Repository
Weizhena/Deep-Research-skills agent skills
- skills
- 10
- GitHub stars
- 2.3k
GitHub description: “Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control”
- Stars
- 2,322 (188 forks)
- Licence
- MIT
- Last push
- Aug 2026
- Created
- Dec 2025
- claude-code
- claude-code-skills
- deep-research-agent
- llm-agent
- research
- gpt-skills
- opencode
- opencode-skills
Install all skills
npx skills add Weizhena/Deep-Research-skillsAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in Weizhena/Deep-Research-skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.Research Conduct preliminary research on a topic and generate research outline. | Weizhena/ | 2.3k | 2 repos | ~1.1k | Automated safety check: Pass | MIT | 1 mo ago |
| 2 | Read research outline, launch independent agent for each item for deep research. | Weizhena/ | 2.3k | 2 repos | ~850 | Automated safety check: Notes | MIT | 1 mo ago |
| 3 | Summarize deep research results into markdown report, cover all fields, skip uncertain values. | Weizhena/ | 2.3k | 2 repos | ~963 | Automated safety check: Notes | MIT | 1 mo ago |
| 4 | 4.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. An agent skill from Weizhena/Deep-Research-skills. | Weizhena/ | 2.3k | 1 repo | ~603 | Automated safety check: Pass | MIT | 1 mo ago |
| 5 | 读取调研outline，为每个item启动独立agent进行深度调研。禁用task output. An agent skill from Weizhena/Deep-Research-skills. | Weizhena/ | 2.3k | 1 repo | ~521 | Automated safety check: Notes | MIT | 1 mo ago |
| 6 | Add field definitions to existing research outline. An agent skill from Weizhena/Deep-Research-skills. | Weizhena/ | 2.3k | 2 repos | ~238 | Automated safety check: Notes | MIT | 1 mo ago |
| 7 | Add items (research objects) to existing research outline. An agent skill from Weizhena/Deep-Research-skills. | Weizhena/ | 2.3k | 2 repos | ~204 | Automated safety check: Notes | MIT | 1 mo ago |
| 8 | 将deep调研结果汇总为markdown报告，覆盖所有字段，跳过不确定值。 | Weizhena/ | 2.3k | 1 repo | ~568 | Automated safety check: Notes | MIT | 1 mo ago |
| 9 | 向现有调研outline补充字段定义。 | Weizhena/ | 2.3k | 1 repo | ~144 | Automated safety check: Notes | MIT | 1 mo ago |
| 10 | 向现有调研outline补充items（调研对象）。 | Weizhena/ | 2.3k | 1 repo | ~132 | Automated safety check: Notes | MIT | 1 mo ago |
Questions, answered from the data.
What is the best skill in Weizhena/Deep-Research-skills?
Research from Weizhena/Deep-Research-skills ranks first of the 10 skills in Weizhena/Deep-Research-skills listed here, with the highest score: its repository has 2.3k GitHub stars, 2 other GitHub owners carry a copy, its SKILL.md loads about 1.1k tokens and it passes the automated safety check with no findings. Next come Research Deep and Research Report.
Are the skills in Weizhena/Deep-Research-skills official?
None yet. All 10 skills in Weizhena/Deep-Research-skills listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from Weizhena/Deep-Research-skills?
Run npx skills add Weizhena/Deep-Research-skills in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.