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 YiShu5/claude-skills --skill htmlhero.skillgit clone --depth 1 https://github.com/YiShu5/claude-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/yishu5/claude-skills/htmlhero.skill)<a href="https://agentmods.dev/skills/yishu5/claude-skills/htmlhero.skill"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/htmlhero.skill/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/yishu5/claude-skills/htmlhero.skill"><img src="https://agentmods.dev/badge/skills/yishu5/claude-skills/htmlhero.skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00107 | $0.01281 |
| Opus 5 | $0.00053 | $0.00641 |
| Sonnet 5 | $0.00021 | $0.00256 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
HTMLHero.skill 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 11d 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
HTMLHero.skill
把用户给的 Hero Prompt 或主题,生成一个可运行、可演示、可继续扩展成 HTML/PPT 的第一页 Hero。
核心原则:第一页不是普通首页,它是后续整套页面的视觉母版。
适用场景
当用户提出以下任一需求时使用:
- 按一个 Hero Prompt 生成第一页
- 把现成 Prompt 的主题、标题、文案换成用户的新主题
- 做一个现代、互动、能跑的 Hero section
- 需要 React / Vite / Tailwind / motion 风格的第一页
- 需要背景视频、打字机标题、交互 pills、导航、CTA、视觉母版
- 用户说“先同步一下”“有什么不懂先问我”“需要你更改的部分: {}”
阶段 1:先读完,再对齐
不要立刻写代码。先完整阅读用户给的:
- Hero Prompt
- 附件文本
- 主题/主旨
- 使用场景
- 现有工程文件
- 技术栈限制
然后提炼:
- 页面主标题和副标题
- 核心叙事或汇报主旨
- 必须保留的元素,如背景视频、打字机、pills、导航
- 可替换元素,如品牌名、按钮文案、选项文案、说明文案
- 视觉风格来源,如字体、色值、间距、卡片、动效
- 是否要创建新工程,还是接入现有工程
- 交付物:本地预览、源码、zip、部署
输出一段简短理解说明,并且必须输出下面这个块。
如果有需要用户确认或替换的内容:
需要你更改的部分: {
"主题/主旨": "需要用户确认或替换的内容",
"主标题": "需要用户确认或替换的内容",
"副标题/说明": "需要用户确认或替换的内容",
"背景媒体": "需要用户确认或替换的内容",
"交互组件": "需要用户确认或替换的内容",
"技术栈/工程位置": "需要用户确认或替换的内容",
"交付物": "需要用户确认或替换的内容"
}
只保留真正需要确认的 key。没有不确定项时输出:
需要你更改的部分: {}
最后问用户是否确认执行。
阶段 2:确认后再执行
只有当用户明确回复类似下面的话,才开始修改代码:
确认执行开始做没问题就按这个来
如果用户继续补充内容,不要急着执行;更新理解和 需要你更改的部分。
执行规则
执行时必须:
- 先检查当前目录是否已有工程,不要盲目覆盖。
- 如果已有工程,优先顺着现有技术栈和文件结构改。
- 如果没有合适工程,再创建轻量 Vite + React 页面。
- 不随意新增依赖;如果需要新增,必须和用户目标直接相关。
- 保留用户指定的 Hero 结构和关键视觉元素。
- 主题替换要彻底:品牌名、标题、副标题、选项、CTA、提示文案都要一致。
- Hero 首屏必须直接是可用体验,不做营销式空壳介绍页。
- 背景视频/图片要真实渲染,不要只留占位。
- 动画要有质感但克制:打字机只用于主标题,背景运动避免卡顿和 PPT 感。
- 页面必须适配桌面和移动端,文字不能重叠、溢出或被媒体挡住。
推荐实现约束
如果用户没有另行指定,优先使用:
- Vite + React
- Tailwind CSS
motion/react做进场、hover、切换动画lucide-react做按钮/icon- CSS variables 保存核心颜色
- 一个主组件 + 少量小组件,先保证可继续扩展
背景视频交互优先选择“视频自然播放 + 鼠标视差/漂移”的方案;只有用户明确要求拖动时间轴时,才用 currentTime scrub。远程 MP4 反复 seek 容易卡顿。
验收
完成后必须尽量验证:
npm run build或项目等价构建命令成功- 本地 dev server 能打开
- 首屏不是空白,主标题可见
- 背景媒体加载或有合理降级
- 主要交互可点击
- 桌面和移动端至少各检查一次
- 如用户要给别人看,生成 zip 并排除
node_modules/、dist/、.git/
交付回复
最终回复保持简短,包含:
- 改了什么
- 关键文件路径
- 本地预览 URL
- 构建/验证结果
- zip 或部署链接,如已生成
不要只给设计建议;确认执行后要完成到可运行、可验证、可交付。
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.
- 11d ago First seen · 131 lines · 107 tokens per session scan A f81a59f5f201
HTMLHero.skill is a skill published in the GitHub repository YiShu5/claude-skills (83 stars, last pushed 3d ago), licensed MIT. It adds 107 tokens to every session and 1,281 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
skill-premium-web-experience
Use for creating, redesigning, or transforming websites into premium, cinematic, conversion-focused web experiences with visual research, storytelling, scroll-driven interaction, responsive design, motion, performance, accessibility, and visual QA.
skill-frontend-ux-guardrails
Use as a frontend UX quality gate for responsive behavior, overflow, accessibility, interaction usability, touch targets, typography, layout stability, mobile behavior, focus states, reduced motion, and final visual validation.
skill-modern-ui-patterns
Use for professional frontend UI implementation with modern component composition, interaction states, forms, tables, cards, navigation, dashboards, SaaS surfaces, and maintainable design-system consistency.
skill-impeccable
Orquestra melhorias de frontend inspiradas no Impeccable a partir de pedidos conversacionais de design, UX, acessibilidade, responsividade, tipografia, layout, cor, motion, clareza, hardening e polish.
skill-saas-admin-dashboard
Build or improve SaaS admin dashboards, internal admin panels, user/customer screens, tenant/workspace screens, plan/payment/log views, sidebar layouts, metrics, filters, tables, support tools, and onboarding administration.
mockup-extraction
Extract reusable components from approved HTML mockups during implementation. Identifies patterns, maps CSS to Tailwind, and populates prototype-patterns.md for visual fidelity. Use at start of /implement for UI-first features.