DESIGN/设计资源·MOTION
HRuiCcc/RuiC-card-skill
一句话生成可拖拽、随视角流光的3D闪卡，附Blender工程One sentence yields a 3D holographic card with parallax shimmer, plus an editable Blender project.
不挑宿主，一句话生成可拖转、会流光的3D闪卡网页，附Blender工程。Turn a sentence into an interactive 3D holographic card with parallax depth, plus an editable Blender project — works with any multimodal model.
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+9.9%+9.9%
467 → 513 stars · 7 个快照467 → 513 stars · 7 snapshots
状态STATUS
持续活跃Active
质量 A-Quality A-
项目发布后迅速获得513颗星，说明社区认可度高Works with any multimodal model and any host that reads SKILL.md.
03 / 它能帮你做什么03 / What it helps you do
说一句话就得到一张3D闪卡网页
拖拽旋转翻面，手机也能用
拿到可编辑的Blender工程继续改
自动验收并生成报告和截图
四种卡面质感随便切换
Generate a 3D card from a sentence or reference image.
Drag, flip, and adjust depth with on-page sliders.
Get an editable Blender project file with layered materials.
Receive transparent layered PNGs and a card configuration file.
Run automated verification that tests drag, flip, sliders, and narrow screens.
04 / 安装04 / Install
文档里没有找到可识别的安装命令。这类项目按发布规则不会进入榜单，只能在这里查看。No recognisable install command was found in the docs. Projects like this never enter the ranked list under our publishing rules — they are viewable here only.
文档未提供安装说明Place the skill folder into your agent's skills directory (e.g., ~/.agents/skills/) and ensure you have Python 3.9+, Node.js, and a multimodal model.
05 / 限制与风险05 / Limits and risk
风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01控制浏览器Controls a browserreadme
- 验收脚本需要一个 Chromium 内核浏览器：系统装的 Chrome / Edge / Chromium 都行，Playwright 缓存里的 Chromium 也认，还可以用 `RUIC_BROWSER` 或 `--browser` 指定路径。**无 GUI 的 Linu
02控制浏览器Controls a browserSKILL.md
- `scripts/verify_web.mjs`: end-to-end browser verification over the DevTools Protocol — locates a Chromium-family browser (an explicit `--b
静态扫描发现两个中等风险：验收脚本会控制 Chromium 内核浏览器（通过 DevTools 协议），在无 GUI 的 Linux 环境也能自动运行。虽然脚本只用于本地验证，但若被恶意利用可能操控浏览器。The verification script requires a Chromium-based browser and can control it via the DevTools Protocol. This is a medium risk for environments where browser automation is restricted.
这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 2,
"ai-tools": 0,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 8,
"productivity": 1
},
"primary": "design",
"secondary": "motion"
},
"localRuntime": null,
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 1,
"design": 1,
"browser": 2,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "name contains 'skill'",
"weight": 0.4
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"SKILL.md"
],
"skillMdFetched": 1
}