Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cafe3310/public-agent-skills --skill llm-demo-websitegit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cafe3310/public-agent-skills/llm-demo-website)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/llm-demo-website"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/llm-demo-website/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/llm-demo-website"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/llm-demo-website.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01004 |
| Opus 5.5 | $0.00015 | $0.00402 |
| Sonnet 5.5 | $0.00007 | $0.00201 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
llm-demo-website scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
LLM Demo Website (Design & Concept Showcase Generator)
当个设计大师和前端专家。根据用户提示,完整、相近地写出用户所需的视觉风格的特点,包括颜色,样式,布局,给人的感受,体现的情感,对比,文字排版风格等。将这些内容标准化成 tailwindcss 和普通 css 表达的样式,以及 html 表达的组件。结合互联网最新的前沿审美,生成极具视觉表现力、适合演示与展示的单页面 HTML 设计系统演练场(Showcase)。
技术栈规范
- 样式方案: 使用 Tailwind CSS CDN 快速搭建页面的网格与骨架结构:
<script src="https://cdn.tailwindcss.com"></script>
- 配合内联
<style>块,使用 Vanilla CSS 与现代配色颜色函数定义精细的微动效、投影、特殊渐变及高端视觉微调。
- 图标库: 使用 Lucide 原生 JS 版图标库。
- 在 head 引入:
- 在 body 中使用属性占位,例如:
- 必须在 body 最底部或 DOM 加载后执行:lucide.createIcons();
- 占位图(LoremFlickr):
使用 LoremFlickr 接口获取符合网页视觉风格和主题的真实占位图:
- 格式:
https://loremflickr.com/{宽度}/{高度}/{关键词} - 示例:
https://loremflickr.com/800/600/abstract,minimalist
- 格式:
执行工作流
当用户要求设计某种视觉风格或主题的演示站时,Agent 必须严格执行以下步骤:
1. 深度审美搜索
要求:不能仅凭大模型自身的静态知识,必须执行尽可能丰富的、不同维度的深度搜索:
- 检索垂直风格在业界的最前沿体现(如
"modern minimal layout Awwwards")。 - 检索具体的高级配色方案与配色色值范例(如
"linear app design system colors 配色")。 - 检索特定动效与交互技巧(如
"smooth hover card border css micro-interactions")。
分析沉淀:以 Markdown 形式向用户完整阐述该风格的视觉特点,包括:
- 核心感受与情感:该设计带给用户的物理场景联想与情绪张力。
- 色彩与对比:主色调、辅助色及前景与背景的配色对比逻辑。
- 网格与布局:页面的视觉动线、不对称布局或变形。
- 文字排版:选用的 Google Fonts 字体配对、字重对比与行高字距。
2. 区块划分与设计
详细定义各个区块的视觉表现、内容文案与拟呈现的交互。你可以自由添加合适的内容,包括:
- Hero 部分:用尽可能直观的方式展示该风格的调性,be impressive。
- 配色和主题色版
- 组件列表,装饰,阴影等风格
- 文字和排版风格
- 更多关于此视觉设计风格的描述。
3. 样式与组件标准化(Design System Definition)
将第 1、2 步确立的设计提案转化为代码级的标准化规范:
- Tailwind 配置拓展:写出自定义颜色、字体、阴影的类名映射。
- CSS 自定义属性:使用配色定义一组核心配色变量(如
--bg,--fg,--primary,--accent)。 - 核心组件定义:规定核心卡片、按钮、分割线的 CSS 表达。
4. 生成高完成度单页面 HTML
整合上述内容,编写完整的单页面 HTML,力求完美呈现。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 78 lines · 37 tokens per session scan A 4f08ff6dcd05
llm-demo-website is a skill published in the GitHub repository cafe3310/public-agent-skills (256 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 1,004 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-05.
llm-demo-website compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| llm-demo-websitecafe3310/public-agent-skills | Skill | 256 | yesterday | Apache-2.0 | A | 37 | Claude Code, Codex |
| imagegen-frontend-webfirstsun-dev/skills | Skill | 5 | 4d ago | none | A | 126 | Claude Code, Codex |
| image-to-codefirstsun-dev/skills | Skill | 5 | 4d ago | none | A | 116 | Claude Code, Codex |
| design-taste-frontend-v1firstsun-dev/skills | Skill | 5 | 4d ago | none | A | 61 | Claude Code, Codex |
| ui-animationfirstsun-dev/skills | Skill | 5 | 4d ago | none | A | 75 | Claude Code, Codex |
| redesign-existing-projectsfirstsun-dev/skills | Skill | 5 | 4d ago | none | A | 45 | Claude Code, Codex |
| frontend-designfirstsun-dev/skills | Skill | 5 | 4d ago | none | A | 40 | Claude Code, Codex |