Skip to content
Agentmart
Submit a tool

deep-research

Structured deep research workflow with human-in-the-loop control.

Skill by bighardperson

IndexedMIT★ 62
Write a review

Install

Works with Claude Code. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bighardperson-deep-research

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Structured deep research workflow with human-in-the-loop control. Use /research to generate research outline, /research-deep for parallel web search across items, /research-report to compile markdown reports. Supports academic research, benchmark research, technology selection, market analysis, and due diligence. Triggers: 'deep research', 'research topic', 'benchmark comparison', 'technology survey', 'market analysis'. Requires: WebSearch capability.

Use cases: documents, research, productivity

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/deep-research

Tools it pre-approves 6

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Write,
  • Glob,
  • WebSearch,
  • Task,
  • AskUserQuestion

What's inside

Skill name
deep-research
Description
Structured deep research workflow with human-in-the-loop control. Use /research to generate research outline, /research-deep for parallel web search across items, /research-report to compile markdown reports. Supports academic research, benchmark research, technology selection, market analysis, and due diligence. Triggers: 'deep research', 'research topic', 'benchmark comparison', 'technology survey', 'market analysis'. Requires: WebSearch capability.
License
MIT
Allowed tools
Read,, Write,, Glob,, WebSearch,, Task,, AskUserQuestion
Instructions
73 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • name: "deep-research" does not match folder "Deep Research"

Files (21)

  • SKILL.md
  • _skillhub_meta.json
  • web-search-agent.md · agents/
  • academic-papers.md · agents/web-search-modules/
  • chinese-tech.md · agents/web-search-modules/
  • general-web.md · agents/web-search-modules/
  • github-debug.md · agents/web-search-modules/
  • stackoverflow.md · agents/web-search-modules/
  • web-search-opencode.md · agents/
  • SKILL.md · research-add-fields/
  • SKILL.md · research-add-items/
  • SKILL.md · research-deep/
  • SKILL.md · research-en/research-add-fields/
  • SKILL.md · research-en/research-add-items/
  • SKILL.md · research-en/research-deep/
  • SKILL.md · research-en/research-report/
  • SKILL.md · research-en/research/
  • validate_json.py · research-en/research/
  • SKILL.md · research-report/
  • SKILL.md · research/
  • validate_json.py · research/

SKILL.md (first lines)

# Deep Research — 结构化深度调研工作流

基于 [Deep-Research-skills](https://github.com/Weizhena/Deep-Research-skills) 项目，提供人机协作的结构化调研能力。

## 核心命令

| 命令 | 说明 |
|------|------|
| `/research <topic>` | 初步调研，生成 outline.yaml + fields.yaml |
| `/research-deep` | 并行深度搜索，逐项收集数据 |
| `/research-report` | 汇总生成 Markdown 报告 |
| `/research-add-items` | 追加调研条目 |
| `/research-add-fields` | 追加调研字段 |

## 工作流程

```
/research "AI Agent 2025"
    ↓ 生成大纲（items + fields）
    ↓ 用户确认/修改
/research-deep
    ↓ 并行 web-search-agent 逐项搜索
    ↓ 结果写入 results/
/research-report
    ↓ 汇总为 report.md
```

## 适用场景

- **学术调研**：论文综述、Benchmark 对比
- **技术选型**：框架评估、工具对比
- **市场调研**：竞品分析、行业趋势
- **尽职调查**：公司研究、投资分析

## 目录结构

```
deep-research/
├── research/SKILL.md          # /research 命令（中文版）
├── research-deep/SKILL.md     # /research-deep 命令
├── research-report/SKILL.md   # /research-report 命令
├── research-add-items/SKILL.md
├── research-add-fields/SKILL.md
├── research-en/               # 英文版本
│   ├── research/SKILL.md
│   ├── research-deep/SKILL.md
│   ├── research-report/SKILL.md
│   ├── research-add-items/SKILL.md
│   └── research-add-fields/SKILL.md
└── agents/                    # 搜索代理
    ├── web-search-agent.md
    └── web-search-modules/    # 搜索策略模块
```

## 输出示例

```
{topic_slug}/
├── outline.yaml    # 调研条目 + 执行配置
├── fields.yaml     # 字段定义
├── results/        # 逐项搜索结果
│   ├── item_1.yaml
│   ├── item_2.yaml
│   └── ...
└── report.md       # 最终报告
```

## 致谢

- 作者：[Weizhena](https://github.com/Weizhena)
- 灵感：RhinoInsight — Improving Deep Research through Control Mechanisms for Model Behavior and Context

From bighardperson/computer-science-skills-collection, MIT.

More from bighardperson/computer-science-skills-collection

Signals

Stars
62
Forks
10
Open issues
0
Last commit (this folder)
Apr 26, 2026 (6 months ago)
Last release
Apr 26, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/bighardperson/computer-science-skills-collection
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from bighardperson

Cite this page

deep-research skill. Agent Mart. https://agentmart.dev/skills/bighardperson-deep-research (last updated 2026-10-24)