Remotion Ads logo

Remotion Ads

Community
Maartenlouis
remotion-ads

Professional video ad creation with Remotion — Instagram Reels (9:16), website explainers (16:9), and carousels (4:5). Use when creating video ads, animated social content, or educational explainer videos. Includes ElevenLabs voiceover with word-level captions, AI icon generation, background music, ad copywriting frameworks, and Meta campaign management. Also use when the user provides a URL and wants to create a video for that page.

Overview

PublisherMaartenlouis
Repositoryremotion-ads
Skill nameremotion-ads
Stars
66
Forks
13
Bundled files
29
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.

  • 29 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Remotion Ads 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/Maartenlouis/remotion-ads/tree/main
  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/Maartenlouis/remotion-ads.git \
  .claude/skills/remotion-ads
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Remotion Ads 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 Remotion Ads 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 Remotion Ads 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.

Remotion Ads

Create professional video ads and explainer videos with Remotion, ElevenLabs voiceover, and animated captions.

Setup

  1. Copy references/brand-config-template.md → references/brand-config.md
  2. Fill in brand colors, fonts, voice, caption styling, and content rules
  3. Create pronunciation dictionary from assets/dictionaries/template.pls

See references/setup.md for dependencies and folder structure.


Supported Formats

FormatAspectResolutionDurationScenes
Instagram Reels9:161080×192015-60s4 (Hook→Problem→Solution→CTA)
Instagram Reels (Ohneis)9:161080×192015-45sBeat-driven (word-level)
Website Explainers16:91920×108060-160s6 (Hook→Problem→Context→Solution→Process→CTA)
Carousels4:51080×1350Static5-10 slides

See references/formats.md for safe zones and crop specs. See references/ohneis-style.md for beat-driven cinematic reel template. See references/website-videos.md for 16:9 long-form format.


Workflow

From scratch

bash
# 1. Write scene JSON
# 2. Generate voiceover with word timestamps
node scripts/generate.js \
  --scenes scenes.json \
  --with-timestamps \
  --dictionary your-brand \
  --output-dir public/audio/ad-example/

# 3. Create Remotion composition using actualDuration from info.json
# 4. Render
npx remotion render AdExample out/ad-example.mp4 --codec=h264 --crf=18

From a URL (page → video)

bash
# 1. Extract page data into scene JSON
node scripts/url-to-scenes.js --url https://example.com/page --format reels --output scenes.json
# 2. Review/edit the generated scenes.json
# 3. Continue with voiceover + composition as above

See references/url-to-video.md for the full URL-to-video workflow.


Safe Zones (Critical)

Reels (1080×1920)

┌──────────────────────────┐ 0px
│     TOP DANGER (285px)   │
├──────────────────────────┤
│ ←80px  SAFE AREA  120px→ │
│      880×1235px          │
├──────────────────────────┤
│   BOTTOM DANGER (400px)  │
└──────────────────────────┘ 1920px
tsx
const SAFE = { top: 285, bottom: 400, left: 80, right: 120 };

Website Videos (1920×1080)

tsx
const SAFE = { top: 60, bottom: 60, left: 80, right: 80 };

Scene JSON Format

json
{
  "name": "ad-example",
  "voice": "VoiceName",
  "character": "narrator",
  "dictionary": "your-brand",
  "scenes": [
    { "id": "scene1", "text": "Hook text.", "duration": 3.5, "character": "dramatic" },
    { "id": "scene2", "text": "Problem.", "duration": 4.5 },
    { "id": "scene3", "text": "Solution.", "duration": 4.0, "character": "expert" },
    { "id": "scene4", "text": "CTA.", "duration": 3.0, "character": "calm" }
  ]
}

Voice Character Presets

CharacterStyleStabilitySimilarityStyle Param
dramaticIntense, emotional0.30.80.7
narratorProfessional, smooth0.50.750.4
expertAuthoritative0.60.850.3
calmSoothing, reassuring0.70.80.2
conversationalCasual, friendly0.450.70.5

Composition Template

tsx
import { AbsoluteFill, Audio, Series, staticFile } from "remotion";

// Import from your brand-config.md values
const COLORS = { primary: "#000", accent: "#888", dark: "#111", background: "#fff" };

export const AdTemplate: React.FC = () => {
  const { fps } = useVideoConfig();
  // Use actualDuration from info.json, not estimated
  const DURATIONS = { scene1: 3.42, scene2: 4.35, scene3: 4.12, scene4: 3.31 };
  const pad = 5;

  return (
    <AbsoluteFill>
      <Audio src={staticFile("audio/ad-example/ad-example-combined.mp3")} />
      <Series>
        <Series.Sequence durationInFrames={Math.round(DURATIONS.scene1 * fps) + pad}>
          <Scene1Hook />
        </Series.Sequence>
        {/* ... remaining scenes */}
      </Series>
    </AbsoluteFill>
  );
};

See references/components.md for reusable scene components. See references/voiceover.md for TransitionSeries audio sync.


Reference Files

Load these on demand based on the task:

Core (read first)

FileWhen to read
setup.mdProject initialization
brand-config-template.mdConfiguring brand: colors, fonts, voice, captions, compliance
formats.mdDimension specs, safe zones, crop previews

Video Creation

FileWhen to read
ohneis-style.mdBeat-driven cinematic reel template: mixed-font typography, hard cuts, moody photos
voiceover.mdElevenLabs TTS, models, scene JSON, timing sync, dictionaries
captions.mdAnimated captions: TikTok-style, word-by-word, karaoke
animations.mdSpring configs, transitions, animation components
components.mdReusable scene template components
html-in-canvas.mdRender live DOM into a canvas with 2D filters or WebGL2 shaders (vintage, progressive blur, page-tour mockup)
website-videos.md16:9 long-form format, 6-scene structure
url-to-video.mdCreate videos from existing web pages

Audio

FileWhen to read
sound-effects.mdElevenLabs SFX generation
music.mdBackground music via ElevenLabs or Suno

Assets & Static

FileWhen to read
local-assets.mdBackground images, icons, illustrations
carousels.md4:5 carousel design and batch rendering

Copywriting

FileWhen to read
ad-copywriting.mdScript frameworks, hook formulas, CTA patterns
copy-frameworks.mdHeadline templates, section formulas
natural-transitions.mdHuman-sounding transitions, AI-tell avoidance

Distribution

FileWhen to read
paid-ads.mdMeta campaign strategy, targeting, budgets
social-content.mdContent calendar, repurposing framework

Scripts

ScriptPurpose
scripts/generate.jsElevenLabs voiceover with dictionaries, request stitching (note: --with-timestamps flag is currently a no-op)
scripts/gemini-tts.mjsGemini TTS — single-request generate + silence split with text-proportion boundary picker
scripts/suno-direct.tsSuno background music generation
scripts/url-to-scenes.jsExtract page content into scene JSON

Pre-Upload Checklist

Reels

  • 1080×1920, H.264, 30fps
  • All text within safe zones
  • No content in top 285px or bottom 400px
  • Font sizes ≥ 48px
  • Voiceover synced, captions timed
  • ~15s total duration

Website Videos

  • 1920×1080, H.264, 30fps
  • Font sizes ≥ 36px
  • 60-160s duration
  • 6-scene structure with appropriate voice characters

Carousels

  • 1080×1350, PNG
  • 80px padding from edges
  • 5-10 slides with swipe indicators

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 Remotion Ads AI skill do?

Professional video ad creation with Remotion — Instagram Reels (9:16), website explainers (16:9), and carousels (4:5). Use when creating video ads, animated social content, or educational explainer videos. Includes ElevenLabs voiceover with word-level captions, AI icon generation, background music, ad copywriting frameworks, and Meta campaign management. Also use when the user provides a URL and wants to create a video for that page.

Why use Remotion Ads on TypingMind?

Because you install it once and use it with any model. Remotion Ads 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 Remotion Ads in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Maartenlouis/remotion-ads/tree/main. 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 Remotion Ads?

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 Remotion Ads?

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

Is the Remotion Ads AI skill free?

Yes. It is published on GitHub by Maartenlouis 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 👇