Deep Research

Deep Research is a Data skill for Claude Code, published by nexu-io in nexu.

3.3K stars263 forkson nexu-io/nexuAdded 2026/08/17Repository updated 2026/04/26

ai-agentbyokclaudeclaude-codeclawbotcodexdiscordfeishullmopen-sourceopenclawopenclaw-desktopopenclaw-feishuopenclaw-slackopenclaw-wechatopenclaw-weixinseedance2skillsslack

Install in seconds

Install Deep Research

Copy Deep Research into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/nexu-io/nexu/tree/main/apps/desktop/static/bundled-skills/deep-research ~/.claude/skills/deep-research

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/nexu-io/nexu.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: apps/desktop/static/bundled-skills/deep-research/SKILL.md in nexu-io/nexu
Installs to: ~/.claude/skills/deep-research
Collection: One of 23 skills cataloged from this repository
Category: Data — 668 skills

What Deep Research does

Deep Research turns a vague topic into a high-quality report using an eight-step workflow: decompose questions, source tiered references, extract fact cards, build comparison frameworks, validate conclusions, and package deliverables. Use it for in-depth research or comparative analysis.

Deep Research is cataloged under Data on DirSkills. Deep Research comes from a repository tagged ai-agent, byok, claude, claude-code and clawbot.

Documentation

README

Excerpt

Deep Research（深度调研 8 步法）

将用户提出的模糊主题，通过系统化方法转化为高质量、可交付的调研报告。

核心理念

结论来自机制对比，不是「我感觉像」
先钉牢事实，再做推导
资料权威优先：L1 > L2 > L3 > L4
中间结果必须保存，便于回溯和复用

参考文档

文档	内容
`templates/intermediate-outputs.md`	中间产物格式模板
`templates/comparison-framework.md`	对比框架模板
`templates/fact-card.md`	事实卡片模板
`templates/report-structure.md`	报告结构模板

工作目录结构

~/Downloads/research/<topic>/
├── 00_问题拆解.md          # Step 0-1 产出
├── 01_资料来源.md          # Step 2 产出
├── 02_事实卡片.md          # Step 3 产出
├── 03_对比框架.md          # Step 4 产出
├── 04_推导过程.md          # Step 6 产出
├── 05.5_校验记录.md        # Step 6.5 产出（独立 Agent 校验）
├── 05_验证记录.md          # Step 7 产出
├── FINAL_调研报告.md       # Step 8 产出
└── raw/                    # 原始资料存档

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Deep Research

What else does nexu-io publish alongside Deep Research?
Deep Research is one of 23 skills that DirSkills catalogs from nexu-io/nexu, the repository it ships in. Its siblings there include ClawHub CLI, Coding Agent and Datadog Log Investigation. Each one is a separate skill with its own page in this directory, installs the same way Deep Research does, and is maintained by nexu-io in that same repository. The rest of the collection is listed on the nexu-io/nexu page.
How does Deep Research compare to other Data skills?
Deep Research ranks #217 by stars among the 668 Data skills in this catalog. The most-starred ones next to it are Benchmark Methodology, Jupyter Notebook and Solana. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Deep Research against them. Open each page to compare what they document and how they install.