Communitygithub.com

appariciojunior/video-editor-skills

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.

What is video-editor-skills?

video-editor-skills is a Claude Code agent skill that 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.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/appariciojunior/video-editor-skills/tree/HEAD/skills/motion-overlays

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

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).

Individual skills in this repo

This repo contains 3 individual skills — each has its own dedicated page.

Related Skills