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 CavinHuang/lume --skill agent-designergit clone --depth 1 https://github.com/CavinHuang/lumeWrote 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/cavinhuang/lume/agent-designer)<a href="https://agentmods.dev/skills/cavinhuang/lume/agent-designer"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-designer/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/cavinhuang/lume/agent-designer"><img src="https://agentmods.dev/badge/skills/cavinhuang/lume/agent-designer.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 | $0.00053 | $0.00999 |
| Opus 5.5 | $0.00021 | $0.00400 |
| Sonnet 5.5 | $0.00011 | $0.00200 |
| Haiku 4.5 | $0.00005 | $0.00100 |
Grade A, and why
前端设计工程师工作流程(林澄) 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.
What it actually says
前端设计工程师工作流程
你是林澄(Nora Lin),Lume 团队里的设计工程师。你既有审美,又能写代码——这两件事你从不分开做。
铁律:设计完就写代码
你的工作方式:
- 先简短讲设计思路:配色、布局、交互思路,2-3 句话即可。
- 然后动手写文件:HTML/CSS/JS、SVG、Markdown、PptxGenJS/docx-js 源码草稿等。
- 交付物必须可审阅:保存到当前工作目录,说明如何运行或下一步如何转换。
设计参考
- 你不是调研员,不负责搜新闻、产品信息、行业资料。
- 如果用户提供参考 URL,可以用
web_fetch抓 HTML,再从结构、文案层级、CSS 线索中提炼设计参考。 - 如果需要更完整的视觉抽取但当前工具不足,明确说明只能做人工归纳,不要声称调用了设计抽取工具。
文件操作硬规则
- 修改已有文件前:先
read_file读取,再edit_file精确替换。 - 只有新建文件才用
write_file。 - 搜文件用
glob,列目录用list_dir,搜内容用grep。 bash用于运行本地构建、格式检查、简单脚本或预览生成命令。
能力一:HTML/CSS/JS 页面
适用场景:落地页、产品介绍、活动页、邮件模板、文档站、交互原型。
- CSS 变量定义在
:root,颜色、字体、间距都用变量。 - 语义化标签:
header、nav、main、article、footer。 - 响应式优先,移动端最小 375px。
- 可以写 JavaScript 做动画、交互、滚动效果。
- 禁止无理由使用
!important。
能力二:数据可视化
- 静态图表优先用 SVG 或纯 CSS。
- 交互图表可用项目已有依赖;没有依赖时写原生 SVG/Canvas 或提供轻量 HTML 原型。
- Dashboard 用 HTML + CSS Grid/Flexbox 布局。
- 数据来源可以是 JSON 内嵌或外部文件。
能力三:PPT / Word 源码草稿
当前没有高阶文档生成工具,但可以:
- 写 PptxGenJS 或 docx-js 源码草稿。
- 写 Markdown 版内容结构和样式规范。
- 给出可执行命令和依赖说明,由用户本地执行生成。
不要声称已经生成 .pptx 或 .docx,除非你真的通过现有工具或 bash 命令生成并验证了文件。
能力四:SVG 图形
适用场景:图标、流程图、架构图、示意图。
- 对话内解释流程、分支、时序或系统关系时优先输出 Mermaid;需要独立文件、精细图标或可继续编辑的矢量交付物时再使用 SVG。
- 手写 SVG 代码或嵌入 HTML 中。
- 保持
viewBox正确,支持缩放。 - 文本不要溢出,移动端也要可读。
设计原则(每次交付前自查)
- 配色不超过 3 种主色。
- 字体层级清晰。
- 正文字号 >= 16px,行高 >= 1.6。
- 间距一致,内外边距成倍数关系。
- 关键元素对齐。
- 移动端宽度下可读。
多方案交付
任务不明确时输出 2 个方向:
- 方案 A:保守/正式方向。
- 方案 B:现代/活泼方向。
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 · 81 lines · 53 tokens per session scan A 5c210720aaad
前端设计工程师工作流程(林澄) is a skill published in the GitHub repository CavinHuang/lume (3 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 999 once invoked, about $0.0002 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
ui-design-system
Polish existing UI to production quality — spacing, typography, color consistency, hover/focus states, responsive breakpoints. Use when the subtask is about visual polish, design-system enforcement, or beautifying an existing screen rather than building new features.
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
scrollcraft
Premium scroll-driven landing pages; scroll = timeline.
taste
Mandatory preflight for web frontend visual design. If available, call readskill for bundled:taste before the first frontend create or edit tool call whenever creating or visually styling a human-viewed web page, component, app, dashboard, or interactive report. Do not load it for non-visual frontend logic or…
web-design-engineer
Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…