Oneshot Website logo

Oneshot Website

Community
cafe3310
oneshot-website

Generate immersive, one-shot single-file HTML websites with embedded CSS and JS. No external images. Hostable on CodePen or Vercel. Use for writeup showcases, AI capability demos, and portfolio pieces.

Overview

Publishercafe3310
Repositorypublic-agent-skills
Skill nameoneshot-website
Stars
256
Forks
30
Bundled files
2
LicenseApache-2.0
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.

  • 2 bundled files

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

  • Open source

    Published by cafe3310 on GitHub. Read the source before you install it.

Installation

Install the Oneshot Website 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/cafe3310/public-agent-skills/tree/main/skills_parked/oneshot-website
  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/cafe3310/public-agent-skills.git /tmp/public-agent-skills
mkdir -p .claude/skills
cp -r /tmp/public-agent-skills/skills_parked/oneshot-website .claude/skills/oneshot-website
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Oneshot Website 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 Oneshot Website 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 Oneshot Website 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.

Oneshot Website

Generate a stunning, self-contained single-file HTML website -- fully immersive, scroll-driven, cinematic. No external images, no build step. Drop into CodePen or push to Vercel as-is.

Inspired by high-end digital brand experiences and the kind of creative coding that makes people say "this was done in one shot?"

When to invoke

Use when:

  • Demonstrating an LLM's creative + technical range for writeups or articles
  • Creating a stunning demo to embed in a CodePen
  • Producing a portfolio piece or proof-of-concept landing page
  • Showing off one-shot generation capabilities

The Generation Prompt

When this skill is invoked, generate the full HTML file using this master approach:


Write complete HTML, CSS, and JavaScript in a single self-contained file for an immersive, cinematic website about [THEME].

The site must feel like a living brand experience -- sections that breathe as you scroll, typography that has weight and presence, and atmosphere you can almost feel.

Theme Selection

If no theme is specified, choose one from the repertoire in references/themes.md that hasn't been recently used. Never default to clockwork, clocks, or time-perception themes.

Recommended defaults (rotate through these):

  1. Elegant restaurant storefront -- dark marble, candlelight, menu sections appearing like courses being served
  2. Luxury perfume house -- mist particles, scent notes drifting, amber and obsidian palette
  3. Antiquarian bookshop at night -- warm amber light, floating text fragments, vellum textures in CSS
  4. Deep sea research station -- bioluminescent creatures via canvas, pressure gauge UI, midnight blue
  5. Jazz club and vinyl lounge -- smoke rings via SVG, waveform visualizations, sepia and amber

Technical Constraints (NON-NEGOTIABLE)

  • Single file: All HTML, CSS, JS in one .html file
  • No external images: Use CSS gradients, SVG inline art, Canvas API, or unicode/emoji symbols only
  • No CDN dependencies for core visuals (Google Fonts via @import is acceptable)
  • No frameworks: Vanilla JS only. No React, Vue, Alpine, etc.
  • Static: Must work as a static file (no server-side logic)
  • Self-hostable: Drop into Vercel as index.html or paste into CodePen

Quality Bar

This is NOT a simple landing page. It should feel like it was commissioned by a world-class brand agency. Include:

Visual craft:

  • Scroll-triggered reveals with Intersection Observer (not scroll events -- use IO for performance)
  • Parallax depth on at least 2 layers (background moves slower than foreground)
  • Typography that has character -- mix of serif and sans, large display type with tight tracking
  • Color palette of 3-4 tones maximum, applied with intention (not rainbow)
  • Subtle animated texture or grain overlay via CSS (repeating SVG noise, pseudo-element with opacity)

Interaction:

  • Cursor that responds subtly (not gimmicky -- a small dot or trail at most)
  • Hover states that feel intentional (transforms, not just color changes)
  • At least one section with a scrolling marquee or horizontal text ticker
  • Navigation that changes opacity/style on scroll

Atmosphere:

  • Hero section with large, centered typographic statement
  • At minimum 5 distinct sections with scroll transitions between them
  • Footer with subtle details (coordinates, a fictional address, a motto in a second language)
  • A moment of surprise -- one section that does something unexpected (inverted colors, a canvas animation, text that rearranges)

Polish details:

  • font-display: swap on any web fonts
  • will-change: transform on animated elements
  • Smooth scroll behavior on html
  • Mobile-responsive (flexbox/grid, no fixed px widths on containers)
  • prefers-reduced-motion media query to disable animations for accessibility

Output Format

Produce two files:

1. PROMPT.md -- the exact one-shot prompt that will be used to generate this site.

2. index.html -- the complete single-file website. Start with <!DOCTYPE html> and end with </html>. No explanation before or after the HTML.

Format of PROMPT.md:

markdown
# One-Shot Prompt

**Theme**: [theme name]
**Generated**: [date]
**Model**: [model name and version]

## Prompt

[The complete verbatim prompt that would reproduce this exact site if fed to any capable LLM fresh]

## Notes

- [Any notable techniques used]
- [Hosting: CodePen / Vercel / local]

Name fictional brands with restraint: evocative, not punny. Think: "Maison Vorieux", "Sublevel 7", "The Meridian Press", not "Tasty Bistro" or "Cool Restaurant".


Hosting

CodePen

  1. Create new Pen
  2. Paste entire contents into the HTML panel
  3. Enable "Full Page" view

Vercel

bash
mkdir my-site && cd my-site
# save as index.html
vercel --prod

Local preview

bash
open index.html   # macOS
# or
python3 -m http.server 3000

Example Output Names

The generated site should have a real name. Examples by theme:

ThemeBrand NameTagline
RestaurantMaison VorieuxFine dining, honest cooking
PerfumeAtelier ObscurScent as memory
BookshopThe Meridian PressEst. 1887
Deep SeaSublevel 7Research below the thermocline
JazzThe Amber RoomLive music every Thursday
BotanicalSelva StudioPlants for considered spaces
MineralCabinet BrutSpecimen traders since 1952
ObservatoryStation NuitWatching since 1901
Night MarketHawker's AlmanacEvery dish has a story

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 Oneshot Website AI skill do?

Generate immersive, one-shot single-file HTML websites with embedded CSS and JS. No external images. Hostable on CodePen or Vercel. Use for writeup showcases, AI capability demos, and portfolio pieces.

Why use Oneshot Website on TypingMind?

Because you install it once and use it with any model. Oneshot Website 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 Oneshot Website in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cafe3310/public-agent-skills/tree/main/skills_parked/oneshot-website. 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 Oneshot Website?

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 Oneshot Website?

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

Is the Oneshot Website AI skill free?

Yes. It is published on GitHub by cafe3310 under the Apache-2.0 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 👇