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 AI Native UI. Trigger when user wants conversational interfaces, adaptive layouts, and generative AI aesthetics.
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill ai-native-ui --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ai-native-uiContext preview
The summary Claude sees to decide when to auto-load this skill.
Web and App implementation guide for AI Native UI. Trigger when user wants conversational interfaces, adaptive layouts, and generative AI aesthetics.
name: ai-native-ui description: Web and App implementation guide for AI Native UI. Trigger when user wants conversational interfaces, adaptive layouts, and generative AI aesthetics. date_added: "2026-06-17" risk: safe source: self source_type: self
> "Fluid, adaptive, and conversational. The interface morphs to serve the content."
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. **Conversational First**: The chat input or voice prompt is the primary navigation method, not a sidebar of links. 2. **Generative States**: Loading states aren't spinners; they are shimmering text, morphing gradients, or skeletal layouts that resolve smoothly into content. 3. **Adaptive Components**: Cards and blocks size themselves dynamically based on the generated content length.
body {
background-color: #FAFAFA;
color: #1A1A1A;
font-family: 'Inter', sans-serif;
}
/* The AI Chat Input */
.ai-prompt-box {
background: #ffffff;
border-radius: 24px;
padding: 16px 24px;
box-shadow: 0 8px 30px rgba(0,0,0,0.05);
border: 1px solid transparent;
/* AI Glow Border */
background-clip: padding-box, border-box;
background-origin: padding-box, border-box;
background-image:
linear-gradient(#ffffff, #ffffff),
linear-gradient(90deg, #8A2387, #E94057, #F27121);
transition: all 0.3s ease;
}
.ai-prompt-box:focus-within {
box-shadow: 0 12px 40px rgba(233, 64, 87, 0.15);
}
/* Generative Shimmer Text */
.ai-generating-text {
background: linear-gradient(90deg, #aaa 0%, #333 50%, #aaa 100%);
background-size: 200% auto;
color: transparent;
-webkit-background-clip: text;
animation: shine 1.5s linear infinite;
}
@keyframes shine {
to { background-position: 200% center; }
}struct AINativeInput: View {
@State private var isGenerating = true
@State private var gradientOffset = 0.0
var body: some View {
VStack {
// Generative Text Shimmer
if isGenerating {
Text("Synthesizing response...")
.font(.headline)
.foregroundStyle(
LinearGradient(
colors: [.gray.opacity(0.3), .gray, .gray.opacity(0.3)],
startPoint: UnitPoint(x: gradientOffset - 1, y: 0),
endPoint: UnitPoint(x: gradientOffset + 1, y: 0)
)
)
.onAppear {
withAnimation(.linear(duration: 1.5).repeatForever(autoreverses: false)) {
gradientOffset = 1.0
}
}
}
// AI Input Box
HStack {
TextField("Ask anything...", text: .constant(""))
Image(systemName: "sparkles")
.foregroundColor(.purple)
}
.padding()
.background(Color.white)
.cornerRadius(24)
.overlay(
RoundedRectangle(cornerRadius: 24)
.stroke(
LinearGradient(colors: [.purple, .pink, .orange], startPoint: .topLeading, endPoint: .bottomTrailing),
lineWidth: 2
)
)
.shadow(color: .pink.opacity(0.15), radius: 20)
}
.padding()
}
}import 'package:shimmer/shimmer.dart';
class AINativeInput extends StatelessWidget {
@override
Widget build(BuildContext context) {
return Padding(
padding: const EdgeInsets.all(16.0),
child: Column(
mainAxisSize: MainAxisSize.min,
children: [
// Generative Shimmer
Shimmer.fromColors(
baseColor: Colors.grey[300]!,
highlightColor: Colors.grey[600]!,
child: const Text('Synthesizing response...',
style: TextStyle(fontSize: 16, fontWeight: FontWeight.bold)),
),
const SizedBox(height: 16),
// AI Input Box
Container(
decoration: BoxDecoration(
color: Colors.white,
borderRadius: BorderRadius.circular(24),
boxShadow: [
BoxShadow(color: Colors.pink.withOpacity(0.15), blurRadius: 20),
],
),
child: Container(
decoration: BoxDecoration(
borderRadius: BorderRadius.circular(24),
// Gradient border simulation
gradient: const LinearGradient(
colors: [Colors.purple, Colors.pink, Colors.orange],
),
),
padding: const EdgeInsets.all(2), // Border width
child: Container(
decoration: BoxDecoration(
color: Colors.white,
borderRadius: BorderRadius.circular(22),
),
padding: const EdgeInsets.symmetric(horizontal: 16, vertical: 4),
child: Row(
children: const [
Expanded(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…