Weizhena/Deep-Research-skills: 20 Agent Skills

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

Repository	Weizhena/Deep-Research-skills
GitHub stars	2,316
Skills	20
Category	Research and science
License	MIT
Last updated	Aug 23, 2026
Install counts	Weizhena/Deep-Research-skills on skills.sh, Vercel's skills directory, which shows installs and security audits per skill

Install Weizhena/Deep-Research-skills

All skills, any agent	`npx skills add Weizhena/Deep-Research-skills`
One skill	`npx skills add Weizhena/Deep-Research-skills --skill research-add-fields`
Only for Claude Code	`npx skills add Weizhena/Deep-Research-skills -a claude-code`, or copy a skill folder to `~/.claude/skills/` (all projects) or `.claude/skills/` (one project)

npx skills is the open-source skills CLI; it asks which agents to install for. Skills can include scripts that your agent will run: read a skill before installing it, as you would any code.

Skills in Weizhena/Deep-Research-skills

Skill	What it does
research-add-fields	Add field definitions to existing research outline.
research-add-items	Add items (research objects) to existing research outline.
research-deep	Read research outline, launch independent agent for each item for deep research. Disable task output.
research-report	Summarize deep research results into markdown report, cover all fields, skip uncertain values.
research	Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.
research-add-fields	Add field definitions to existing research outline.
research-add-items	Add items (research objects) to existing research outline.
research-deep	Read research outline, launch independent agent for each item for deep research. Disable task output.
research-report	Summarize deep research results into markdown report, cover all fields, skip uncertain values.
research	Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.
research-add-fields	Add field definitions to existing research outline.
research-add-items	Add items (research objects) to existing research outline.
research-deep	Read research outline, launch independent agent for each item for deep research. Disable task output.
research-report	Summarize deep research results into markdown report, cover all fields, skip uncertain values.
research	Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.
research-add-fields	向现有调研outline补充字段定义。
research-add-items	向现有调研outline补充items（调研对象）。
research-deep	读取调研outline，为每个item启动独立agent进行深度调研。禁用task output。
research-report	将deep调研结果汇总为markdown报告，覆盖所有字段，跳过不确定值。
research	对目标话题进行初步调研，生成调研outline。用于学术调研、benchmark调研、技术选型等场景。

Names and descriptions come from each skill's SKILL.md and are written by the pack's authors.

More research and science skill packs

All research and science skills

#	Skill pack	Skills	GitHub stars	Updated
1	K-Dense-AI/scientific-agent-skills Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready…	177	48K	2026-10-05
2	Yuan1z0825/nature-skills 符合nature论文学术表达和科研绘图的Skill	22	46.6K	2026-10-08
3	Orchestra-Research/AI-Research-SKILLs Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code…	98	13.4K	2026-06-16
4	trailofbits/skills Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows	85	7,434	2026-10-07
5	wuyoscar/GPT-Image2-Skill GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing	2	5,671	2026-09-30
6	aipoch/open-science The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with e…	25	5,500	2026-10-08