cc-design-html-prototyping
High-fidelity HTML design and prototype creation skill for AI coding agents — slide decks, interactive prototypes, landing pages, UI mockups, animations, and brand style cloning.
What this skill does
# CC Design
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
CC Design is a structured design workflow skill for AI coding agents. It enables Claude Code, Codex, and compatible agents to act as expert product designers — producing high-fidelity HTML artifacts including slide decks, interactive prototypes, landing pages, UI mockups, and animated motion studies. It supports brand style cloning from 68+ design systems and uses Playwright for visual verification.
---
## Installation
Clone into the Claude Code skills directory:
```bash
git clone https://github.com/ZeroZ-lab/cc-design.git ~/.claude/skills/cc-design
```
Or as a submodule in an existing skill collection:
```bash
git submodule add https://github.com/ZeroZ-lab/cc-design.git skills/cc-design
```
Install export script dependencies (for PPTX, PDF, and inline HTML export):
```bash
cd ~/.claude/skills/cc-design/scripts && npm install && cd -
npx playwright install chromium
```
---
## Project Structure
```
cc-design/
├── SKILL.md # Core skill definition (always loaded)
├── EXAMPLES.md # Brand cloning and advanced usage examples
├── agents/
│ └── openai.yaml # Codex-compatible interface config
├── references/
│ ├── getdesign-loader.md # Brand style loading from getdesign.md
│ ├── platform-tools.md # Claude Code + Playwright tool reference
│ ├── react-babel-setup.md # React/Babel pinned versions and scope rules
│ ├── starter-components.md # Starter component catalog
│ └── tweaks-system.md # In-page tweak controls
├── templates/
│ ├── deck_stage.js # Slide presentation stage
│ ├── design_canvas.jsx # Side-by-side option grid
│ ├── ios_frame.jsx # iPhone device frame
│ ├── android_frame.jsx # Android device frame
│ ├── macos_window.jsx # macOS window chrome
│ ├── browser_window.jsx # Browser window chrome
│ └── animations.jsx # Timeline animation engine
└── scripts/
├── package.json
├── gen_pptx.js # HTML → PPTX export
├── super_inline_html.js # HTML + assets → single file
└── open_for_print.js # HTML → PDF via Playwright
```
---
## Design Workflow
The skill follows a six-phase loop for every design request:
```
Understand → Explore → Plan → Build → Verify → Deliver
```
1. **Understand** — Clarify intent, audience, constraints, and existing brand context before writing any code.
2. **Explore** — Read existing design tokens, component libraries, or product code in the repo. Load brand systems from `getdesign.md` when a brand name is mentioned.
3. **Plan** — Write a brief todo list of components, layout decisions, and variation axes.
4. **Build** — Produce HTML + inline React/Babel components. Use pinned CDN versions (see below).
5. **Verify** — Use Playwright to take a screenshot and check the browser console for errors.
6. **Deliver** — Write the final file, offer export options (PPTX, PDF, single-file HTML).
---
## Core Principles
- **Context-first design** — Never design from scratch when existing brand systems, component libraries, or product code is available. Scan the repo and load relevant context before creating new visual directions.
- **Progressive disclosure** — The main `SKILL.md` stays concise. Technical references in `references/` are loaded on demand to keep context window usage minimal.
- **3+ variations** — Always generate at least three design directions across layout, visual intensity, interaction model, or motion axes.
---
## Key Capabilities
| Category | Details |
|---|---|
| Output formats | Interactive prototypes, slide decks, landing pages, UI mockups, animated motion studies, design explorations |
| Brand style cloning | 68+ brands via [getdesign.md](https://getdesign.md): Stripe, Vercel, Notion, Linear, Apple, Tesla, Figma, GitHub, Airbnb, and more |
| Design systems | Auto-discovers and reuses existing tokens, typography, spacing, and color patterns from the project |
| Variations | Generates 3+ directions across layout, interaction, visual intensity, and motion axes |
| Prototyping | React + Babel inline JSX with pinned CDN versions, component scope management |
| Tweaks system | Self-contained in-page design controls with real-time preview and `localStorage` persistence |
| Verification | Playwright screenshot + console error check after every build step |
| Export | PPTX via `gen_pptx.js`, PDF via `open_for_print.js`, single-file via `super_inline_html.js` |
---
## React + Babel Setup (Pinned Versions)
All prototypes use pinned CDN versions to guarantee reproducibility:
```html
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Prototype</title>
<script src="https://unpkg.com/[email protected]/umd/react.development.js"></script>
<script src="https://unpkg.com/[email protected]/umd/react-dom.development.js"></script>
<script src="https://unpkg.com/@babel/[email protected]/babel.min.js"></script>
<script src="https://cdn.tailwindcss.com"></script>
</head>
<body>
<div id="root"></div>
<script type="text/babel">
const { useState, useEffect, useRef } = React;
function App() {
return (
<div className="min-h-screen bg-white flex items-center justify-center">
<h1 className="text-4xl font-bold text-gray-900">Hello, CC Design</h1>
</div>
);
}
ReactDOM.createRoot(document.getElementById('root')).render(<App />);
</script>
</body>
</html>
```
**Rules for inline JSX:**
- Always use `type="text/babel"` on script tags containing JSX.
- Destructure hooks from `React` at the top of the script block — do not use `React.useState` inline.
- Keep all components in a single script block unless explicitly splitting files.
- Never use ES module `import` syntax — CDN UMD builds expose globals only.
---
## Brand Style Cloning
Mention a brand name in the prompt to trigger automatic loading of its design system from [getdesign.md](https://getdesign.md):
```
"Create a pricing page with Stripe's aesthetic"
"Notion-style kanban board"
"Mix Vercel's minimalism with Linear's purple accents"
"Show me this dashboard in Apple style vs Tesla style"
```
The agent will:
1. Fetch the brand's design tokens (colors, typography, spacing, radius, shadow, motion).
2. Apply them as CSS custom properties on `:root`.
3. Reference them consistently throughout the component tree.
Example of brand tokens applied as CSS custom properties:
```html
<style>
:root {
/* Stripe-inspired tokens */
--color-primary: #635bff;
--color-primary-dark: #4b44cc;
--color-surface: #ffffff;
--color-surface-alt: #f6f9fc;
--color-text: #0a2540;
--color-text-muted: #425466;
--color-border: #e3e8ee;
--radius-md: 8px;
--radius-lg: 12px;
--font-sans: 'Inter', system-ui, sans-serif;
--shadow-card: 0 4px 24px rgba(10,37,64,0.08);
}
</style>
```
---
## Export Scripts
### HTML → PPTX
```bash
node ~/.claude/skills/cc-design/scripts/gen_pptx.js \
--input ./output/deck.html \
--output ./output/deck.pptx
```
### HTML → PDF
```bash
node ~/.claude/skills/cc-design/scripts/open_for_print.js \
--input ./output/prototype.html \
--output ./output/prototype.pdf
```
### HTML → Single Inline File
Embeds all linked CSS, JS, and images as base64 data URIs:
```bash
node ~/.claude/skills/cc-design/scripts/super_inline_html.js \
--input ./output/prototype.html \
--output ./output/prototype.standalone.html
```
---
## Playwright Verification
After every build step, take a screenshot and check for console errors:
```javascript
// Playwright verification snippet (used by the agent internally)
const { chromium } = require('playwright');
(async () => {
const browser = await chromium.launch();
const page = await browser.newPage();
const errors = [];
page.on('Related in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".