llm-demo-website

llm-demo-website is a skill for Claude Code, Codex from cafe3310/public-agent-skills. It costs 37 tokens per session (1,004 once invoked), scanned A, original, Apache-2.0.

A design-and-code skill for generating a single-page website that demonstrates a visual style and its interface components. It uses web research and turns the resulting direction into HTML, Tailwind CSS, and regular CSS examples.

In plain words
What is it for?
Use it to create a one-page design showcase for a requested style, including its visual explanation, reusable interface examples, and placeholder images.
Why use it?
It connects a visual brief to a concrete browser page instead of leaving the design as description alone. The page provides a place to inspect colours, layouts, typography, components, and motion.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create a one-page design showcase for a requested style, including its visual explanation, reusable interface examples, and placeholder images.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cafe3310/public-agent-skills/llm-demo-website
Install

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.

Any agent
npx skills add cafe3310/public-agent-skills --skill llm-demo-website
Clone the repo
git clone --depth 1 https://github.com/cafe3310/public-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for llm-demo-website

README.md
[![agentmods](https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/llm-demo-website/github.svg)](https://agentmods.dev/skills/cafe3310/public-agent-skills/llm-demo-website)
Your own site
<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.

agentmods 80×15 button for llm-demo-website

Your own site · 80×15
<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>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 4f08ff6dcd05, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

skills_parked/llm-demo-website/SKILL.md · 78 lines

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

  1. 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。
  1. 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();
  1. 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

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:

  1. 检索垂直风格在业界的最前沿体现(如 "modern minimal layout Awwwards")。
  2. 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")。
  3. 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。

Changes

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.

  1. 2d ago First seen · 78 lines · 37 tokens per session scan A 4f08ff6dcd05

Subscribe to this mod's changes

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.

Related

llm-demo-website compared with skills from other repositories

llm-demo-website next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
llm-demo-websitecafe3310/public-agent-skillsSkill256yesterdayApache-2.0A37Claude Code, Codex
imagegen-frontend-webfirstsun-dev/skillsSkill54d agononeA126Claude Code, Codex
image-to-codefirstsun-dev/skillsSkill54d agononeA116Claude Code, Codex
design-taste-frontend-v1firstsun-dev/skillsSkill54d agononeA61Claude Code, Codex
ui-animationfirstsun-dev/skillsSkill54d agononeA75Claude Code, Codex
redesign-existing-projectsfirstsun-dev/skillsSkill54d agononeA45Claude Code, Codex
frontend-designfirstsun-dev/skillsSkill54d agononeA40Claude Code, Codex