Deep Research Agent logo

Deep Research Agent

CommunityPopular
ZHangZHengEric
deep-research-agent

深度研究技能,用于系统性调研与分析。适用于研究、调研、竞品分析、市场分析或结构化信息收集等需求。

Overview

PublisherZHangZHengEric
RepositorySage
Skill namedeep-research-agent
Stars
1.2K
Forks
113
Bundled files
27
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 27 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ZHangZHengEric on GitHub. Read the source before you install it.

Installation

Install the Deep Research Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ZHangZHengEric/Sage/tree/main/app/skills/deep-research-agent
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ZHangZHengEric/Sage.git /tmp/Sage
mkdir -p .claude/skills
cp -r /tmp/Sage/app/skills/deep-research-agent .claude/skills/deep-research-agent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Deep Research Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Deep Research Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Deep Research Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

深度研究 Agent

以增量方式开展系统化研究并输出。

工作流

1. 大纲 → 2. 初始化 → 3. 研究 → 4. 更新 → 5. JSON → 6. HTML

1. 创建大纲(必须)

研究前先向用户展示大纲:

  • 研究目标
  • 需要回答的关键问题
  • 需要探索的信息来源
  • 预期交付物

获得用户确认后再继续。

2. 初始化研究环境

运行初始化脚本,使用绝对路径创建工作目录:

bash
python skills/deep-research-agent/scripts/init_research.py <absolute_template_path> <absolute_project_path>

用法: python init_research.py <absolute_template_path> <absolute_project_path>

模板(研究方向模板):

不同研究类型使用对应的 Markdown 模板:

模板统一放在 deep-research-agent/templates 目录下,初始化时只需选择对应模板文件路径。

创建内容:

  • report.md - 复制选定模板(位于项目目录)
  • materials/ - 原始资料与笔记目录(包含 raw/ 与 notes/)

重要: 不要用 mkdir 或 Write tool 手动创建目录,必须通过初始化脚本生成结构。

3. 执行研究(增量)

搜索并立即保存:

每条有价值的信息都要 先保存到 materials 目录:

python
file_write(
    file_path="{project_path}/materials/raw/source_001.md",
    content="""## 来源: [标题]
- URL: [链接]
- 时间: [日期]

### 关键信息
- [要点1]
- [要点2]

### 数据
- [数据点]

### 引用原文
> [原文摘录]
"""
)

研究策略:

  • 按章节/小节搜索
  • 立即保存来源到 materials/
  • 标注与报告章节的关联

4. 按章节更新报告

当某一节内容充足时,立即更新报告:

python
file_update(
    file_path="{project_path}/report.md",
    operations=[{
        "update_mode": "search_replace",
        "search_pattern": "## 1. 研究背景与目标\n\n{研究背景说明}",
        "replacement": """## 1. 研究背景与目标

### 1.1 研究背景

[基于materials/中的资料,撰写详细背景]

[包含数据支撑、引用来源]

### 1.2 研究目标

[具体目标]

### 1.3 研究范围

[范围界定]"""
    }]
)

更新规则:

  • 某一节有 3+ 可靠来源即可撰写
  • 必须完全替换:更新时务必彻底替换模板中的占位符内容,不要保留任何示例文字(如 [在此填写...]、{占位符} 等)
  • 逐段检查:替换后通读该节内容,确保没有残留的模板示例文字

5. 质量检查与内容验证

在生成最终输出前,必须执行以下检查:

5.1 清理模板内容
  • 检查 report.md 中是否还有未填充的模板占位符(如 {研究背景说明}、{在此填写...}、[请填写...] 等)
  • 全部删除或替换为实际内容,禁止保留任何占位符
5.2 章节完整性检查
  • 确保所有章节都已用实际研究内容替换,没有空章节
  • 检查是否有仅包含标题而无实质内容的章节
  • 如某些章节确实无相关内容,直接删除该章节标题,不要留空
5.3 内容合理性验证
  • 通读全文:从头到尾阅读报告,确保逻辑连贯
  • 检查一致性:确保数据、结论在各章节中保持一致
  • 验证引用:确保引用的来源与实际收集的 materials 对应
  • 删除示例文字:确保没有残留的模板示例文字(如 "[基于materials/中的资料...]" 等指导语)
5.4 最终确认清单
  • 无模板占位符残留
  • 无空章节
  • 无示例/指导文字残留
  • 数据来源已标注
  • 逻辑连贯,结论合理

检查通过后,生成包含结构化数据的 research_data.json:

json
{
  "topic": "...",
  "created_at": "...",
  "outline": {...},
  "materials_count": 15,
  "sections_completed": ["1.1", "1.2", "3.1"],
  "key_findings": [...],
  "sources": [...]
}

输出结构

{user_specified_project_path}/
├── report.md               # 主报告(增量更新)
├── report.html             # 阅读友好的 HTML 版本
├── research_data.json      # 结构化数据
└── materials/
    ├── raw/                # 原始来源
    ├── notes/              # 按章节整理的笔记
    └── ...

关键原则

  1. 先保存:所有来源立即写入 materials/
  2. 尽早更新:内容成熟就写入报告
  3. 按章节推进:不要等全部研究完成
  4. 引用来源:报告内引用 materials/ 文件
  5. 结构一致:research_data.json 与报告保持一致
  6. HTML 输出:最终必须将 report.md 转为 HTML,使用 scripts/md_to_html.py 生成。
    • 命令:python skills/deep-research-agent/scripts/md_to_html.py /absolute/path/report.md
    • 默认输出为 report.html,可用 --out 指定输出路径。

模板选择指南

模板位置:deep-research-agent/templates。无需在此列出具体模板名称。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Deep Research Agent AI skill do?

深度研究技能,用于系统性调研与分析。适用于研究、调研、竞品分析、市场分析或结构化信息收集等需求。

Why use Deep Research Agent on TypingMind?

Because you install it once and use it with any model. Deep Research Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Deep Research Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZHangZHengEric/Sage/tree/main/app/skills/deep-research-agent. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Deep Research Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Deep Research Agent?

As many as you like. As long as a model supports skills, you can use Deep Research Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Deep Research Agent AI skill free?

Yes. It is published on GitHub by ZHangZHengEric under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇