Motion Overlays logo

Motion Overlays

Community
appariciojunior
motion-overlays

Brand motion graphics for creator videos - a Remotion component kit (key phrases, lists, lower thirds, journeys, big words…) timed to the creator's words from a beats sheet, rendered as transparent ProRes and placed on V2+ in DaVinci Resolve, with face-safe and caption-safe layouts. Use for "overlays", "motion graphics", "make it interesting", "graphics", or when overlays cover the face or fight the captions.

Overview

Publisherappariciojunior
Repositoryvideo-editor-skills
Skill namemotion-overlays
Stars
360
Forks
50
Bundled files
Instructions only
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 appariciojunior on GitHub. Read the source before you install it.

Installation

Install the Motion Overlays 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/appariciojunior/video-editor-skills/tree/main/skills/motion-overlays
  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/appariciojunior/video-editor-skills.git /tmp/video-editor-skills
mkdir -p .claude/skills
cp -r /tmp/video-editor-skills/skills/motion-overlays .claude/skills/motion-overlays
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Motion Overlays 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 Motion Overlays 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 Motion Overlays 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.

Motion overlays (Remotion kit)

The creator's cut is approved and usually re-edited by them. You add graphics on top; their picture and audio are never touched.

The kit

A Remotion project with one composition (Beat) that renders any component from props, at the timeline's size and fps, transparent. Components read every value from a brand tokens file (brand.json: colours, fonts, sizes at a 1080-high unit, padding, motion timings) so the look changes in one place. Typical set:

ComponentUse for
LowerThirdname + role, first appearance
KeyPhrasethe sentence that carries a point (*word* = highlighter)
ListReveal / Flowitems or steps appearing as they're said
Compare / BeforeAftertwo sides, a change
CountUpa number they say
Quote / PersonalNotea strong line, an opinion
BigWordone idea, full frame, 1–2 s
CommentPrompta question for the comments
VlogOpener, PlaceTime, Journey, TimeJumpvlog moments: title, where/when, travel A → B, "3 hours later"
TitleCard / EndCard / ChapterTagstructure, only if asked

Motion that creators liked: one smooth ease-in-out move per element, glide in, hold, glide out. No pop, no bounce. Light or regular weights at big sizes, monospace uppercase labels, generous padding.

Each time

  1. Which timeline (never the template).
  2. Map words → frames on that timeline (walk V1 items: source in-point, timeline start → every kept word's timeline time).
  3. Plan beats and propose them (time · component · copy), wait for OK. Roughly one every 30–60 s. Copy = their words, numbers exactly as said, names checked on the web, nothing invented, nothing they want secret, the right story direction (a trip to somewhere vs. going back).
  4. beats.json: id, component, at_word (or at_seconds on B-roll, where there are no words), end_word / seconds, data with at_word cues for items.
  5. Render (transparent ProRes 4444; full-frame components are large, several GB for ~16 beats), check, then place on the first free track from V2 up.
  6. Overlay SFX: off by default unless the creator likes them (subtle whoosh at most).

Check over the real frame before placing (non-negotiable)

Grab the frame under each beat from the camera file, render the overlay still, composite them, and look. Also draw the caption band on it. We caught all of these only this way:

  • Face: panels designed for 16:9 (right third free) covered the face in a 4:3 selfie frame. Fix in the kit: when the frame is narrower than 16:9, scale side panels as a whole to the outer ~34% of the width, 80 px from the edge, and scale full-frame type to its 16:9 proportions so it stays below the chin.
  • Overflow: an 11-item list didn't fit until scaled; more than ~11 items needs another layout.
  • Captions: bottom-anchored elements (opener, big word, lower third, journey) sat in the subtitle band. Fix in the kit: a token like caption_band_top_at_1080 and every bottom offset = max(own, band top).
  • Widows: a highlighted word followed by "." wrapped the dot onto its own line. Fix in the kit: glue punctuation to the highlight's last word (nowrap) and use text-wrap: pretty on display text.

Fix layout problems in the kit, never per video, so every future video inherits the fix.

Replacing beats

Change the beat, render under a new id/filename (-v2), remove your old clip, place the new one. Re-running must skip beats already placed and never re-add something the creator deleted without saying so.

Report

One line per beat (time, component, on-screen copy), what you fixed in the kit, and anything tight (small text, near the face).

Frequently asked questions

What does the Motion Overlays AI skill do?

Brand motion graphics for creator videos - a Remotion component kit (key phrases, lists, lower thirds, journeys, big words…) timed to the creator's words from a beats sheet, rendered as transparent ProRes and placed on V2+ in DaVinci Resolve, with face-safe and caption-safe layouts. Use for "overlays", "motion graphics", "make it interesting", "graphics", or when overlays cover the face or fight the captions.

Why use Motion Overlays on TypingMind?

Because you install it once and use it with any model. Motion Overlays 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 Motion Overlays in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/appariciojunior/video-editor-skills/tree/main/skills/motion-overlays. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Motion Overlays?

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 Motion Overlays?

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

Is the Motion Overlays AI skill free?

It is published on GitHub by appariciojunior. Check the repository for licensing terms. 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 👇