God Social Media

Community

cumabozkurt

god-social-media

Social media design at exact platform specs - Instagram (feed 4:5, square, Stories/Reels 9:16, carousel), TikTok, YouTube (thumbnails, banners, Shorts), Facebook, LinkedIn, X/Twitter, Pinterest, Threads, Bluesky, Snapchat, WhatsApp, Telegram - with safe zones, carousel storytelling, thumbnail psychology, templates and HTML/SVG export recipes. Use for any social post, story, ad creative, cover, banner, avatar or thumbnail.

Overview

Publisher	cumabozkurt
Repository	`god-of-design`
Skill name	`god-social-media`
Stars	7
Forks	1
Bundled files	2
License	MIT
Links	Skill source Repository Homepage

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 cumabozkurt on GitHub. Read the source before you install it.

Installation

Install the God Social Media AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/cumabozkurt/god-of-design/tree/main/skills/god-social-media
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.

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-social-media .claude/skills/god-social-media

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable God Social Media 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 Social Media 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 Social Media 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 Social Media

Procedure

Platform + format + goal. For example: "Instagram carousel, 1080×1350, goal: saves". Load the exact spec from references/platform-specs.md.
Safe zones. Keep text and faces out of UI overlays (9:16 formats: top ~250px and bottom ~340px on a 1920px-high canvas, plus a right-side action rail on TikTok/Reels). Profile-photo crops are circular.
Thumb-stopping hierarchy: one idea per frame, readable at phone size (the headline must work at ~30% scale), a big contrast focal point, and a face or object for emotion.
Type minimums on a 1080px-wide canvas: headline ≥ 64px, body ≥ 32px, captions ≥ 28px. Max ~20–25 words per frame.
Brand consistency: same grid, type and colour system across a series. Vary the layout within the system.
Export: PNG for graphics and text (sRGB), JPG ≥ 85% quality for photos, MP4 H.264 + AAC for video (30 fps, ≤ the platform bitrate). Name files platform_format_campaign_v1.png.
Accessibility: alt text, captions, sufficient contrast, camelCase hashtags.

Carousel storytelling (Instagram / LinkedIn)

Hook frame: a bold promise or question, plus a visual cue to swipe (→, a cut-off element crossing the edge).
Frames 2…n-1: one point each, consistent position for headline and number (2/8).
Last frame: summary + CTA ("Save this", "Follow for part 2").

Design continuous panoramas by building one wide canvas (e.g. 5400×1350 for 5 frames) and slicing it into 1080px-wide frames.
LinkedIn carousels are uploaded as PDF documents (each page = one slide). Use 1080×1350 or 1080×1080 pages.

YouTube thumbnail formula

1280×720 (16:9), < 2MB (JPG/PNG/GIF/WEBP). Use 1 face with a clear emotion + 1 object + ≤ 4 words in huge type. High contrast between subject and background. Avoid the bottom-right corner (timestamp overlay). Test at 168×94px: it must still read.

Generation recipes

HTML/CSS → PNG: build a fixed-size <div style="width:1080px;height:1350px">, then screenshot it with Playwright: npx playwright screenshot --viewport-size=1080,1350 file.html out.png (or page.screenshot). See god-output.
SVG: use viewBox="0 0 1080 1350" with embedded fonts or text converted to paths for portability.
Canva: use the exact dimensions as a custom size, or the Canva MCP/Connect API autofill with brand kit (see god-output).
Image generation: state the aspect ratio explicitly (--ar 4:5 Midjourney, aspect_ratio: "9:16" in APIs) and leave negative space for text. Add text afterwards in code, because generated text is often misspelled.

See references/platform-specs.md for all sizes, and references/content-patterns.md for post archetypes.

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 Social Media AI skill do?

Why use God Social Media on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cumabozkurt/god-of-design/tree/main/skills/god-social-media. 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 Social Media?

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 Social Media?

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

Is the God Social Media 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

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Frontend Slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a…

Plan Canvas

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

God Social Media

Procedure

Carousel storytelling (Instagram / LinkedIn)

YouTube thumbnail formula

Generation recipes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now