Og Image logo

Og Image

Community
roslove44
og-image

Creates an Open Graph image (social share preview) optimized for BrandArtisan. Use when the user wants an "og image", a "share image", or an "Open Graph / Twitter / LinkedIn / Discord" preview for a project. Produces a 1200x630 .tsx template aligned with the brand guidelines, rendered as a light PNG through the project's Satori engine. Requires a project with its brand.md in place.

Overview

Publisherroslove44
Repositorybrand-artisan
Skill nameog-image
Stars
5
Forks
0
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by roslove44 on GitHub. Read the source before you install it.

Installation

Install the Og Image 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/roslove44/brand-artisan/tree/main/skills/og-image
  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/roslove44/brand-artisan.git /tmp/brand-artisan
mkdir -p .claude/skills
cp -r /tmp/brand-artisan/skills/og-image .claude/skills/og-image
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Og Image 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 Og Image 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 Og Image 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.

og-image: optimized Open Graph image

Goal: produce the PNG asset of a share image (1200×630), through the project's pipeline (Satori -> resvg), aligned with the guidelines. BrandArtisan generates the image only; the og:/twitter: tags live on the site that hosts it.

This is a specialization of new-template with the OG constraints hard-coded. Same conventions: the Template contract (from brand-artisan), assets through brand(), fonts discovered in fonts/, export default ... satisfies Template.

0. Prerequisites (blocking)

The chain project -> template folder -> guidelines must exist before you start. Do not begin until it does:

  • Resolve <project> (from the arguments, otherwise ask).
  • Check templates/<project>/ and brands/<project>/brand.md.
  • If the guidelines or the project are missing -> STOP: ask the user to run /new-project <project> first. No visual without guidelines (CLAUDE.md rule).

1. Frame it

  • <name> is a kebab-case slug, default og (or og-<page> if there are several previews). Check that templates/<project>/<name>.tsx does not exist.
  • Read brands/<project>/brand.md: palette (hex), type, which logo variant to use depending on the background, and the don'ts.
  • Read brands/<project>/project.md if it exists: set the tone and the claims (don't invent figures or promises). If absent -> ask for the tone and the message rather than guessing.
  • Ask for the message: short headline + tagline (1 sentence). No paragraph.

2. OG constraints (to respect in the template)

  • Exact size 1200×630 (1.91:1 ratio). The standard recognized by Facebook, LinkedIn, Slack, Discord and X. Do not deviate; absolute minimum 600×315.
  • Opaque background, never transparency: the platforms compose the image over varied backgrounds.
  • Safe area of roughly 80 px of margin: keep the logo and the text towards the center. The corners can be cropped or rounded (Discord, X), so nothing important goes in them.
  • Legible when small: the preview often displays about 400 px wide on mobile. Large headline (~60–90 px), short tagline, strong contrast. Mental test: still legible once shrunk to 400 px wide.
  • Light weight: aim for < 300 KB. Beyond that, some consumers (WhatsApp in particular) do not generate the preview. The engine's flat rendering is naturally light: favor the mark as an SVG data-URI (as og.tsx does), avoid embedding large raster PNGs, and don't inflate with scale: leaving scale out (= 1) is enough at 1200×630 for OG.
  • PNG: that is the engine's output, ideal for crisp text.

3. Write the template

templates/<project>/<name>.tsx, with colors as constants taken from the guidelines (invent nothing). Skeleton:

tsx
import type { ReactNode } from "react";
import { brand, type Template } from "brand-artisan";
// import { readFile } from "node:fs/promises"; // if you load the mark (SVG/PNG)

const SIZE = { width: 1200, height: 630 }; // OG standard, no scale

// <Project> guideline palette (from brands/<project>/brand.md).
const INK = "#......";

// const markSvg = await readFile(brand("<project>/favicon/icon.svg"));

function render(): ReactNode {
  return (
    <div
      style={{
        width: "100%",
        height: "100%",
        display: "flex",
        flexDirection: "column",
        justifyContent: "center",
        padding: 80, // safe area
        backgroundColor: INK, // opaque background
      }}
    >
      {/* logo + large headline + short tagline, strong contrast */}
    </div>
  );
}

export default { size: SIZE, title: "<Human title>", render } satisfies Template;

Keep the code minimal (principle #2): factor out a background effect locally only if it repeats.

4. Verify

  • npm run typecheck -> green.
  • npm run build -> writes out/<project>/<slug>.png.
  • Check the PNG: dimensions 1200×630, opaque background, weight < 300 KB (beyond that, warn and lighten: drop a heavy raster, lower a scale).
  • Preview: npm run dev then /<project>/<name>; check legibility by mentally shrinking to about 400 px.

Success criterion: a 1200×630 PNG, opaque, under 300 KB, legible when small, and using only the colors and type from brand.md except where the user says otherwise.

Frequently asked questions

What does the Og Image AI skill do?

Creates an Open Graph image (social share preview) optimized for BrandArtisan. Use when the user wants an "og image", a "share image", or an "Open Graph / Twitter / LinkedIn / Discord" preview for a project. Produces a 1200x630 .tsx template aligned with the brand guidelines, rendered as a light PNG through the project's Satori engine. Requires a project with its brand.md in place.

Why use Og Image on TypingMind?

Because you install it once and use it with any model. Og Image 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 Og Image in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/roslove44/brand-artisan/tree/main/skills/og-image. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Og Image?

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 Og Image?

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

Is the Og Image AI skill free?

Yes. It is published on GitHub by roslove44 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 👇