awesome-agent-skills — security grade SAFE, quality 64/100

Security audit verdict: SAFE · quality 64/100

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 libukai · Codex Skill · ★ 5.0k

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

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

About awesome-agent-skills

简体中文 日本語 本项目致力于遵循少而精的原则,收集和分享最优质的 Skills 教程、案例和实践,帮助更多人轻松迈出搭建 Agent 的第一步。 欢迎关注我的 𝕏 账号 @李不凯正在研究 ,以及 💬 微信公众号 @李不凯正在研究 即时获取 Skills 的最新资源和实战教程! 基本介绍 Skills (智能体技能)是一种轻量级的开放标准,用于通过专业知识和工作流程来扩展 AI Agent 的能力。 当你需要执行可重复的工作流程时,你无需在每次和 AI 的对话中重复解释自己的流程、知识和偏好,Skills 让你只需教导一次,便能让 AI 学会相关的技能。 标准结构 根据标准定义,每个 Skill 都是一个规范化命名的文件夹,其中集合了指令、脚本和资源,AI 通过在上下文中渐进式导入这些内容来理解和学习相关技能。 markdown my-skill/ ├── SKILL.md # 必需:说明和元数据 ├── scripts/ # 可选:可执行代码 ├── references/ # 可选:文档参考资料 └── assets/ #

agentawsome-listclaudecodeopenclawskills

Quick Facts

Stars5,041
Forks402
CategoryCodex Skill
Quality Score64.4548521772341/100
Open Issues102
Last Updated2026-09-04
Created2025-12-21
Platformsaws, claude-code
Est. Tokens~18k

Compatible Skills

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

  • awesome-claude — semantic(0.22)+complementary+shared_fw(anthropic)+same_lang+similar_pop+shared_platform (61%)
  • claude-code-ultimate-guide — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • agent-skills — semantic(0.19)+complementary+shared_fw(vercel)+similar_pop+shared_platform (55%)
  • skills — semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (54%)
  • awesome-claude-code — semantic(0.28)+complementary+shared_fw(anthropic)+similar_pop+shared_platform (53%)

awesome-agent-skills alternative? Top 6 similar tools

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

  • AI-Infra-Guard by Tencent · ⭐ 6.4k

    A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca

  • ios-simulator-skill by conorluddy · ⭐ 1.2k

    An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with you

  • context-mode by mksglu · ⭐ 23.9k

    Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memo

  • memU by NevaMind-AI · ⭐ 14.4k

    Personal memory across agents

  • open-swe by langchain-ai · ⭐ 10.8k

    An Open-Source Asynchronous Coding Agent

  • Upsonic by Upsonic · ⭐ 8.0k

    Build autonomous AI agents in Python.

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Frequently Asked Questions

What is awesome-agent-skills?

awesome-agent-skills is Agent Skills 终极指南:快速入门、资源推荐、精选技能与实用工具 |The Ultimate Guide to Agent Skills: QuickStart, Resources, Features&Toolkit. It is categorized as a Codex Skill with 5.0k GitHub stars.

How do I install or use awesome-agent-skills?

You can find installation instructions and usage details in the awesome-agent-skills GitHub repository at github.com/libukai/awesome-agent-skills. The project has 5.0k stars and 402 forks, indicating an active community.

What are the best alternatives to awesome-agent-skills?

The top alternatives to awesome-agent-skills on Agent Skills Hub include AI-Infra-Guard, ios-simulator-skill, context-mode. 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 Codex Skill tools