RuiC-card-skill — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 HRuiCcc · Agent Tool · ★ 345

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

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

About RuiC-card-skill

✦ RuiC Card Skill 一个通用 Agent Skill:不挑宿主,多模态模型都能用——把小时候文具店门口那种会闪的全息卡复刻到浏览器里。 说一句话,就得到一张会随视角流光、带层次景深的 3D 闪卡网页,外加一个可以随便改的 Blender 工程。 小时候买不起的闪卡,现在你想印谁就印谁。这是你的私人卡牌工坊。 它是一台全自动闪卡生产线:你给一句话或一张参考图,剩下全交给模型—— 画四层图:主体、背景、线稿、文字,画在同一块画布、同一套坐标里 搭 3D 场景:Blender 建卡牌几何,把四层图按景深在空间里"撑开"——主体前凸、背景后缩 铺全息材质:镭射彩虹的相位跟着视角走,转到哪闪到哪;烫金 / 银箔 / 珠光 / 原画四种质感 组装网页:Three.js 查看器打包成单文件,起本地服务,打开页面实测拖拽、翻面、滑块、手机布局 交付:网页链接 + 源工程 + 四层透明 PNG + 配置 + 渲染图 技术栈就三样:Blender(官方便携版自动安装,不碰系统环境)+ Three.js(按同一套 UV 公式重建材质)+ Python 流水线(画完图之后一步到位)。skill 本体只有代码和文字,装上就能用;你生成的画作、工程、模型全部待在你自己的项目目录里。 🎬 演示 调整前 · 图层分散 初版层距:主体、特效、文字隔得较开,转动时明显"散开": ▶ 观看调整前完整视频 演示效果由 DeepSeek V4.1 Flash 实现。 调整后 · 层距收紧(现默认) 调整后:各层收近一档,卡片整体更紧凑,仍保留层次景深——这是当前出厂默认效果: ▶ 观看调整后完整视频 演示效果由 DeepSeek V4.1 Flash 实现。 ✨ 特性 一句话出卡:描述或参考图 → 分层图 → 配置 → 流水线 → 网页,全程自动,你只负责想 不挑宿主、不挑模型:不绑定某一家——流水线里模型要自己画四层图、自己打开渲染帧判断对不对,所以只要是多模态模型(能出图、能看图),配任何读 的宿主都能跑通 真 3D 层次景深:主体前凸、背景后缩,层与层随视角错开,不是一张平面贴图 视点流光:镭射彩虹的相位跟着视角走,转到哪闪到哪;烫金 / 银箔 / 珠光 / 原画四种卡面质感 浏览器里随便玩:拖拽旋转、翻面、景深/光泽/画面比例滑块,手机横竖屏都适配 出厂自带验收: 自己拉起无头浏览器和本地服务,把拖拽、翻面、缩放、键盘、五个滑块、四种质感、截图下载、390px 窄屏、减动效逐项跑完,并且比对真实画面帧(不是只看滑杆读数变没变),报告和截图落进 。macOS / Windows / Linux 都能跑,无 GUI 的容器与 root 环

agent-skillagent-skillsblendercollectible-cardholographicmultimodalskillsthreejswebgl

Quick Facts

Stars345
Forks29
LanguageJavaScript
CategoryAgent Tool
Quality Score60.5790738036841/100
Open Issues5
Last Updated2026-09-20
Created2026-09-07
Platformsbrowser, node
Est. Tokens~14k

RuiC-card-skill alternative? Top 6 similar tools

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

  • noobot by xiayu1987 · ⭐ 179

    Cheapest Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed ex

  • skillkit by rohitg00 · ⭐ 1.5k

    Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Curso

  • claude-workflow-v2 by CloudAI-X · ⭐ 1.4k

    Universal Claude Code workflow plugin with agents, skills, hooks, and commands

  • agent-skills by oxylabs · ⭐ 875

    Official Agent skills of Oxylabs products

  • copilot-mcp by VikashLoomba · ⭐ 505

    A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude

  • skillport by gotalab · ⭐ 406

    Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is RuiC-card-skill?

RuiC-card-skill is 全息闪卡通用 Agent Skill:多模态模型都能用,不挑宿主——一句话生成可拖转、会流光、带层次景深的 3D 闪卡网页,附可编辑 Blender 工程. It is categorized as a Agent Tool with 345 GitHub stars.

What programming language is RuiC-card-skill written in?

RuiC-card-skill is primarily written in JavaScript. It covers topics such as agent-skill, agent-skills, blender.

How do I install or use RuiC-card-skill?

You can find installation instructions and usage details in the RuiC-card-skill GitHub repository at github.com/HRuiCcc/RuiC-card-skill. The project has 345 stars and 29 forks, indicating an active community.

What are the best alternatives to RuiC-card-skill?

The top alternatives to RuiC-card-skill on Agent Skills Hub include noobot, skillkit, claude-workflow-v2. 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