Facebook Post logo

Facebook Post

Community
roslove44
facebook-post

Creates a Facebook post image (feed post, poster, simple ad visual) at Meta's dimensions, in the chosen orientation. Use when the user wants a "Facebook image", a "Facebook post", a "poster", an "ad visual" or a "publication" for a project. Asks for the orientation (portrait by default, square, landscape) and produces a .tsx template at the right ratio, aligned with the brand guidelines, rendered as a PNG through the project's engine. Requires a project with its brand.md in place.

Overview

Publisherroslove44
Repositorybrand-artisan
Skill namefacebook-post
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 Facebook Post 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/facebook-post
  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/facebook-post .claude/skills/facebook-post
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Facebook Post 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 Facebook Post 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 Facebook Post 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.

facebook-post: Facebook post image

Goal: produce the PNG asset of a Facebook post image (a feed publication, a poster, a simple ad visual), at the chosen Meta ratio, aligned with the guidelines.

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

Status of the dimensions. Meta publishes no dimension spec for organic posts: the figures below come from the Ads Manager specs (Ads Guide + placement pages). Since the feed's rendering engine is the same, that is the best available reference. The ratios are official Meta; for landscape, the pixel figures are a convention (Meta documents no resolution for that ratio).

0. Prerequisites (blocking)

The chain project -> template folder -> guidelines must exist:

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

1. Frame it

  • Which orientation? Ask. Default: portrait (4:5, the best performer in the feed). Otherwise square (1:1) or landscape (1.91:1).
  • Default slug facebook-post (or facebook-post-<orientation> if there are several variants). Check that the target .tsx does not exist.
  • Read brands/<project>/brand.md: palette (hex), type, logo variants 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 + standfirst (1 sentence). No paragraph.
  • If the project already holds a .tsx, read it as a style reference.

2. Facebook constraints (to respect in the template)

Dimensions per orientation

OrientationSize (px)RatioStatus
Portrait (default)1440x18004:5Meta target resolution (min 1080x1350)
Square1080x10801:1Official Meta minimum
Landscape1080x5661.91:1Official ratio; convention pixels (alt 1200x628)
  • Don't use 16:9 in landscape: it is not supported in the Facebook Feed. The supported landscape is 1.91:1.
  • Official minimum width: 600 px. Don't go below it.
  • scale: 2 is possible for a crisper render; unnecessary at the sizes above.

Layout

  • Opaque background, never transparency.
  • Safe area of roughly 80 px of margin: keep the logo and the text towards the center, since the feed may crop slightly and round the corners depending on context.
  • Legible when small: the feed often displays narrow on mobile. Large headline, short standfirst, strong contrast.
  • Meta's old 20 % text rule is gone: there is no text limit, but keep the poster airy and legible.

Format and weight

  • PNG (or JPG): the engine outputs PNG, crisp for text and logos.
  • Meta's maximum weight: 30 MB. Flat rendering is nowhere near that limit, so there is nothing particular to optimize.

3. Write the template

templates/<project>/<slug>.tsx, with colors as constants taken from the guidelines (invent nothing). Pick SIZE according to the orientation. 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)

// Pick according to the orientation:
const SIZE = { width: 1440, height: 1800 }; // Portrait 4:5 (default)
// const SIZE = { width: 1080, height: 1080 }; // Square 1:1
// const SIZE = { width: 1080, height: 566 };  // Landscape 1.91:1

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

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 standfirst, strong contrast */}
		</div>
	);
}

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

Shared conventions: assets through brand("<project>/..."), fonts discovered in fonts/; a missing font -> follow the "missing font" appendix in new-template, never silently. Keep the code minimal (principle #2).

4. Verify

  • npm run typecheck -> green.
  • npm run build -> writes out/<project>/<slug>.png.
  • Check the PNG: exact dimensions for the orientation, opaque background, correct ratio (4:5 / 1:1 / 1.91:1).
  • Preview: npm run dev then /<project>/<slug>; check legibility shrunk to the width of a mobile feed.

Success criterion: a PNG at Meta's dimensions for the chosen orientation, opaque, legible when small, and using only colors and type from brand.md.

Frequently asked questions

What does the Facebook Post AI skill do?

Creates a Facebook post image (feed post, poster, simple ad visual) at Meta's dimensions, in the chosen orientation. Use when the user wants a "Facebook image", a "Facebook post", a "poster", an "ad visual" or a "publication" for a project. Asks for the orientation (portrait by default, square, landscape) and produces a .tsx template at the right ratio, aligned with the brand guidelines, rendered as a PNG through the project's engine. Requires a project with its brand.md in place.

Why use Facebook Post on TypingMind?

Because you install it once and use it with any model. Facebook Post 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 Facebook Post in TypingMind?

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

Which AI models can use Facebook Post?

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 Facebook Post?

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

Is the Facebook Post 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 👇