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 jackguihx-alt/html2style --skill html2stylegit clone --depth 1 https://github.com/jackguihx-alt/html2styleWrote 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/jackguihx-alt/html2style/html2style)<a href="https://agentmods.dev/skills/jackguihx-alt/html2style/html2style"><img src="https://agentmods.dev/badge/skills/jackguihx-alt/html2style/html2style/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/jackguihx-alt/html2style/html2style"><img src="https://agentmods.dev/badge/skills/jackguihx-alt/html2style/html2style.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 | $0.00145 | $0.04410 |
| Opus 5.5 | $0.00058 | $0.01764 |
| Sonnet 5.5 | $0.00029 | $0.00882 |
| Haiku 4.5 | $0.00015 | $0.00441 |
Grade A, and why
html2style 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML2Style
把真实网站转化为可移植的设计证据与可复用视觉规则,使其他 Agent 不依赖原网页、原聊天记录或特定厂商浏览器也能继续使用。
语言与全球化
- 中文优先:当用户使用中文或未明确指定语言时,人类可读交付物默认使用
zh-CN。 - 国际用户:当用户使用英文或明确要求英文时,使用
en。 - 执行
html2style skill时显式传入--locale zh-CN或--locale en;MCP 的create_style_skill使用同名locale参数。 - 本地化生成 Skill 的
SKILL.md、agents/openai.yaml和最终用户说明。 - CLI 命令、MCP 工具名、文件名、JSON schema、Token 名称和代码标识符始终保持英文,避免破坏跨地区自动化。
- 原网站文案和测量证据保持原始语言。除非用户明确要求,不要把内容翻译与设计提取混在一起。
- 回复语言跟随用户当前语言,而不是参考网站语言。
Default deliverables / 默认交付物:
<style-name>-style/:默认最终交付的标准 Skill 文件夹,可以复制到新项目或 Agent 的 skills 目录。SKILL.md:唯一 Agent 入口,说明如何将这套网页风格用于新任务。agents/openai.yaml:Skill 列表、快捷提示和 UI 元数据。assets/preview.html:人类可以直接打开的自包含 HTML 风格预览。references/STYLE.md:可迁移到不同产品或业务场景的完整设计规则。references/style-profile.json:从浏览器证据生成、支撑风格规则的确定性测量。references/measurements.md:可选的测量摘要,仅在需要追溯精确依据时读取。- 旧
design-package/:仅在用户需要 manifest、原始证据、自动化入口或完整归档时使用html2style bundle生成。 DESIGN.md:供 Agent 使用的结构化设计系统事实来源。design-system.html:使用提取到的 Token 和组件渲染,供人类查看的 HTML 设计系统。- 图标库:存在图标时,生成可搜索 HTML、
icons-data.json和独立 SVG 文件。 - 资源 manifest:图片、背景、字体、SVG、资源 URL 和响应式参考截图。
- 还原度对比:设计系统验证使用代表性样本;用户要求完整复刻时覆盖整个可见页面。
- 设计语言迁移:为新人物、产品或业务创建原创网站,复用测量得到的视觉原则,但不复制原站品牌、内容或专有素材。
优先使用真实页面证据:DOM、计算样式、CSS 变量、网络资源、验证截图和可见交互。不要只凭记忆或截图推断精确 Token;能够提取原始图片、Logo 或图标时,不要用近似占位物替代。
开始 / Start
- 确定模式:
- 风格提取:用户希望理解或复用视觉语言。只交付风格包,除非用户要求,否则不要额外构建复刻站或新网站。
- 全新采集:用户提供 URL,创建完整交付物。
- 补充现有工作:用户提供
DESIGN.md和 URL。先读现有文件、列出缺口,只采集缺失证据。 - 完整复刻:清点并复现所有可见区块和重复项目,不得静默降级为代表性样本。
- 设计语言迁移:用户提供参考网站或
DESIGN.md与新用途,使用可迁移设计原则创建原创信息架构和内容系统。
- 检查工具:
- 首先运行
html2style doctor或 MCPbrowser_doctor。 - 页面需要 JavaScript 渲染、登录、计算样式、CSS 变量、SVG sprite、截图或交互状态时,使用内置的 Agent 中立浏览器流程。
- 宿主 Agent 自带的浏览器工具可以辅助检查,但不能成为这套工作流的必要依赖。
- 只有公开 HTML 已包含目标内容且不需要精确计算样式时,才使用静态抓取。
- 浏览器工具不可用时,阅读
references/browser-tooling-bootstrap.md并指导安装,不要对动态页面静默降级。
- 首先运行
- 确定页面和视口范围:
- 网站明显包含不同页面类型,而用户只提供一个 URL 时,如果能显著改善页面模式覆盖,可请求 2-5 个代表性 URL。
- 简单单页网站直接使用一个 URL。
- 默认使用
full:桌面高/短、平板高/短和移动端,覆盖同时受宽度与高度控制的响应式图片。 - 只有速度明显更重要时才使用
standard或minimal,并记录跳过的响应式条件。 - 对比原站和复刻站时保持视口尺寸完全一致。
- 安全处理登录:
- 使用
--headed --login-wait <seconds>打开临时可见浏览器,让用户手动登录。 - 不要索取凭据、自动绕过 MFA 或替用户选择账号。
- 使用
What ships with it
35 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 259 B
- assets/design-preview-shell.template.html 5.9 KB
- assets/DESIGN.template.md 21 KB
- assets/STYLE.template.md 6.0 KB
- examples/product-editorial/design-package/AGENT-HANDOFF.md 1.7 KB
- examples/product-editorial/design-package/manifest.json 1.5 KB
- examples/product-editorial/design-package/START-HERE.html 4.8 KB
- examples/product-editorial/design-package/START-HERE.md 1.4 KB
- examples/product-editorial/design-package/style-board.html 49 KB
- examples/product-editorial/design-package/style-profile.json 1.9 KB
- examples/product-editorial/design-package/STYLE.md 6.7 KB
- examples/product-editorial/product-editorial-style/agents/openai.yaml 287 B
- examples/product-editorial/product-editorial-style/assets/preview.html 49 KB
- examples/product-editorial/product-editorial-style/references/style-profile.json 1.9 KB
- examples/product-editorial/product-editorial-style/references/STYLE.md 6.7 KB
- examples/product-editorial/product-editorial-style/SKILL.md 2.0 KB
- examples/product-editorial/README.md 1.3 KB
- references/advanced-visual-systems.md 3.3 KB
- references/apple-homepage-case-study.md 6.3 KB
- references/browser-tooling-bootstrap.md 4.1 KB
- references/design-language-transfer.md 3.5 KB
- references/high-fidelity-reconstruction.md 5.0 KB
- references/validation-and-learning.md 2.5 KB
- references/website-reading-checklist.md 11 KB
- scripts/audit-reconstruction.mjs 2.7 KB runs code
- scripts/check-browser-tooling.mjs 1.5 KB runs code
- scripts/create-design-package.mjs 23 KB runs code
- scripts/create-style-skill.mjs 11 KB runs code
- scripts/extract-browser-evidence.mjs 53 KB runs code
- scripts/extract-icons.mjs 15 KB runs code
- scripts/extract-style-profile.mjs 2.0 KB runs code
- scripts/render-design-preview.mjs 66 KB runs code
- scripts/render-visual-comparison.mjs 5.3 KB runs code
- scripts/validate-asset-urls.mjs 3.1 KB runs code
- scripts/validate-package.mjs 4.5 KB runs code
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.
- 1mo ago First seen · 242 lines · 145 tokens per session scan A 133525589659
html2style is a skill published in the GitHub repository jackguihx-alt/html2style (2 stars, last pushed 2mo ago), licensed MIT. It adds 145 tokens to every session and 4,410 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
daisyui-colors
Color rules that you must use with daisyUI 5.
daisyui-config
Configuration options for daisyUI 5.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
ui-components
UI component library patterns for shadcn/ui and Radix Primitives. Use when building accessible component libraries, customizing shadcn components, using Radix unstyled primitives, or creating design system foundations.
s2-docs
Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components. Use when the user mentions Spectrum, S2, React Spectrum, RSP, Spectrum Web Components, or SWC, or names a Spectrum component (Button, Picker, ComboBox, TextField…
readable-measure
Set line length and measure for comfortable reading across type sizes and breakpoints. Use when tuning body text. Covers measure only — for the full size and weight scale, use typography-scale.