cheat-on-content
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…
Web and App implementation guide for 3D UI. Trigger when user wants actual 3D objects, perspective effects, and spatial depth.
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill 3d-ui --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/3d-uiContext preview
The summary Claude sees to decide when to auto-load this skill.
Web and App implementation guide for 3D UI. Trigger when user wants actual 3D objects, perspective effects, and spatial depth.
name: 3d-ui description: Web and App implementation guide for 3D UI. Trigger when user wants actual 3D objects, perspective effects, and spatial depth. date_added: "2026-06-17" risk: safe source: self source_type: self
> "Breaking the plane. Interfaces that exist in a three-dimensional, rotatable space."
Use this sub-style when the user's request matches the aesthetic described above. This is a child reference of the `design-it` skill and is not meant to be triggered directly.
1. **True Depth (Z-Axis Translation)**: Elements don't just have shadows; they physically move closer to or further from the camera. 2. **Perspective**: Use CSS perspective or WebGL to create realistic vanishing points. 3. **Interactive Rotation**: Elements should respond to mouse movement or device gyroscope by tilting or rotating in 3D space.
.perspective-container {
perspective: 1000px;
display: flex;
justify-content: center;
align-items: center;
}
.card-3d {
width: 300px;
height: 400px;
transform-style: preserve-3d;
transition: transform 0.5s ease;
/* Initial slight rotation */
transform: rotateX(15deg) rotateY(-15deg);
}
.card-3d:hover {
/* Straighten out on hover */
transform: rotateX(0) rotateY(0) translateZ(50px);
}
/* Inner elements popping out */
.card-content {
transform: translateZ(30px); /* Pushes content 30px closer to viewer */
}struct Card3D: View {
@State private var dragOffset = CGSize.zero
var body: some View {
VStack {
Text("3D Card")
.font(.largeTitle.bold())
.foregroundColor(.white)
}
.frame(width: 300, height: 400)
.background(
LinearGradient(colors: [.blue, .purple], startPoint: .topLeading, endPoint: .bottomTrailing)
)
.cornerRadius(24)
.shadow(radius: 20)
// Magic 3D effect based on drag gesture
.rotation3DEffect(
.degrees(Double(dragOffset.width / 10)),
axis: (x: 0, y: 1, z: 0),
perspective: 0.5
)
.rotation3DEffect(
.degrees(Double(-dragOffset.height / 10)),
axis: (x: 1, y: 0, z: 0),
perspective: 0.5
)
.gesture(
DragGesture()
.onChanged { value in
withAnimation(.interactiveSpring()) {
dragOffset = value.translation
}
}
.onEnded { _ in
withAnimation(.spring()) {
dragOffset = .zero
}
}
)
}
}class Card3D extends StatefulWidget {
@override
State<Card3D> createState() => _Card3DState();
}
class _Card3DState extends State<Card3D> {
Offset _offset = Offset.zero;
@override
Widget build(BuildContext context) {
return GestureDetector(
onPanUpdate: (details) {
setState(() => _offset += details.delta);
},
onPanEnd: (_) {
setState(() => _offset = Offset.zero); // Snap back
},
child: TweenAnimationBuilder(
tween: Tween<Offset>(begin: Offset.zero, end: _offset),
duration: const Duration(milliseconds: 200),
curve: Curves.easeOut,
builder: (context, Offset offset, child) {
// Perspective Matrix
final transform = Matrix4.identity()
..setEntry(3, 2, 0.001) // perspective
..rotateX(-offset.dy * 0.01)
..rotateY(offset.dx * 0.01);
return Transform(
transform: transform,
alignment: FractionalOffset.center,
child: Container(
width: 300,
height: 400,
decoration: BoxDecoration(
gradient: const LinearGradient(colors: [Colors.blue, Colors.purple]),
borderRadius: BorderRadius.circular(24),
boxShadow: const [BoxShadow(color: Colors.black45, blurRadius: 20)],
),
alignment: Alignment.center,
child: const Text('3D Card',
style: TextStyle(color: Colors.white, fontSize: 32, fontWeight: FontWeight.bold)),
),
);
},
),
);
}
}const Card3D = () => {
const pan = useRef(new Animated.ValueXY()).current;
const panResponder = useRef(
PanResponder.create({
onStartShouldSetPanResponder: () => true,
onPanResponderMove: Animated.event([null, { dx: pan.x, dy: pan.y }], { useNativeDriver: false }),
onPanResponderRelease: () => {
Animated.spring(pan, { toValue: { x: 0, y: 0 }, useNativeDriver: false }).start();
},
})
).current;
// Map drag distance to degrees
const rotateX = pan.y.interpolate({ inputRange: [-200, 200], outputRange: ['20deg', '-20deg'] });
const rotateY = pan.x.interpolate({ inputRange:MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.
Repo: LiHongwei-cn/lihongwei-cn
给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…
提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind…
cheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环,唯一区别是"发过视频的人"会在 init 时多一步:抓取已有视频建立历史 context(用于后续 cheat-seed 给更贴合的选题、更准的…
从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / script_patterns.md / rubric_notes.md。**这是工具最早期信号的来源**——cold-start…
把老用户的 .cheat-state.json 升级到当前 schema_version。读 migrations/registry.md 算迁移链,按顺序应用每一步迁移文件。幂等:跑两次结果一样。失败停在中间版本不前进。触发词:"迁移"/"升级 state"/"migrate"/"我的 state…
从复盘评论数据派生 / 刷新账号的受众画像,写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分",persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号,cheat-score-blind…