Agent skill

Remotion Assemble

by notivn in notivn/AIEV

How to use Remotion as the assembly layer - read the project's meta.json and stitch the rendered HyperFrames scenes + footage + voice + sound effects into the finished video.

MITAuto-check passedMedia & Creative

Install Remotion Assemble

skills CLI
$ npx skills add notivn/AIEV --skill remotion-assemble -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install notivn/AIEV remotion-assemble --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/notivn/AIEV.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/remotion-assemble .claude/skills/remotion-assemble && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
remotion-assemble
GitHub stars
127
Token cost
~2.4k tokens
SKILL.md length
996 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

How to use Remotion as the assembly layer - read the project's meta.json and stitch the rendered HyperFrames scenes + footage + voice + sound effects into the finished video.

  • Works in 3 steps: Dimensions/fps come from the manifest -… → Embedded video uses , not - it is more… → Timeline = accumulating durationInFrames
  • Tasks that involve Video production
  • SKILL.md covers Structure of engines/remotion, Core principles, Draft vs Final and Known issues & how to avoid them, plus 1 more section
  • Calls npx, ffprobe and ffmpeg

What it does

Remotion Assemble is an agent skill from notivn/AIEV. How to use Remotion as the assembly layer - read the project's meta.json and stitch the rendered HyperFrames scenes + footage + voice + sound effects into the finished video. Read this when writing/editing code in engines/remotion or when assembling the timeline for a video.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Video production and Motion graphics. It works with Remotion and HeyGen. The repository describes itself as: Automatic AI video editing. Claude directs HyperFrames (HTML + GSAP motion graphics) and Remotion (timeline assembly) to turn raw footage into a finished MP4 - transcript… The licence is MIT.

When your agent uses it

  • Tasks that involve Video production
  • Tasks that involve Motion graphics

Example prompts

  • “/remotion-assemble”

Requirements

  • Node.js

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Dimensions/fps come from the manifest - use calculateMetadata to set width/height/fps/durationInFrames dynamically from the props, never…
  2. Embedded video uses , not - it is more stable server-side and lands on the right frame. Whatever fps a HyperFrames scene was rendered at…
  3. Timeline = accumulating durationInFrames

What it can do on your machine

Read from SKILL.md and the folder at commit e40fe03. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx
    • ffprobe
    • ffmpeg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Remotion Assemble loads about 2.4k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 996 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from notivn/AIEV at commit e40fe03, republished under its MIT licence (© notivn). 996 words, ~2,420 tokens.

Download SKILL.mdSave it as .claude/skills/remotion-assemble/SKILL.md (or your agent's skills folder).
name
remotion-assemble
description
How to use Remotion as the assembly layer - read the project's meta.json and stitch the rendered HyperFrames scenes + footage + voice + sound effects into the finished video. Read this when writing/editing code in engines/remotion or when assembling the timeline for a video.

Remotion Assemble - building the timeline from meta.json

In this system Remotion does exactly one thing: assemble the pieces that already exist (scene MP4s rendered by HyperFrames, source footage, voice, sound effects) into the final video. Do not build motion graphics in Remotion - that is HyperFrames' job.

Structure of engines/remotion

engines/remotion/
├── package.json          ← remotion, @remotion/cli, @remotion/renderer
├── remotion.config.ts
└── src/
    ├── Root.tsx               ← registers 3 compositions: "Assemble" + "Poster" + "Thumbnail"
    ├── Assemble.tsx           ← master composition: read manifest → build timeline
    ├── Poster.tsx             ← static poster composition (image projects)
    ├── Thumbnail.tsx          ← static video-thumbnail composition (frame card + title)
    ├── manifest.ts            ← load + validate video props (zod)
    ├── posterManifest.ts      ← load + validate poster props (zod)
    ├── thumbnailManifest.ts   ← load + validate thumbnail props (zod)
    ├── brandFonts.ts          ← load brand fonts via staticFile (offline)
    ├── index.ts               ← entry point registering Root
    └── components/
        ├── SceneClip.tsx      ← <OffthreadVideo>/<Img> for one scene/footage clip
        ├── Transition.tsx     ← hard cut / crossfade (fade) - only these 2
        ├── SfxTrack.tsx       ← places <Audio> at sfx[].atFrame
        ├── MusicTrack.tsx     ← background music: loop + fade + deterministic ducking
        ├── CaptionTrack.tsx   ← karaoke captions from word timestamps
        ├── HighlightTrack.tsx ← main/related key bands (key-layout)
        └── vietnameseFont.ts  ← @font-face Inter vietnamese subset

Manifest fields beyond scenes/captions/overlays (see manifest.ts):

  • watermark - the Style Design corner logo, stamped by the SERVER (jobs/assemble.ts), never by the AI; null = the style has no logo.
  • audio.music - background music { file, volume, duckVolume, speech: [[startSec,endSec],...] } with deterministic ducking over speech ranges (see the background-music skill); null = no music.
  • scenes[].zoom - camera move on footage { origin?, keys: [{frame, scale, ease?}] }; frame counts from the START OF THE SCENE, applied to the wrapper div (never the video element).
  • audio.sfx[].mediaStart - seconds skipped at the head of the sfx file (lead silence trim, see noti-tiktok-vn "SFX loudness and lead silence").

Core principles

  1. A single data-driven Assemble composition. Everything comes from the project's meta.json, passed through defaultProps/inputProps. Adding a new video means no Remotion code changes, only a new manifest.
bash
npx remotion render Assemble \
  --props="<abs>/video-projects/<name>/props.resolved.json" \
  --output="../../outputs/<name>-v1.mp4" \
  --concurrency 8 --gl angle

⚠️ Asset paths in the props must be staging/... - the backend stages assets into engines/remotion/public/staging/ via hardlinks and then writes props.resolved.json. NEVER render straight from meta.json (its paths are relative to the project folder, and Remotion cannot resolve those through staticFile).

--gl angle is MANDATORY on a machine with a GPU - without it Remotion renders with the software renderer, CPU at 100% and GPU at 5%. For drafts add --crf 28 --x264-preset veryfast. (The backend queue adds these flags automatically.)

  1. Dimensions/fps come from the manifest - use calculateMetadata to set width/height/fps/durationInFrames dynamically from the props, never hardcode them in Root.tsx.

  2. Embedded video uses <OffthreadVideo>, not <Video> - it is more stable server-side and lands on the right frame. Whatever fps a HyperFrames scene was rendered at, the manifest must declare that exact fps; an fps mismatch between scene and composition is the number one source of stuttering.

  3. Timeline = accumulating durationInFrames:

tsx
let from = 0;
scenes.map((s) => {
  const seq = (
    <Sequence key={s.id} from={from} durationInFrames={s.durationInFrames}>
      <SceneClip scene={s} />
    </Sequence>
  );
  from += s.durationInFrames - (s.transitionOverlap ?? 0);
  return seq;
});

When a transition has an overlap, subtract that overlap while accumulating - forgetting to subtract leaves a black gap between scenes.

  1. Audio:

    • Voice: one <Audio src={voice}> running from frame 0 - the voice is the sync backbone, scenes follow the voice and never the other way round.
    • Sound effects: each sfx[] entry becomes one <Sequence from={atFrame}><Audio volume={0.3}/></Sequence>. Default sfx volume is 0.3 (~10dB below the voice); override it in the manifest with the volume field if needed.
    • Do not normalize/mix manually with FFmpeg after rendering - mix inside Remotion so the draft sounds like the final.
  2. Caption and overlay tracks live in meta.json, and their timestamps are in FRAMES.

    CaptionTrack and HighlightTrack read props.captions / props.overlays only. They never open a transcript file. If you leave those arrays empty there are no captions, no matter how good the transcript is.

jsonc
// meta.json
"captions": [
  { "from": 90, "durationInFrames": 75,
    "words": [ { "text": "Trí", "start": 90, "end": 96 },
               { "text": "tuệ", "start": 96, "end": 104, "hi": true } ] }
],
"overlays": [
  { "from": 0, "durationInFrames": 150, "tier": "main", "accent": "hot",
    "kicker": "AI", "parts": [ { "t": "Dựng video" }, { "t": "bằng AI", "hi": true } ] }
]

⚠️ The unit changes here. A transcript stores start/end in seconds; captions[].words[] stores them as absolute composition frames (second * fps, counted from the start of the whole video, not from the start of the cue). Passing seconds through produces captions that all flash in the first half-second — and nothing errors, so it is easy to ship by accident.

hi: true marks a highlighted word. tier: "main" renders a top band, "sub" a bottom pill that lifts itself when captions are present.

  1. Every scene needs durationInFrames unless it is a srcVideo scene with both from and to. That is the only case Remotion infers a length for; an image or HyperFrames scene without an explicit durationInFrames throws at render time. This bites hardest on videos with no source footage (text-to-video, image-only explainers), where nothing has a natural duration to infer from.

  2. Asset paths: Remotion code only loads through staticFile() - the backend stages assets into engines/remotion/public/staging/<project>/ (hardlink) and writes the staging/... path into props.resolved.json; Remotion never reads an absolute path. This runs on Windows - always use path.join on the backend, never string concatenation.

Show full SKILL.md (352 more words)Show less

Draft vs Final

DraftFinal
Command--crf 28 --x264-preset veryfast (+ --concurrency 8 --gl angle)defaults (crf 18)
Scene inputrenders/*.draft.mp4renders/*.mp4 (quality standard)
Purposereview pacing, sync, transitionspublishing

The backend picks the scene input set based on the job type - the Remotion code does not distinguish draft from final, it only takes the paths from the manifest.

Known issues & how to avoid them

  • Stutter/freeze at a scene boundary: the scene fps differs from the composition fps, or durationInFrames in the manifest does not match the real length of the MP4. Check with ffprobe -show_streams <file> before assembling.
  • Audio drifting out of sync toward the end: a VBR voice mp3 -> convert it to CBR/WAV before putting it in the manifest (ffmpeg -i voice.mp3 -ar 48000 voice.wav).
  • Color mismatch between HyperFrames scenes and footage: both engines render through Chromium so they usually match; if they do not, check whether the footage has an unusual color space tag (bt709 is the standard) - transcode the footage to bt709 first.
  • Render hanging on Windows: usually caused by Vietnamese characters/spaces in an asset file path - name asset files in ASCII kebab-case right from the import step.
  • One black frame at every footage cut: a srcVideo scene sized round((to-from)*fps) while OffthreadVideo plays round(to*fps) - round(from*fps) frames - the two differ by one (from=1.02, to=3.98 @30fps: 89 vs 88). Always round EACH END, never the difference; resolveSceneDurationInFrames and frameOf in jobs/assemble.ts must stay in lockstep with SceneClip.
  • Whole render dies on one tiny cue (inputRange must be strictly monotonically increasing): a fade written as [0, 4, max(5, last-4), last] is not increasing when a cue is 6 frames or less (a translated cue clamped near the end of the video is enough). Use fadeInOut() from components/fade.ts for any new track instead of hand-writing the range.
  • Rendering on a machine with no network: Remotion tries to download Chrome from remotion.media. Pass --browser-executable=<local chrome/headless_shell> instead.

Remotion license (keep in mind when scaling up)

Remotion is free for individuals and companies of <= 3 people; beyond that you need a Company License. This note is for planning growth - it does not affect the current stage.

© notivn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/remotion-assemble of notivn/AIEV.

Open the folder on GitHubat commit e40fe03

Compare with similar skills

Remotion Assemble next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Remotion Assemble compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Remotion Assemble this skillnotivn/AIEV127—~2.4kAutomated safety check: PassMIT
HyperFrames Video Entry Pointheygen-com/hyperframes60k3 repos~5.2kAutomated safety check: PassApache-2.0
Remotion to HyperFrames Porterheygen-com/hyperframes60k3 repos~2.8kAutomated safety check: PassApache-2.0
Reference Video Replica QcPluviobyte/video-production-skills671—~1.8kAutomated safety check: PassNone
Black White Text OpenerPluviobyte/video-production-skills671—~1kAutomated safety check: PassNone
Remotion To Hyperframeschmonitor/chmonitor3001 repos~2.5kAutomated safety check: PassGPL-3.0

Similar skills

  • HyperFrames Video Entry Point

    heygen-com/hyperframes

    Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.

    60k GitHub starsUsed in 3 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Remotion to HyperFrames Porter

    heygen-com/hyperframes

    Ports an existing Remotion (React) composition to HyperFrames HTML with GSAP, one way, and grades the result against a tiered set of reference fixtures.

    60k GitHub starsUsed in 3 repos~2.8k tokens
    Media & CreativeAuto-check passed
  • Reference Video Replica Qc

    Pluviobyte/video-production-skills

    Analyze, recreate, align, and verify reference-video motion.

    671 GitHub stars~1.8k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Black White Text Opener

    Pluviobyte/video-production-skills

    Create reusable black-background white-text opening animations for new videos.

    671 GitHub stars~1k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Remotion To Hyperframes

    chmonitor/chmonitor

    Port an existing Remotion (React) composition to HyperFrames HTML.

    300 GitHub starsUsed in 1 repo~2.5k tokens
    Media & CreativeAuto-check passed
  • Super Video Maker

    Bomx/super-video-maker-skill

    End-to-end AI video production skill for agentic frameworks.

    310 GitHub stars~11k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes

More from notivn/AIEV

All 14 skills in this repo
  • Background Music

    notivn/AIEV

    Pick background music from the assets/music/ library and configure auto-ducking (music dips automatically under speech) via meta.json audio.music for the Remotion assembly layer.

    127 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Color Grading

    notivn/AIEV

    Color grading video in the AI Edit Video system - delog/tonemap HDR-HLG-log footage, apply the color preset the user approved in the UI, and the visual verification workflow.

    127 GitHub stars~932 tokensUpdated today
    Auto-check passed
  • Build a Vietnamese vertical TikTok explainer in the "MỔ XẺ PAPER AI" (AI paper dissection) format with HyperFrames (HTML/CSS/GSAP → MP4), Noti.vn style.

    127 GitHub stars~4.8k tokensUpdated today
    Auto-check passed
  • Skill Authoring

    notivn/AIEV

    The standard for writing new skills for the AI Edit Video system - file structure, frontmatter, tone of voice, and how to accumulate production lessons into skills.

    127 GitHub stars~925 tokensUpdated today
    Auto-check passed
  • Noti Tiktok Vn

    notivn/AIEV

    Edit a Vietnamese vertical TikTok video (9:16) with HyperFrames following the Noti.vn/GĐT standard - talking-head + kinetic typography + karaoke captions + zoom/punch-in camera + timestamp-synced…

    127 GitHub stars~5.4k tokensUpdated today
    Auto-check passed
  • Build a Vietnamese landscape 16:9 YouTube video (1920×1080) with HyperFrames (HTML/CSS/GSAP → MP4), keeping the Noti.vn/GĐT branding inherited from noti-tiktok-vn.

    127 GitHub stars~5.7k tokensUpdated today
    Auto-check passed

Works with

Questions about Remotion Assemble

What does Remotion Assemble do?

How to use Remotion as the assembly layer - read the project's meta.json and stitch the rendered HyperFrames scenes + footage + voice + sound effects into the finished video. Remotion Assemble is an agent skill from notivn/AIEV.json and stitch the rendered HyperFrames scenes + footage + voice + sound effects into the finished video.

When should I use Remotion Assemble?

Remotion Assemble fits situations like: tasks that involve Video production; tasks that involve Motion graphics.

How do I install Remotion Assemble in Claude Code?

Run `npx skills add notivn/AIEV --skill remotion-assemble -a claude-code`. Or copy the skill folder (.claude/skills/remotion-assemble in notivn/AIEV) into .claude/skills/remotion-assemble in your project. Claude Code loads it when a task matches its description.

How do I install Remotion Assemble in Codex?

Run `npx skills add notivn/AIEV --skill remotion-assemble -a codex`. Or copy the skill folder (.claude/skills/remotion-assemble in notivn/AIEV) into .agents/skills/remotion-assemble in your project. Codex loads it when a task matches its description.

Can I use Remotion Assemble in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add notivn/AIEV --skill remotion-assemble -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/remotion-assemble, .gemini/skills/remotion-assemble, .github/skills/remotion-assemble and .opencode/skills/remotion-assemble in your project.

What does Remotion Assemble need to run?

Going by SKILL.md and its folder, Remotion Assemble needs the command-line tools its instructions call (npx, ffprobe and ffmpeg). Our summary lists: Node.js.

Does Remotion Assemble access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Remotion Assemble safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Remotion Assemble use?

Remotion Assemble is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Remotion Assemble use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Remotion Assemble?

Skills that share tags, products or a category with Remotion Assemble: HyperFrames Video Entry Point (heygen-com/hyperframes, 60k stars), Remotion to HyperFrames Porter (heygen-com/hyperframes, 60k stars), Reference Video Replica Qc (Pluviobyte/video-production-skills, 671 stars) and Black White Text Opener (Pluviobyte/video-production-skills, 671 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Remotion Assemble?

notivn (a GitHub organization) maintains it in notivn/AIEV, which has 127 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 9, 2026.

Source: notivn/AIEV on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.