← Back to Skills Marketplace
xianhaocao

awesome-demo-web-build

by xianhaocao · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
108
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install awesome-demo-web-build
Description
AI-native web demo project generator using Project Blueprint system. Use when user wants to "build a demo", "create a web project", "generate a landing page"...
README (SKILL.md)

AI Web Demo Builder

Interaction Style

Must use selection + free-input for all questions.

  • Show selectable options first
  • Always allow custom input as alternative
  • Ask one question at a time
  • Use numbered choices for easy selection

Phase 1: Project Type

Please select a project type:

# Type Description
1 AI Tool ChatGPT, Claude, AI assistant
2 Dashboard Analytics, admin panel
3 Landing Page Product homepage, landing page
4 SaaS App Notion, Linear multi-module app
5 Content Site Blog, documentation site
6 Tool JSON formatter, image processor
7 E-commerce Online shop, shopping cart
8 Community Forum, social community
9 Marketplace Two-sided marketplace

Enter a number or describe your requirements:


Phase 2: Pages

Please select pages (multiple choice, comma-separated):

Display corresponding pages list based on type:

AI Tool: /chat, /history, /settings, /new Dashboard: /dashboard, /analytics, /reports, /[table] SaaS App: /dashboard, /[module], /settings, /profile Landing Page: / (single page) Content Site: /, /blog, /blog/[slug], /docs, /search

Enter numbers, multiple selections, or describe:


Phase 3: Components

Please select core components (multiple choice):

Display corresponding components list based on type:

Example - AI Tool:

# Component Description
1 ChatInput AI input box
2 ChatMessage Message bubble
3 ChatStream Streaming output
4 ConversationList History list
5 ModelSelector Model selector

Enter a number or describe the components you need:


Phase 4: UI Library

Please select a UI component library:

# UI Library Description
0 Use recommended shadcn/ui + Tailwind (default)
1 shadcn/ui Highly customizable, Radix-based
2 Chakra UI Fast prototyping, theme system
3 Mantine Full-featured, modern feel
4 Ant Design Enterprise admin, strict规范

Enter a number or specify another:


Phase 5: Design Style

Please select a design style:

Method 1: Choose from 57 presets

# Design Description
1 claude Claude AI style
2 linear Linear dark & minimal
3 stripe Stripe light & business
4 openai OpenAI style
5 vercel Vercel minimalist
... Others 52 Full list

Method 2: Provide a reference URL/screenshot

Paste a URL or upload a screenshot, I will analyze and match the closest design style.

Method 3: Custom description

Describe the visual style you want, I will generate a DESIGN.md based on your description.

Enter a number, URL, or describe:


Phase 6: Icon Library

Please select an icon library (optional):

# Icon Library Description
0 Use recommended Lucide React (default)
1 Lucide React Modern & minimal, default option
2 Iconfont Alibaba icon set, custom icons
3 Heroicons Tailwind official icons
4 Phosphor Icons Rich & diverse
5 No icons needed -

Enter a number or specify another:


Project Summary (Confirmation)

Project Type: [type]
Pages: [pages]
Components: [components]
UI Library: [ui-library]
Design Style: [design]
Icon Library: [icon-library]

Scaffolding Command:
[command]

Is this correct? Enter "confirm" to start generating, or tell me what needs to be modified.

Phase 7: Generate Project

After confirmation, execute:

Step 1: Scaffolding

npx create-next-app@latest my-project --typescript --tailwind --app --src-dir
cd my-project
npx shadcn@latest init
npx shadcn@latest add [components]
npm install [dependencies]

Step 2: Inject DESIGN.md

  • WebFetch to get URL from design-catalog.md
  • Write DESIGN.md to project root directory

Step 3: Generate Code

  • Generate components based on blueprint
  • Follow best-practices.md

Output Structure

/project-name
├── app/                    # Next.js pages
├── components/
│   └── ui/                 # shadcn components
├── lib/                    # utils
├── DESIGN.md               # ← Injected design spec
├── tailwind.config.ts      # ← Applied design tokens
└── package.json

Reference Files

File Purpose
references/templates.md Blueprint definition (pages, components, scaffolding)
references/design-catalog.md 57 design style URL mappings
references/best-practices.md Tech stack best practices
references/tech-catalog.md Tech documentation URL mappings

Key Principles

  • Selection + Free-input — Options first, but allow custom input
  • One question at a time — Only ask one dimension at a time
  • Confirmation before generate — Generate only after confirmation
  • DESIGN.md lives in project — Read design specs during AI coding
  • Use scaffolding CLI — Don't generate from scratch
Usage Guidance
This skill appears to be a legitimate web-project scaffolding guide, but take precautions before running the generated commands: - The SKILL.md assumes you have node/npm/npx and network access; the skill metadata does not declare these requirements — install or confirm Node.js tooling first. - The scaffolding commands run npx/npm which will download packages from npm and other registries. Inspect the generated package.json and node_modules before running or deploying the project. - The skill fetches DESIGN.md files from raw.githubusercontent.com and suggests adding remote icon JS from at.alicdn.com; those external resources will be embedded in your project and may execute remote code at runtime. Prefer to review the downloaded DESIGN.md and avoid embedding remote script tags unless you trust the source. - If you plan to run this on a sensitive machine or in CI, run the scaffold in an isolated/containerized environment, and review all fetched files and added dependencies. If you want higher assurance, ask the publisher for explicit declarations of required binaries (node/npm), pinned package versions, and an allowlist of remote hosts the skill will fetch from.
Capability Analysis
Type: OpenClaw Skill Name: awesome-demo-web-build Version: 1.0.1 The skill bundle is a web project generator that scaffolds Next.js applications by executing shell commands (npx, npm) and fetching external design specifications. While these capabilities are aligned with its stated purpose, the process involves using WebFetch to retrieve Markdown files from a third-party GitHub repository (VoltAgent/awesome-design-md) which are then used to guide the AI's code generation logic (SKILL.md, Phase 7). This creates a significant attack surface for indirect prompt injection, where malicious content in the remote design files could influence the generated code or agent behavior. No evidence of intentional malice was found, but the high-risk combination of shell execution and untrusted remote content fetching warrants a suspicious classification.
Capability Tags
crypto
Capability Assessment
Purpose & Capability
The skill's name/description (generate web demo projects) matches the instructions (use npx create-next-app, shadcn, install dependencies, inject DESIGN.md). However the skill declares no required binaries or environment variables even though the runtime instructions assume node/npm/npx, and network access to fetch external DESIGN.md and npm packages — a mismatch that should have been declared.
Instruction Scope
SKILL.md stays within the stated purpose (scaffold a project, inject design spec, generate components). It instructs the agent to perform network fetches (WebFetch) of DESIGN.md from raw.githubusercontent.com and to write DESIGN.md into the project root. Those are reasonable for the task but they permit downloading external content into generated projects and adding remote script tags (iconfont/Alibaba CDN), which increases supply‑chain/runtime risk.
Install Mechanism
There is no formal install spec (instruction-only), which minimizes direct disk changes by the skill itself. But the scaffolding commands invoke npx/npm which will download packages from public registries and third‑party CDNs at runtime — normal for scaffolding, but still a supply‑chain vector. The external sources used (npm packages, raw.githubusercontent.com, at.alicdn.com) are public and common, but the skill does not document or vet specific package versions.
Credentials
The skill requests no credentials or environment variables. That is proportionate to its purpose. There is no attempted access to unrelated config paths or secrets in SKILL.md. (Note: some recommended stacks may later require user credentials, e.g., Supabase or Stripe, but those are not requested by the skill itself.)
Persistence & Privilege
always:false and no install hooks are present. The skill does not request persistent presence, does not modify other skills, and does not declare self-elevation. It writes files into the scaffolded project only after explicit confirmation per the instructions.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install awesome-demo-web-build
  3. After installation, invoke the skill by name or use /awesome-demo-web-build
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- English localization: All user prompts and phase instructions in SKILL.md are now in English. - No functional changes—flow, process, and logic remain the same as before. - Added `.claude/settings.local.json` (for local configuration; does not affect public functionality).
v1.0.0
awesome-demo-web-build 1.0.0 - Initial release of an AI-native web demo project generator using a Project Blueprint system. - Features a step-by-step interactive flow: project type, page selection, component selection, UI & icon libraries, design style, and project confirmation. - Supports selection plus free-input for all configuration steps, always showing selectable options and allowing custom input. - Generates Next.js scaffolded projects with customizable UI (shadcn, Chakra UI, Mantine, AntD) and design system injection. - Outputs a consistent project structure with embedded design guidelines (DESIGN.md). - Reference files catalog best practices, template blueprints, and design options.
Metadata
Slug awesome-demo-web-build
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is awesome-demo-web-build?

AI-native web demo project generator using Project Blueprint system. Use when user wants to "build a demo", "create a web project", "generate a landing page"... It is an AI Agent Skill for Claude Code / OpenClaw, with 108 downloads so far.

How do I install awesome-demo-web-build?

Run "/install awesome-demo-web-build" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is awesome-demo-web-build free?

Yes, awesome-demo-web-build is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does awesome-demo-web-build support?

awesome-demo-web-build is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created awesome-demo-web-build?

It is built and maintained by xianhaocao (@xianhaocao); the current version is v1.0.1.

💬 Comments