Demo Site Builder logo

Demo Site Builder

Organization
buildfastwithai
demo-site-builder

Build a single-file, self-contained HTML demo/landing website that showcases a GitHub repository's functionality. Use this skill whenever asked to generate a demo site, landing page, showcase page, project website, or interactive demo for a repo. Produces one portable demo.html with no build step and no external dependencies beyond optional CDN assets.

Overview

Publisherbuildfastwithai
Repositorygen-ai-experiments
Skill namedemo-site-builder
Stars
785
Forks
225
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by buildfastwithai on GitHub. Read the source before you install it.

Installation

Install the Demo Site Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/buildfastwithai/gen-ai-experiments/tree/main/mcp/servers/launch-mcp/skills/demo-site-builder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/buildfastwithai/gen-ai-experiments.git /tmp/gen-ai-experiments
mkdir -p .claude/skills
cp -r /tmp/gen-ai-experiments/mcp/servers/launch-mcp/skills/demo-site-builder .claude/skills/demo-site-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Demo Site Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Demo Site Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Demo Site Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Demo Site Builder

Turn a repository analysis into ONE self-contained demo.html that a reader can open in any browser and immediately understand what the project does and why it matters. The page both explains and, where feasible, demonstrates the functionality.

Non-negotiables

  • Single file. Everything — HTML, CSS, JS — lives in one demo.html. No build step, no node_modules, no local asset files.
  • Works offline by double-click. It must render fully when opened directly from disk (file://). Only optional enhancements (a web font, a syntax-highlight CDN, an icon set) may load from a CDN, and the page must still look correct if those fail.
  • Grounded in the analysis. Every feature, number, code sample, and claim comes from the analyze_repo output (description, README, languages, topics, stars, commits). Never invent capabilities, benchmarks, or quotes. If the README shows a real usage snippet, reuse it verbatim.
  • No secrets, no live network calls to the user's services. A demo may simulate behavior in-browser, but must not require API keys or hit private endpoints.

Page structure (in order)

  1. Hero — project name, a one-line tagline distilled from the description, 2-4 badges (language, license, stars, latest version if any), and two buttons: "View on GitHub" (links to the repo URL) and a "See it in action" anchor to the demo section.
  2. Problem → Solution — 1-2 short paragraphs: the problem the repo solves and how it solves it. Pulled from the README intro.
  3. Key features — a responsive grid of 3-6 cards, each with an icon/emoji, a title, and one sentence. Only features evidenced by the analysis.
  4. Live demo or walkthrough — the centerpiece:
    • If the repo is a browser-runnable JS/TS library or produces visual/text output that can be reproduced client-side, embed a genuinely interactive widget (inputs → live result) implemented in inline JS.
    • If it is a CLI, backend, or non-browser tool, build a realistic simulated terminal / API playground: the user clicks example commands and sees representative output (clearly labelled "sample output"), driven by canned data taken from the README. Do not fake success of things you cannot actually run.
    • Always label simulated output honestly.
  5. Usage / code example — the real install + minimal usage from the README, in a styled, copy-to-clipboard code block.
  6. Tech stack — languages (with the analyzed percentages) and notable topics as pills.
  7. Footer — repo link, license, "Generated launch demo" note, contributor credit.

Styling guidance

  • Modern, clean, developer-facing. Default to a dark theme (e.g. #0d1117 bg, #e6edf3 text, an accent like #8b7cf8 or #58a6ff) with a light-mode toggle if cheap to add.
  • System font stack (-apple-system, 'Segoe UI', Roboto, Helvetica, Arial, sans-serif) or a single CDN font with a safe fallback.
  • All CSS in one <style> block. Use CSS variables for colors so the theme is easy to tweak. Generous whitespace, max-width container (~1000-1100px), responsive down to mobile with a single media query.
  • Subtle polish only: a hero gradient, soft card shadows/borders, smooth scroll-behavior, hover states. No heavy animation libraries.
  • Accessible: semantic tags (<header> <main> <section> <footer>), sufficient contrast, alt/aria-label where needed, keyboard-focusable interactive elements.

JavaScript guidance

  • Vanilla JS in one inline <script> at the end of <body>. No frameworks unless the repo itself is a framework you're demoing.
  • Keep interactivity self-contained and deterministic. Guard every CDN-dependent feature so the page degrades gracefully.
  • Copy-to-clipboard on code blocks is a nice, cheap touch.

Output contract

  • Emit the complete demo.html as the deliverable (write it to the output directory). It must be valid, self-contained HTML5 starting with <!DOCTYPE html>.
  • Do not include placeholder lorem ipsum — if the analysis lacks something (e.g. no code sample), omit that piece rather than fabricating it.

Reference

  • references/template.html — a ready starter skeleton (hero, features grid, demo playground, code block, tech pills, footer, dark theme, copy button). Adapt it to the repo; strip sections you can't fill honestly.

Quick checklist before delivering

  1. Opens correctly from file:// with no console errors.
  2. Every claim traces back to the analysis — nothing invented.
  3. Simulated output is clearly labelled as such.
  4. Responsive at mobile width; contrast is readable.
  5. Repo URL is linked in the hero and footer.
  6. It's one file, no external build, CDN assets are optional and gracefully degrade.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Demo Site Builder AI skill do?

Build a single-file, self-contained HTML demo/landing website that showcases a GitHub repository's functionality. Use this skill whenever asked to generate a demo site, landing page, showcase page, project website, or interactive demo for a repo. Produces one portable demo.html with no build step and no external dependencies beyond optional CDN assets.

Why use Demo Site Builder on TypingMind?

Because you install it once and use it with any model. Demo Site Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Demo Site Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/buildfastwithai/gen-ai-experiments/tree/main/mcp/servers/launch-mcp/skills/demo-site-builder. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Demo Site Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Demo Site Builder?

As many as you like. As long as a model supports skills, you can use Demo Site Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Demo Site Builder AI skill free?

Yes. It is published on GitHub by buildfastwithai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇