Remotion Video logo

Remotion Video

CommunityPopular
TechNomadCode
remotion-video

Make a short video about a product or brand (promo, launch, explainer, demo or social clip) entirely in code with Remotion, from idea to a rendered MP4 with sound. The owner approves the idea and a storyboard before anything is built.

Overview

PublisherTechNomadCode
RepositoryAI-Product-Development-Toolkit
Skill nameremotion-video
Stars
1K
Forks
169
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Remotion Video 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/TechNomadCode/AI-Product-Development-Toolkit/tree/main/agent-skills/remotion-video
  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/TechNomadCode/AI-Product-Development-Toolkit.git /tmp/AI-Product-Development-Toolkit
mkdir -p .claude/skills
cp -r /tmp/AI-Product-Development-Toolkit/agent-skills/remotion-video .claude/skills/remotion-video
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Remotion Video 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 Video 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 Video 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.

Make a short video about the owner's product or brand, entirely in code with Remotion: picture, sound and the final MP4. The work follows brief.md in this skill's folder. If the file is missing, tell the owner to install the skills again.

The owner answers at two points with "go" or what to change. Build nothing before the first go.

1. Proposal, then wait

  • If the current folder has a BRIEF.md, this is a revision of an earlier video. Read it, propose only the changes the owner asked for, and keep the rest.
  • If the owner gave you their own filled brief, use it. Otherwise, fill in brief.md yourself.
    • Use what the owner named: a link, a folder or a product.
    • If they named nothing, read the current folder: README, site copy, logo, colours and fonts.
    • If there's nothing to read, ask one question: "What's the video for? Paste a link, a folder path or one sentence."
  • Reply with these items, each kept short, in under ten lines in total. Skip intros and extra sections:
    • Product: what it is and who it's for, in one sentence.
    • Kind: promo, launch, explainer, demo or social clip, taken from the owner's request. If the request doesn't say, use a promo.
    • Idea: two or three sentences on how it opens, what happens and how it ends. The story shows what the product does for someone.
    • Look and sound: one sentence.
    • Format: length, size and frame rate.
    • New lines: any on-screen line that isn't from the owner's own material, or "none".
    • License: what Remotion's license means for the owner, with the link. Check its official license page first; don't answer from memory.
    • Add one more line only if something blocks the idea, for example missing or low-quality assets.
  • End with "Go?". Install nothing and create no files before the answer.

2. Storyboard, then wait

  • Set up a Remotion project. If the current folder is empty, use it. Otherwise create a new folder next to the product's project. Save the filled brief in it as BRIEF.md, so later changes start from it.
  • Before writing Remotion code, check its current docs for the installed version.
  • Use one timing file for both picture and sound.
  • Render 6–8 key frames onto one sheet. Caption each frame with one line about what you see and hear. Send the sheet and end with "Go?".

3. Film

  • Build the film the brief describes. Make the sound in code: effects and ambience, timed from the same timing file. Use no synthetic voice and no music unless the owner asks for them or provides them.
  • Check before delivery:
    • Go through the brief's "Before it's done" list.
    • Step through the frames around every transition. Nothing should pop, jump or vanish between frames.
    • Do a cold read. If you can delegate, have one reviewer who hasn't seen your notes watch a contact sheet as a first-time viewer and say what they understood. Otherwise, do it yourself. Fix whatever confuses them. Run a bigger review only if the owner asks.
    • The MP4 has the expected frame count and resolution. Its audio track is as long as the picture and in sync. Loudness is about -16 LUFS, with true peaks below -1 dBTP.
  • Deliver what the brief's "Hand-over" lists, plus what you couldn't check. Always say that nobody has listened to the sound.

Rules

  • Show what the product does for a person. Don't recreate its website or app screens, and don't list features.
  • Keep only a few words on screen at a time. Keep the product name and address on screen for at least 2 seconds.
  • Every visual must make sense to someone who has never heard of the product. If a metaphor needs explaining, replace it.
  • Let the story set the length. Don't rush beats to hit a number.
  • When the owner asks for changes, keep everything they didn't mention. Never overwrite an earlier render; save the new one alongside it.

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 Video AI skill do?

Make a short video about a product or brand (promo, launch, explainer, demo or social clip) entirely in code with Remotion, from idea to a rendered MP4 with sound. The owner approves the idea and a storyboard before anything is built.

Why use Remotion Video on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TechNomadCode/AI-Product-Development-Toolkit/tree/main/agent-skills/remotion-video. 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 Video?

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 Video?

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

Is the Remotion Video AI skill free?

Yes. It is published on GitHub by TechNomadCode 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 👇