Supervisor-Skills — security grade SAFE, quality 58/100

Security audit verdict: SAFE · quality 58/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by HKUSTDial · AI Tool · ★ 6.9k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Supervisor-Skills safe to install? View the security audit →

About Supervisor-Skills

Supervisor-Skills: 将博导十年科研经验,炼化为你的 AI 副导师。 English · 中文 📰 News - [2026-07-15] 🤝 团队与豆包达成合作,Supervisor-Skills 正式作为豆包·办公模式的核心科研技能完成部署,驱动「科研评估」与「学术创作」两大官方能力,将本项目沉淀的科研方法论带给亿级用户。 - [2026-07-10] 🚀 v2.1:新增 (证据门控的论文正文写作)、(忠于原意的语言润色)、(综述级文献调研)三个技能; 升级为正文输出;评估与评审技能引入学科范式路由。详见 CHANGELOG。 - [2026-07-03] 🎤 受邀在 2026 中国智能体大会 Skill 会场进行分享。 - [2026-07-03] 🧩 新增 技能:参考图一键重建为可编辑 Draw.io。 - [2026-05-21] ⭐ GitHub Star 突破 1,000(发布第 32 天)。 - [2026-04-19] 🎉 项目发布:七个锚点技能覆盖论文全生命周期,配套 handbook 系统课程。 为什么做这个项目? 大家好,我是骆昱宇,香港科技大学(广州)的助理教授。从自己读博到指导学生,我反复看到一个场景:许多才华横溢的研究生,在踏入科研大门时,常常被相似的困境所困扰: 理论与实践脱节:读了再多"科研指南",面对自己的课题时,依旧不知如何下笔。

ai-researchai-researcherawesomeawesome-listphd-researchresearch-skillsskillsvibe-research

Quick Facts

Stars6,852
Forks435
LanguagePython
CategoryAI Tool
Quality Score57.6930580502307/100
Open Issues2
Last Updated2026-09-05
Created2026-04-19
Platformspython
Est. Tokens~15k

Compatible Skills

These tools work well together with Supervisor-Skills for enhanced workflows:

Supervisor-Skills alternative? Top 6 similar tools

Looking for a Supervisor-Skills alternative? If you're comparing Supervisor-Skills with other ai tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • awesome-agent-skills by VoltAgent · ⭐ 33.9k

    A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude C

  • awesome-claude-skills by travisvn · ⭐ 14.6k

    A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particular

  • AI-Research-SKILLs by Orchestra-Research · ⭐ 11.5k

    Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills a

  • awesome-ai-in-finance by georgezouq · ⭐ 6.5k

    🔬 A curated list of awesome LLMs & deep learning strategies & tools in financial market.

  • awesome-agent-skills by heilcheng · ⭐ 6.1k

    Tutorials, Guides and Agent Skills Directories

  • awesome-generative-ai by filipecalegario · ⭐ 3.5k

    A curated list of Generative AI tools, works, models, and references

More AI Tool Tools

Explore other popular ai tool tools:

View all AI Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Supervisor-Skills?

Supervisor-Skills is 将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿,你的 AI 科研副导师。. It is categorized as a AI Tool with 6.9k GitHub stars.

What programming language is Supervisor-Skills written in?

Supervisor-Skills is primarily written in Python. It covers topics such as ai-research, ai-researcher, awesome.

How do I install or use Supervisor-Skills?

You can find installation instructions and usage details in the Supervisor-Skills GitHub repository at github.com/HKUSTDial/Supervisor-Skills. The project has 6.9k stars and 435 forks, indicating an active community.

What are the best alternatives to Supervisor-Skills?

The top alternatives to Supervisor-Skills on Agent Skills Hub include awesome-agent-skills, awesome-claude-skills, AI-Research-SKILLs. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse AI Tool tools