Skill collection
haibarazz/awesome-codex-research agent skills
- skills
- 9
- GitHub stars
- 100
- Stars
- 100 (3 forks)
- Licence
- No licence
- Last push
- Sep 2026
- Created
- Sep 2026
Install all skills
npx skills add haibarazz/awesome-codex-researchAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in haibarazz/awesome-codex-research, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Run rigorous end-to-end autonomous ML and AI research after a user provides a dataset, target, and research budget. | haibarazz/ | 100 | — | ~2.2k | Automated safety check: Pass | No licence | 16 days ago |
| 2 | Guide a complete baseline-first ML or computational data-science method-innovation project, from workspace and direction discovery through finding and running common and recent baselines, diagnosing… | haibarazz/ | 100 | — | ~715 | Automated safety check: Pass | No licence | 16 days ago |
| 3 | A skill your agent uses when the host coding agent should control an AutoDL or SSH server from the local machine, run remote commands, and explicitly upload or download selected files. | haibarazz/ | 100 | — | ~2.7k | Automated safety check: Pass | No licence | 16 days ago |
| 4 | A skill your agent uses when AutoDL Remote should run or monitor long remote jobs through tmux panes. | haibarazz/ | 100 | — | ~666 | Automated safety check: Pass | No licence | 16 days ago |
| 5 | 5.Auto Exp Plan, execute, monitor, verify, compare, and document reproducible machine-learning experiments. | haibarazz/ | 100 | — | ~1.4k | Automated safety check: Pass | No licence | 16 days ago |
| 6 | 面向信息系统计算设计科学（CDS）研究，根据用户的数据、研究情境与研究问题，分别识别问题／理论视角和技术／算法两条文献对话线，检索并核验全文，制作可追溯的文献对话地图，最终澄清研究的最近邻、理论祖先、方法缺口与可辩护定位。适用于选题定位、相关工作规划、方法定位和后续综述；核心不是代写文献综述。 | haibarazz/ | 100 | — | ~558 | Automated safety check: Pass | No licence | 16 days ago |
| 7 | 结合论文原文拆解审稿意见为最小可回应原子问题，规划补实验与回复构思两条工作线，归组共同关切，并输出带忠实中文翻译注释、每条 comment 一份建议逻辑和原子点英文小标题的可编译 LaTeX 回复骨架。用于返修规划、review decomposition、atomic concerns、rebuttal strategy 和回复信模板生成；完整回复正文留待作者后续撰写。 | haibarazz/ | 100 | — | ~1.1k | Automated safety check: Warn | No licence | 16 days ago |
| 8 | 在实现、实验、写作或规划之前进行轻量级意图对齐。当用户明确要求对齐意图、复述需求、确认理解时使用；当请求存在歧义、两种合理的实现方式会产生明显不同结果时，也应在开始任何中小型实现/实验/写作任务前主动使用。对于意图完全清晰的一步式小请求不要使用，也不要进入完整的 Plan Mode。 | haibarazz/ | 100 | — | ~593 | Automated safety check: Pass | No licence | 16 days ago |
| 9 | 润色既有英文学术论文或用户直接粘贴的英文论文段落，按授权范围处理理论边界、论证结构、参考文献真实性、英文表达、LaTeX 安全和 AI 写作痕迹。用于修改、润色、重写或审计已有内容；不用于从零撰写论文。 | haibarazz/ | 100 | — | ~1.2k | Automated safety check: Pass | No licence | 16 days ago |
Questions, answered from the data.
What is the best skill in haibarazz/awesome-codex-research?
Autoresearch from haibarazz/awesome-codex-research ranks first of the 9 skills in haibarazz/awesome-codex-research listed here, with the highest score: its repository has 100 GitHub stars, its SKILL.md loads about 2.2k tokens and it passes the automated safety check with no findings. Next come Cds Method Innovation and Autodl Remote.
Are the skills in haibarazz/awesome-codex-research official?
None yet. All 9 skills in haibarazz/awesome-codex-research 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 haibarazz/awesome-codex-research?
Run npx skills add haibarazz/awesome-codex-research 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.