mcpbeat Sign in

Deck Open Slide Canvas Agent Skill

Locked 1920x1080 canvas deck with React component-level free composition, not bound to a fixed template.

990 tokens
context cost
SKILL.md, read when the skill is used
3
files
plus fonts, images or templates
0
copies elsewhere
how many repositories repackaged it
83 386
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/nexu-io/open-design --skill deck-open-slide-canvas

What comes with it

2 509 bytes besides the instruction
example.html
example.md

The instruction itself

as written by the author

【模板: 1920 画布自由 Deck】

【意图】不想被模板束缚的场景 (个人作品集、奇特演讲、艺术 / 设计课 deck)。给一个固定 1920×1080 画布 + 极强的类型 / 调色约束, 让 agent 像写 React 组件一样按内容自由排布每一页。Inspired by 1weiho/open-slide。

【硬性技术规格】

  • 画布: 每页严格 width: 1920px; height: 1080px; 用 transform: scale(...) 适配视窗 (默认 scale(0.7) 居中)。
  • 绝对禁止 overflow: 每页内容必须 fit in 1920×1080, 不许滚动条出现。
  • 字号 type scale (px): 2xs:18 · xs:22 · sm:28 · md:36 · lg:48 · xl:64 · 2xl:88 · 3xl:120 · 4xl:160 · 5xl:220。
  • 边距 padding: 96 / 128 / 160 三档之一。
  • 每页有 <section class="slide" data-slide-id="<n>">。

【调色板 — 每个 deck 选 1 套, 全程不改】

  • 🌫 Ash & Lime — bg #f1efea, ink #161616, accent #c5e803。
  • 🌌 Sea Indigo — bg #0a0e1a, ink #f5f5f7, accent #5ac8fa。
  • 🧉 Mate Mocha — bg #1a1411, ink #f5e9d6, accent #d97757。
  • 🌸 Pearl Rose — bg #fdf6f3, ink #1a1015, accent #ff5d8f。

【布局自由度 — 这是核心】

  • 不强制模板, 每页根据内容性质自选布局: cover / question / quote / image-text / 三列 / 五列 / 列表 / 数据卡 / 满版图。
  • 但每页必须遵守一条规则: 视觉重心 (visual hierarchy) 只有 1 个 — 一句金句、一个数字、一张图, 不要"什么都强调"。
  • 不许塞两段平等的文字; 真要并列就上 3 列等权重网格。

【字体】

  • 西文: Inter Tight (display) + Inter (body); 或 Source Serif Pro (editorial 风时)。
  • 中文: Noto Sans SC (sans 风) 或 Noto Serif SC (editorial 风); 不混 sans + serif。
  • mono: JetBrains Mono 给数据 / 时间戳。

【设计细节】

  • 严禁 emoji 装饰 (内容里的允许); 严禁多色彩虹; accent 只用一个色。
  • 严禁 SVG icon 套用 lucide / feather 等通用库 (自己写 inline SVG)。
  • 加键盘 ← / → 切换 + hash 同步; 角标固定: 右下 №N/M, 左下 deck title。
  • 必须用用户的真实内容; 严禁 lorem ipsum。
  • 单文件 HTML; Tailwind CDN; 不要外链图片。

Other skills for the same job

different authors, same section of the catalogue
Canvas Design
by anthropics
vendor ×16

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

3k tokens
Algorithmic Art
by anthropics
vendor ×14

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

4.9k tokens scripts
Image Enhancer
by frostant
×6

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

635 tokens
JSON Canvas
by ZhanlinCui
×4

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

3.5k tokens
X Article Publisher
by ZhanlinCui
×4

Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.

3.1k tokens scripts zh
Video Downloader
by CommandCodeAI
×4

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

671 tokens
High End Visual Design
by lornshrimp
×3

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

2.6k tokens
Histolab
by christophacham
×3

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

5.2k tokens

How to use it

Copy the folder

Take nexu-io/deck-open-slide-canvas from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.