ai4s-skills — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

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 ai4s-research · Claude Skill · ★ 167

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

🔒 Is ai4s-skills safe to install? View the security audit →

About ai4s-skills

Seven agent skills for AI-for-Science research — turn a research direction into literature surveys, runnable experiments, publication-grade papers, and integrity audits, with every citation, number, and figure traceable to its source. English · 中文 Contents 🧩 The skills 🔗 How they connect ✅ Authenticity 🔬 Example 📦 Install 🚀 Usage 🗂️ Repository layout 🛠️ Included tools 🤝 Contributing ⚖️ License 🙏 Acknowledgments The skills | [ai4s-agent](skills/a

agent-skillsai-agentai-for-scienceai-scientistai4sclaude-codeclaude-skillsliterature-reviewopen-scienceopencode

Quick Facts

Stars167
Forks17
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score73.9279372854071/100
Last Updated2026-07-28
Created2026-06-27
Platformsclaude-code, python
Est. Tokens~15k

Compatible Skills

These tools work well together with ai4s-skills for enhanced workflows:

  • Auto-Research-Skills — semantic(0.45)+complementary+rare_topics+same_lang+similar_pop+shared_platform (79%)
  • Light-skills — semantic(0.47)+complementary+rare_topics+same_lang+similar_pop+shared_platform (75%)
  • research-harness — semantic(0.36)+complementary+rare_topics+same_lang+similar_pop+shared_platform (72%)
  • AlterLab-Academic-Skills — semantic(0.35)+complementary+rare_topics+same_lang+similar_pop+shared_platform (71%)

ai4s-skills alternative? Top 6 similar tools

Looking for a ai4s-skills alternative? If you're comparing ai4s-skills with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Light-skills by Light0305 · ⭐ 620

    An AI workflow skill pack for research, competitions, and innovation projects.

  • Auto-Research-Skills by brycewang-stanford · ⭐ 151

    A curated hub of autonomous-research skills & agents — from idea to paper, on autopilot. | 自主科研技能与智能体精选库 —— 从灵

  • awesome-academic-research-skills by kael-odin · ⭐ 77

    面向中文用户的学术论文与科研 Agent Skill 每日排行榜 · 自动搜索、过滤并排名 GitHub 上的 Claude Code / Codex / OpenCode 科研 Skill 仓库

  • AlterLab-Academic-Skills by AlterLab-IEU · ⭐ 63

    239 evaluated academic Claude/agent skills across 17 research domains (bioinformatics, data science, clinical,

  • medsci-skills by Aperivue · ⭐ 287

    Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publ

  • AutoResearch-SibylSystem by Sibyl-Research-Team · ⭐ 277

    Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is ai4s-skills?

ai4s-skills is Open-source agent skills for AI for Science: topic exploration, literature survey, experiments, paper writing, and integrity audit — driven by any coding agent.. It is categorized as a Claude Skill with 167 GitHub stars.

What programming language is ai4s-skills written in?

ai4s-skills is primarily written in Python. It covers topics such as agent-skills, ai-agent, ai-for-science.

How do I install or use ai4s-skills?

You can find installation instructions and usage details in the ai4s-skills GitHub repository at github.com/ai4s-research/ai4s-skills. The project has 167 stars and 17 forks, indicating an active community.

What license does ai4s-skills use?

ai4s-skills is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to ai4s-skills?

The top alternatives to ai4s-skills on Agent Skills Hub include Light-skills, Auto-Research-Skills, awesome-academic-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 Claude Skill tools