读和信息整合的深度自主研究任务。
本Skill通过Interactions API调用Gemini Deep Research Agent（
deep-research-pro-preview-12-2025
）。

Prerequisites

前提条件

  • GOOGLE_API_KEY
    : Required for accessing the Interactions API (currently in Preview via AI Studio).
  • google-genai
    SDK v0.3.0+
  • GOOGLE_API_KEY
    ：访问Interactions API的必填项（目前可通过AI Studio预览使用）。
  • google-genai
    SDK v0.3.0及以上版本

Usage

使用方法

Basic Research

基础研究

Start a research task and stream the results to the console.
bash
uv run skills/deep-research/scripts/research.py "Research the history of RISC-V architecture."
启动一项研究任务并将结果流式输出到控制台。
bash
uv run skills/deep-research/scripts/research.py "Research the history of RISC-V architecture."

Research with Context (Files or Directories)

带上下文的研究（文件或目录）

Provide local files (PDFs, text) or entire directories for the agent to read and incorporate into its research.
Direct Upload (Best for specific docs):
bash
undefined
提供本地文件（PDF、文本）或整个目录，供Agent读取并整合到研究中。
直接上传（适合特定文档）：
bash
undefined

Single file

单个文件

uv run skills/deep-research/scripts/research.py "Analyze this report" --file report.pdf
uv run skills/deep-research/scripts/research.py "Analyze this report" --file report.pdf

Entire directory

整个目录

uv run skills/deep-research/scripts/research.py "Summarize these meeting notes" --file ./notes/

**File Search Store (Best for large corpora):**
Use `--use-file-store` to index files into a searchable store (RAG) instead of uploading them into the context window.

```bash
uv run skills/deep-research/scripts/research.py "Find trends in these 1000 PDFs" --file ./large_corpus/ --use-file-store
uv run skills/deep-research/scripts/research.py "Summarize these meeting notes" --file ./notes/

**文件搜索存储（适合大型语料库）：**
使用`--use-file-store`将文件索引到可搜索存储（RAG）中，而非上传到上下文窗口。

```bash
uv run skills/deep-research/scripts/research.py "Find trends in these 1000 PDFs" --file ./large_corpus/ --use-file-store

Saving the Report

保存报告

Save the final Markdown report to a file.
bash
uv run skills/deep-research/scripts/research.py "Competitive landscape of EV batteries" --output report.md
将最终的Markdown报告保存到文件。
bash
uv run skills/deep-research/scripts/research.py "Competitive landscape of EV batteries" --output report.md

Continuing Research (Follow-up)

延续研究（跟进）

Ask follow-up questions to an existing research session using the 
Interaction ID
(displayed at the start of the previous run).
bash
uv run skills/deep-research/scripts/research.py "Elaborate on the second point about lithium supply." --follow-up "INTERACTION_ID_HERE"
使用
Interaction ID
（上一次运行开始时显示的ID）对现有研究会话提出跟进问题。
bash
uv run skills/deep-research/scripts/research.py "Elaborate on the second point about lithium supply." --follow-up "INTERACTION_ID_HERE"

References

参考资料

  • Online Documentation
  • 在线文档

How it Works

工作原理

  1. Planning: The agent breaks down your prompt into steps.
  2. Execution: It autonomously searches the web and reads your provided files.
  3. Resilience: The script automatically reconnects if the long-running stream drops.
  4. Synthesis: It produces a comprehensive, cited report.
  1. 规划：Agent将你的提示拆解为多个步骤。
  2. 执行：自主进行网页搜索并读取你提供的文件。
  3. 弹性机制：如果长时间运行的流中断，脚本会自动重新连接。
  4. 整合：生成一份全面且带有引用的报告。