Research Deep

by Weizhena

Research Deep is an AI Engineering skill for Claude Code, published by Weizhena in Deep-Research-skills.

2K stars161 forkson Weizhena/Deep-Research-skillsAdded 2026/08/18+1% in starsRepository updated 2026/05/07

View source on GitHub Download repo ZIP

claude-codeclaude-code-skillsdeep-research-agentgpt-skillsllm-agentopencodeopencode-skillsresearch

Install in seconds

Install Research Deep

Copy Research Deep 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/Weizhena/Deep-Research-skills/tree/master/skills/research-zh/research-deep ~/.claude/skills/research-deep

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/Weizhena/Deep-Research-skills.git

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

In this catalog

Source file: skills/research-zh/research-deep/SKILL.md in Weizhena/Deep-Research-skills
Installs to: ~/.claude/skills/research-deep
Collection: One of 13 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Research Deep does

Research Deep reads a research outline (outline.yaml) and launches independent background agents to investigate each item, writing structured Chinese JSON results with validation and checkpoint resumption. Use it to run multi-item deep research pipelines in Claude Code.

Research Deep is cataloged under AI Engineering on DirSkills. Research Deep comes from a repository tagged claude-code, claude-code-skills, deep-research-agent, gpt-skills and llm-agent.

Documentation

README

Excerpt

检查output_dir下已完成的JSON文件
跳过已完成的items

Step 3: 分批执行

按batch_size分批（完成一批需要得到用户同意才可进行下一批）
每个agent负责items_per_agent个项目
启动web-search-agent（后台并行，禁用task output）

参数获取：

{topic}: outline.yaml中的topic字段
{item_name}: item的name字段
{item_related_info}: item的完整yaml内容（name + category + description等）
{output_dir}: outline.yaml中execution.output_dir（默认./results）
{fields_path}: {topic}/fields.yaml的绝对路径
{output_path}: {output_dir}/{item_name_slug}.json的绝对路径（slugify处理item_name：空格替换为_，移除特殊字符）

硬约束：以下prompt必须严格复述，仅替换{xxx}中的变量，禁止改写结构或措辞。

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

Commands Research Deep provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/research-deep

Frequently asked about Research Deep

What else does Weizhena publish alongside Research Deep?
Research Deep is one of 13 skills that DirSkills catalogs from Weizhena/Deep-Research-skills, the repository it ships in. Its siblings there include Preliminary Research, Research and Research. Each one is a separate skill with its own page in this directory, installs the same way Research Deep does, and is maintained by Weizhena in that same repository. The rest of the collection is listed on the Weizhena/Deep-Research-skills page.
How does Research Deep compare to other AI Engineering skills?
Research Deep ranks #887 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. 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 Research Deep against them. Open each page to compare what they document and how they install.