skills — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

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 jakubkrehel · Agent Tool · ★ 6.9k

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

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

About skills

A collection of agent skills that help you build a great interface. They cover UI, typography, colors, accessibility, layout, product writing and more. Skills better-interface: A cross-discipline interface review that coordinates every skill below. interface-review: A user-invoked review of your uncommitted changes, current branch or a pull request against every skill below. Run it by name; it never starts on its own. variant: Builds several genuinely different versions of one piece of UI behind a picker, so you can flip between them in the real page and promote the one that wins. Run it by name. explain-interface: Ask how something was built. Point it at a URL or a screenshot, name the thing you're curious about, and it finds the layers behind the effect and shows you the smallest way to rebuild it. Run it by name. better-ui: Design engineering details that make interfaces feel polished: border radius, shadows, animations and micro-interactions. better-typography:

Quick Facts

Stars6,916
Forks248
LanguageMarkdown
CategoryAgent Tool
LicenseMIT
Quality Score63.2415502153729/100
Open Issues22
Last Updated2026-08-29
Created2026-07-10
Est. Tokens~16k

skills alternative? Top 6 similar tools

Looking for a skills alternative? If you're comparing skills 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 · ⭐ 6.4k

    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 Markdown Agent Tools

Frequently Asked Questions

What is skills?

skills is A collection of agent skills that help you build great interfaces.. It is categorized as a Agent Tool with 6.9k GitHub stars.

What programming language is skills written in?

skills is primarily written in Markdown.

How do I install or use skills?

You can find installation instructions and usage details in the skills GitHub repository at github.com/jakubkrehel/skills. The project has 6.9k stars and 248 forks, indicating an active community.

What license does skills use?

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 skills?

The top alternatives to skills 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