Agency Socials logo

Agency Socials

Community
glebis
agency-socials

Generate social media covers and assets for AGENCY Community events, meetups, and YouTube recordings. Use when creating event covers, YouTube thumbnails, or social posts for the AGENCY Community.

Overview

Publisherglebis
Repositoryclaude-skills
Skill nameagency-socials
Stars
379
Forks
56
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 glebis on GitHub. Read the source before you install it.

Installation

Install the Agency Socials 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.
  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/glebis/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/agency-socials .claude/skills/agency-socials
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agency Socials 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 Agency Socials 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 Agency Socials 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.

AGENCY Community Social Assets Generator

Generate covers and visual assets for AGENCY Community events using the established design system.

Design System

Colors

  • Background: #0f0f0f
  • Frame/borders: #2a2a2a
  • Accent (orange): #e85d04
  • Primary text: #f0f0f0
  • Secondary text: #999
  • Muted text: #555 / #444
  • Grid lines: rgba(42,42,42,0.12)

Typography

  • Title/Header: Geist Bold (700) — large, high-impact headlines
  • Metadata (top bar, bottom bar): JetBrains Mono — monospace, uppercase, letter-spaced
  • Speaker/people names: EB Garamond — elegant serif
  • Handles/technical labels: JetBrains Mono — monospace, orange accent

Font loading

html
<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=EB+Garamond:ital,wght@0,400;0,500;0,600;0,700;1,400;1,500;1,600;1,700&family=JetBrains+Mono:wght@300;400;500&display=swap&subset=cyrillic" rel="stylesheet">
<link rel="preload" href="https://cdn.jsdelivr.net/npm/geist@1.3.1/dist/fonts/geist-sans/Geist-Bold.woff2" as="font" type="font/woff2" crossorigin>
css
@font-face {
  font-family: 'Geist';
  src: url('https://cdn.jsdelivr.net/npm/geist@1.3.1/dist/fonts/geist-sans/Geist-Bold.woff2') format('woff2');
  font-weight: 700;
}

Layout Principles

  • Frame: 1px solid #2a2a2a border, inset 12px from edges
  • Top bar: JetBrains Mono, label left, date/time right (orange)
  • Bottom bar: JetBrains Mono, metadata left and right, uppercase
  • Background grid: subtle 40px grid lines
  • Accent line: 3px orange bar below titles
  • Photos: off-grid placement, fade to background on edges (left, bottom, top), slight scanline effect, fully desaturated grayscale(1) contrast(1.1) brightness(0.95)
  • Text: left-aligned, can overlap photo slightly, large and readable at thumbnail size

Minimum font sizes (must be readable at thumbnail)

  • Top/bottom bar: 13-15px
  • Speaker names: 28px+
  • Handles: 20px+
  • Titles: 62px+ (square), 76px+ (YouTube 16:9)

Asset Sizes

lu.ma Event Cover (square)

  • Dimensions: 800×800px
  • Viewport: --viewport-size="800,800"

YouTube Thumbnail (16:9)

  • Dimensions: 1280×720px
  • Viewport: --viewport-size="1280,720"
  • Style reference: matches lab-meeting.html template in youtube-uploader
  • Uses same design tokens but wider layout

Telegram Post Image

  • Dimensions: 1080×1080px or 1280×720px

Generation Process

  1. Create HTML file at ~/Desktop/agency-{type}-cover.html
  2. Place speaker photo next to the HTML (same directory)
  3. If speaker photo is in clipboard, save with: osascript -e 'set theFile to POSIX file "/path/to/photo.png"' -e 'set theImage to the clipboard as «class PNGf»' -e 'set fileRef to open for access theFile with write permission' -e 'write theImage to fileRef' -e 'close access fileRef'
  4. Render at 2x scale for crisp text using Node.js script:
js
const { chromium } = require('playwright');
(async () => {
  const browser = await chromium.launch();
  const context = await browser.newContext({
    viewport: { width: W, height: H },
    deviceScaleFactor: 2
  });
  const page = await context.newPage();
  await page.goto('file:///path/to/html');
  await page.waitForTimeout(3000);
  await page.screenshot({ path: '/output/path.png', fullPage: true });
  await browser.close();
})();
  1. Review output, iterate on layout

Template Structure

html
<!-- Standard structure for all asset types -->
<body>
  <div class="bg-grid"></div>
  <div class="frame"></div>
  <div class="top-bar">
    <span class="top-left">{event type}</span>
    <span class="top-right">{date · time}</span>
  </div>
  <div class="photo-area"><!-- speaker photo with effects --></div>
  <div class="content">
    <div class="title">{headline with .highlight spans}</div>
    <div class="accent-line"></div>
    <div class="speaker"><strong>{name}</strong> <span class="handle">@{handle}</span></div>
  </div>
  <div class="bottom-bar">
    <span>{format · price}</span>
    <span>agency · community</span>
  </div>
</body>

Photo Effects

  • Fade from left edge: linear-gradient(to right, #0f0f0f, transparent) width 200px
  • Fade from bottom: linear-gradient(to top, #0f0f0f, transparent) height 250px
  • Fade from top: linear-gradient(to bottom, #0f0f0f, transparent) height 80px
  • Scanlines: repeating-linear-gradient(transparent, transparent 2px, rgba(0,0,0,0.05) 2px, rgba(0,0,0,0.05) 4px)
  • Orange accent border on left edge: linear-gradient(transparent, #e85d04, transparent) opacity 0.4
  • Photo filters: grayscale(1) contrast(1.1) brightness(0.95) (fully B&W)
  • Photo positioned off-grid (partially bleeding off right edge)

Example Invocations

  • "Create a cover for the AGENCY meetup with Vlad about browser automation"
  • "Generate a YouTube thumbnail for tonight's meetup recording"
  • "Make a Telegram announcement image for the next community event"

Frequently asked questions

What does the Agency Socials AI skill do?

Generate social media covers and assets for AGENCY Community events, meetups, and YouTube recordings. Use when creating event covers, YouTube thumbnails, or social posts for the AGENCY Community.

Why use Agency Socials on TypingMind?

Because you install it once and use it with any model. Agency Socials 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 Agency Socials in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/glebis/claude-skills/tree/main/agency-socials. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Agency Socials?

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 Agency Socials?

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

Is the Agency Socials AI skill free?

Yes. It is published on GitHub by glebis 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 👇