Facebook Page logo

Facebook Page

Community
roslove44
facebook-page

Creates the visuals for a Facebook Page (profile photo = the brand, and cover photo) at Facebook's official dimensions. Use when the user wants a "Facebook profile photo", a "Facebook cover", a "Facebook page banner" or "the FB page logo" for a project. Produces one or two .tsx templates at the sizes Facebook imposes (profile 320x320, cover 851x315), aligned with the brand guidelines, rendered as PNGs through the project's engine. Requires a project with its brand.md in place.

Overview

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

Use it in TypingMind

Enable Facebook Page 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 Page 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 Page 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-page: visuals for a Facebook Page

Goal: produce the PNG assets of a Facebook Page at the official dimensions (source: Facebook help page 125379114252045), aligned with the guidelines. Two possible visuals, independent of each other:

  • profile photo: for an organization, this is the brand (320x320, cropped to a circle by Facebook);
  • cover photo: the Page's tall banner (851x315).

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.

0. Prerequisites (blocking)

The chain project -> template folder -> guidelines must exist before you start:

  • 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 visual(s)? Ask: profile, cover, or both. Don't guess if the user did not say.
  • Default slugs: facebook-profile (320x320) and facebook-cover (851x315). Check that the target .tsx does not exist.
  • Read brands/<project>/brand.md: palette (hex), type, the logo / favicon variants and their rules depending on the background, and the don'ts.
  • If the project already holds a .tsx, read it as a style reference and match its conventions (colors as constants, background effects kept local).

2. Facebook constraints (to respect in the template)

Facebook's official dimensions (do not deviate):

Profile photo

  • Size 320x320 (square) for optimal quality. scale: 2 is possible for a crisper render (Facebook resamples anyway).
  • Cropped to a circle by Facebook: the visual is square but displays round. Nothing important in the corners (they get cut). Opaque full-bleed background, brand centered.
  • It displays small (176 px on desktop, 196 px on mobile, 36 px on basic mobiles): for an organization, use the mark alone / the favicon, not the full wordmark, which would become illegible. Follow brand.md for the variant and the background.

Cover photo

  • Size 851x315 (recommended, sRGB). Absolute minimum 400x150. Don't go below it.
  • Safe area: the center. Facebook crops the sides on mobile (a 2.4:1 format, so roughly 48 px trimmed from each side) and the desktop display is 16:9. Keep text and logo inside, with a side margin of at least ~60 px.
  • Dead zone bottom left (profile photo): on the page, the avatar covers the bottom left of the cover, so any text or logo falling there is hidden. Leave it clear: left margin ~2.5 % of the width, box ~11 % W × ~23 % H anchored bottom left. On 851×315: roughly x 22→116, y 243→315.
  • Opaque background, never transparency.

Format and weight (both)

  • PNG: Facebook recommends PNG as soon as there is a logo or text (crisper than JPG), which is exactly what the engine outputs.
  • < 100 KB for the cover (faster loading). Flat rendering is naturally light: favor the mark as an SVG data-URI, avoid embedding a large raster PNG, don't inflate with scale.

3. Write the template(s)

templates/<project>/<slug>.tsx, with colors as constants taken from the guidelines (invent nothing). Keep the code minimal (principle #2).

Profile (skeleton)

tsx
import { readFile } from "node:fs/promises";
import type { ReactNode } from "react";
import { brand, type Template } from "brand-artisan";

const SIZE = { width: 320, height: 320 }; // FB profile, cropped to a circle (scale:2 possible)

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

// A mark suited to a small round display (the favicon), not the wordmark.
const markSvg = await readFile(brand("<project>/favicon/icon.svg"));
const markSrc = `data:image/svg+xml;base64,${markSvg.toString("base64")}`;

function render(): ReactNode {
	return (
		<div
			style={{
				width: "100%",
				height: "100%",
				display: "flex",
				alignItems: "center",
				justifyContent: "center",
				backgroundColor: BRAND, // opaque full-bleed background (the circle)
			}}
		>
			{/* mark centered, nothing in the corners (outside the circle) */}
			<img src={markSrc} width={188} height={188} alt="" />
		</div>
	);
}

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

Cover (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

const SIZE = { width: 851, height: 315 }; // FB cover (recommended)

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

// Safe area: ~60px side margin (2.4:1 mobile crop), bottom-left corner left clear
// (the profile photo covers it).
const SAFE_X = 60;

function render(): ReactNode {
	return (
		<div
			style={{
				width: "100%",
				height: "100%",
				display: "flex",
				flexDirection: "column",
				justifyContent: "center",
				paddingTop: 40,
				paddingBottom: 40,
				paddingLeft: 200, // leaves the bottom-left corner to the profile photo
				paddingRight: SAFE_X,
				backgroundColor: INK, // opaque background
			}}
		>
			{/* logo + short standfirst, inside the safe area */}
		</div>
	);
}

export default { size: SIZE, title: "<Project> Facebook cover", 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.

4. Verify

  • npm run typecheck -> green.
  • npm run build -> writes out/<project>/<slug>.png.
  • Check each PNG: exact dimensions (320x320 / 851x315), opaque background, < 100 KB for the cover.
  • Profile: mentally check the circular crop (nothing important in the corners) and legibility at about 36 px.
  • Cover: check that nothing important sits in the bottom-left corner or in the ~60 px side margins.
  • Preview: npm run dev then /<project>/<slug>.

Success criterion: PNGs at Facebook's exact dimensions, opaque, cover under 100 KB, brand (not wordmark) legible when small for the profile, safe area respected for the cover, and using only colors and type from brand.md.

Appendix: putting the visuals on the Page

Out of the repo's scope (BrandArtisan only makes the image). On the Facebook side:

  • Profile photo: Page settings -> Profile photo; check the round rendering and the crop it proposes.
  • Cover photo: add the banner; Facebook offers to reposition it; confirm that the text stays visible on mobile (the sides) and that the profile photo hides nothing important in the bottom left.

Frequently asked questions

What does the Facebook Page AI skill do?

Creates the visuals for a Facebook Page (profile photo = the brand, and cover photo) at Facebook's official dimensions. Use when the user wants a "Facebook profile photo", a "Facebook cover", a "Facebook page banner" or "the FB page logo" for a project. Produces one or two .tsx templates at the sizes Facebook imposes (profile 320x320, cover 851x315), aligned with the brand guidelines, rendered as PNGs through the project's engine. Requires a project with its brand.md in place.

Why use Facebook Page on TypingMind?

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

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

Which AI models can use Facebook Page?

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 Page?

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

Is the Facebook Page 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 👇