God Output logo

God Output

Community
cumabozkurt
god-output

Output recipes and handoff - production HTML/CSS, Tailwind, React/Next.js with shadcn/ui, Vue/Svelte notes, SVG graphics, email HTML, rendering HTML/SVG to PNG/PDF (Playwright), image export settings, favicon/OG sets, file naming, and handoff to Figma (variables, auto layout, specs) and Canva (sizes, brand kit, autofill, MCP). Use when turning a design decision into files, choosing an export format, or preparing a design for developers, Figma or Canva.

Overview

Publishercumabozkurt
Repositorygod-of-design
Skill namegod-output
Stars
7
Forks
1
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 cumabozkurt on GitHub. Read the source before you install it.

Installation

Install the God Output 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/cumabozkurt/god-of-design/tree/main/skills/god-output
  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/cumabozkurt/god-of-design.git /tmp/god-of-design
mkdir -p .claude/skills
cp -r /tmp/god-of-design/skills/god-output .claude/skills/god-output
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable God Output 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 God Output 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 God Output 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.

God Output

Choose the format

NeedBest output
Website / landing page prototypeSingle-file index.html with Tailwind (CDN for prototypes, a build step for production) or plain CSS
Production React appReact/Next.js components + Tailwind v4 tokens (+ shadcn/ui primitives when the project uses it)
Social graphic, poster, slide as an imageHTML/SVG at the exact pixel size → PNG via Playwright
Logo, icon, patternHand-written SVG (optimised), plus PNG exports
Print documentSVG/PDF (vector), or HTML with Paged.js/WeasyPrint; final CMYK preflight in pro tools
Deckdeck.html (16:9 sections) or a .pptx spec / python-pptx
EmailTable-based HTML, inline CSS, 600–640px wide, web-safe font fallbacks
Design-tool handoffTokens JSON + specs + assets → Figma variables / Canva brand kit

HTML/CSS baseline (copy into every page)

html
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Specific page title · Brand</title>
<meta name="description" content="One specific sentence.">
<meta property="og:image" content="/og.png"><!-- 1200×630 -->
<link rel="icon" href="/favicon.svg" type="image/svg+xml">
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=...&display=swap" rel="stylesheet">
<style>
  :root { color-scheme: light dark; /* tokens from god-tokens */ }
  *, *::before, *::after { box-sizing: border-box; }
  body { margin: 0; font-family: var(--font-body);
         color: var(--color-text); background: var(--color-bg);
         -webkit-font-smoothing: antialiased; text-rendering: optimizeLegibility; }
  img, svg, video { display: block; max-width: 100%; height: auto; }
  :focus-visible { outline: 2px solid var(--color-focus, currentColor); outline-offset: 2px; }
  @media (prefers-reduced-motion: reduce) {
    *, *::before, *::after { animation-duration: .01ms !important;
      transition-duration: .01ms !important; scroll-behavior: auto !important; }
  }
</style>
</head>
<body>
<a class="skip-link" href="#main">Skip to content</a>
<header>…</header><main id="main">…</main><footer>…</footer>
</body></html>

Tailwind prototypes: <script src="https://cdn.jsdelivr.net/npm/@tailwindcss/browser@4"></script> plus a <style type="text/tailwindcss">@theme { … }</style> block. For production, install tailwindcss with the Vite/PostCSS plugin.

React + shadcn/ui notes

  • Map tokens to shadcn's CSS variables (--background, --foreground, --primary, --primary-foreground, --muted, --border, --ring, --radius) in globals.css. Then restyle. Default shadcn styling with zero changes is a slop tell.
  • Keep components presentational and accept className. Use cva for variants.
  • Use next/font (Next.js) to self-host Google Fonts with zero layout shift.

Render HTML/SVG → PNG/PDF

bash
npx -y playwright@latest install chromium                    # once
# PNG at an exact size (2x scale by default)
node skills/god-output/scripts/render.mjs poster.html poster.png 1080 1350
# PDF, one page per slide/section
node skills/god-output/scripts/render.mjs deck.html deck.pdf 1920 1080

(The script uses Playwright if installed and otherwise prints the manual command.)

Export settings

AssetFormatSettings
UI images/photosAVIF/WebP with JPG fallbackQuality 70–82; srcset 1x/2x; explicit width/height
Graphics with textPNG-24 or SVGsRGB
Social imagesPNG (graphics) / JPG 85–92 (photo)Exact platform size, sRGB, < 8MB
Favicon setfavicon.svg + favicon.ico (32) + apple-touch-icon.png (180) + icon-192.png / icon-512.png (PWA manifest)
OG imagePNG/JPG 1200×630Text ≥ 48px, centred safe area
PrintPDF/X-4 or PDF/X-1aCMYK, bleed, crop marks (pro tool preflight)
VideoMP4 H.264 + AAC1080p, 30fps, platform bitrate limits

File naming: brand_asset_variant_size@scale.ext → godofdesign_logo_horizontal_dark@2x.png.

Figma handoff

  1. Create Variables collections: Primitives (raw colours, spacing), Semantic (roles) with modes Light/Dark, mirroring god-tokens names.
  2. Text styles for each type-scale step; effect styles for shadows.
  3. Components with auto layout (padding = spacing tokens), variants for states, and properties for text/icon toggles.
  4. Frames at real device sizes, layout grids matching god-layout.
  5. Annotate: spacing, behaviour, breakpoints, motion specs (duration/easing), accessibility notes (heading levels, focus order, alt text).
  6. If a Figma MCP/API is available, read existing variables and components first and reuse them. Never duplicate the system.

Canva handoff

  1. Use custom dimensions matching the platform spec (e.g. 1080×1350 px for an IG portrait).
  2. Set up a Brand Kit: logos (SVG/PNG), colours (hex), fonts (upload brand fonts or choose the closest Canva fonts), plus a brand template.
  3. Provide a content sheet (CSV: one row per design, columns per text/image field) for Bulk Create or Autofill (Canva Connect API / Canva MCP autofill-design with a brand template).
  4. Keep text as live text (editable). Avoid flattening into images.
  5. If the Canva MCP is connected: search brand templates → get the dataset (field names) → autofill with your content → export PNG/PDF. Always confirm with the user before publishing or sharing anything.

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 God Output AI skill do?

Output recipes and handoff - production HTML/CSS, Tailwind, React/Next.js with shadcn/ui, Vue/Svelte notes, SVG graphics, email HTML, rendering HTML/SVG to PNG/PDF (Playwright), image export settings, favicon/OG sets, file naming, and handoff to Figma (variables, auto layout, specs) and Canva (sizes, brand kit, autofill, MCP). Use when turning a design decision into files, choosing an export format, or preparing a design for developers, Figma or Canva.

Why use God Output on TypingMind?

Because you install it once and use it with any model. God Output 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 God Output in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cumabozkurt/god-of-design/tree/main/skills/god-output. 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 God Output?

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 God Output?

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

Is the God Output AI skill free?

Yes. It is published on GitHub by cumabozkurt 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 👇