openskills — 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 numman-ali · Agent Tool · ★ 10.8k

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

🔒 Is openskills safe to install? View the security audit →

About openskills

Universal skills loader for AI coding agents One CLI. Every agent. Same format as Claude Code. Quick Start · How It Works · Commands · Create Skills · FAQ ✨ What Is OpenSkills? OpenSkills brings Anthropic's skills system to every AI coding agent — Claude Code, Cursor, Windsurf, Aider, Codex, and anything that can read . Think of it as the universal installer for SKILL.md. 🚀 Quick Start By default, installs are project-local (, or with ). Use for . ✅ Why OpenSkills Exact Claude Code compatibility — same prompt format, same marketplace, same folder structure Universal — works with Claude Code, Cursor, Windsurf, Aider, Codex, and more Progressive disclosure — load skills only when needed (keeps context clean) Repo-friendly — skills live i

Quick Facts

Stars10,765
Forks670
LanguageTypeScript
CategoryAgent Tool
Quality Score63.7445994944768/100
Open Issues43
Last Updated2026-01-18
Created2025-10-26
Platformsnode
Est. Tokens~15k

Compatible Skills

These tools work well together with openskills for enhanced workflows:

  • rulesync — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)
  • MonkeyCode — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (60%)
  • ai-devkit — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • atlas — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (58%)
  • superset — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)

openskills alternative? Top 6 similar tools

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

  • open-saas by wasp-lang · ⭐ 15.8k

    A 100% free modern JS SaaS boilerplate (React, NodeJS, Prisma). Full-featured: Auth (email, google, github, sl

  • notebooklm-skill by PleasePrompto · ⭐ 7.8k

    Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your

  • agent-skills by tech-leads-club · ⭐ 6.5k

    The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Curso

  • excalidraw-diagram-skill by coleam00 · ⭐ 4.3k

    Skill to give Claude Code (and any coding agent) the ability to generate beautiful and practical Excalidraw di

  • raptor by gadievron · ⭐ 3.8k

    Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and

  • playwright-skill by lackeyjb · ⭐ 3.0k

    General-purpose Playwright automation for coding agents

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is openskills?

openskills is Universal skills loader for AI coding agents - npm i -g openskills. It is categorized as a Agent Tool with 10.8k GitHub stars.

What programming language is openskills written in?

openskills is primarily written in TypeScript.

How do I install or use openskills?

You can find installation instructions and usage details in the openskills GitHub repository at github.com/numman-ali/openskills. The project has 10.8k stars and 670 forks, indicating an active community.

What are the best alternatives to openskills?

The top alternatives to openskills on Agent Skills Hub include open-saas, notebooklm-skill, agent-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 Agent Tool tools