taste-skill — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

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 Leonxlnx · Codex Skill · ★ 90.3k

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

🔒 Is taste-skill safe to install? View the security audit →

Featured in: Humanizer & Anti-Slop Skills

About taste-skill

Taste Skill The Anti-Slop Frontend Framework for AI Agents Portable Agent Skills that upgrade AI-built interfaces: stronger layout, typography, motion, and spacing instead of boilerplate-looking UIs. This repo also includes image-generation skills for reference boards (web, mobile, brand kits). Pair them with ChatGPT Images or similar generators, then hand the frames to Codex, Cursor, or Claude Code for implementation. <img src="https://img.shields.io/badge/Tools-Codex%20%C2%B7%20Cursor%20%C2%B7%2

agentaiclaudeclaude-codecodexcodingdesignfrontendlowcodenocode

Quick Facts

Stars90,268
Forks6,147
LanguageJavaScript
CategoryCodex Skill
LicenseMIT
Quality Score70.3678852200822/100
Open Issues71
Last Updated2026-09-26
Created2026-02-19
Platformsclaude-code, codex, node
Est. Tokens~15k

Compatible Skills

These tools work well together with taste-skill for enhanced workflows:

  • Waza — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • peon-ping — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)
  • frontend-slides — semantic(0.16)+complementary+same_lang+similar_pop+shared_platform (56%)
  • dbskill — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (51%)
  • design-studio — semantic(0.19)+complementary+rare_topics+same_lang+shared_platform (51%)

taste-skill alternative? Top 6 similar tools

Looking for a taste-skill alternative? If you're comparing taste-skill 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.

  • serena by oraios · ⭐ 29.9k

    A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your a

  • ai-guide by liyupi · ⭐ 20.6k

    程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程,分享 OpenClaw 保姆级教程、大模型玩法(DeepSeek / GPT / Gemini / Claude / GLM)、最新 AI 资讯、Pr

  • dify by langgenius · ⭐ 157.8k

    Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. De

  • lobehub by lobehub · ⭐ 83.0k

    🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, an

  • awesome-claude-skills by ComposioHQ · ⭐ 75.3k

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

  • cc-switch by farion1231 · ⭐ 139.7k

    A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is taste-skill?

taste-skill is Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop. It is categorized as a Codex Skill with 90.3k GitHub stars.

What programming language is taste-skill written in?

taste-skill is primarily written in JavaScript. It covers topics such as agent, ai, claude.

How do I install or use taste-skill?

You can find installation instructions and usage details in the taste-skill GitHub repository at github.com/Leonxlnx/taste-skill. The project has 90.3k stars and 6147 forks, indicating an active community.

What license does taste-skill use?

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

What are the best alternatives to taste-skill?

The top alternatives to taste-skill on Agent Skills Hub include serena, ai-guide, dify. 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