fx-orbit

Make social-post cards orbit the speaker in 3D on a talking-head video. Thumbnails and posts circle their torso, slide behind their body and pass in front of it. Renders an MP4 for Reels, TikTok or Sh

SKILL.md

GitHub

Video Studio: run every command from the Video Studio folder; ENGINE is engines/video-fx/engine (set up already: node "engines/video-fx/engine/fx.mjs" doctor should be all ✔). These lines win over the steps below where they differ:

  • Footage from a studio job: the source is jobs/<id>/source.*. Put configs and renders in jobs/<id>/fx/ (<effect>.json, <Effect>.mp4), never next to the original.
  • Never transcribe again. Before the first still or render of a range: node studio/words-convert.mjs video-fx projects/<id>/transcript/words.json jobs/<id>/fx/words-<start>-<end>.json <start> <end>, then add --words jobs/<id>/fx/words-<start>-<end>.json (same --start/--end) to every still/render of that range. To pick moments, read projects/<id>/transcript/words.json instead of fx.mjs words. Use words (Whisper small on CPU) only for a video that isn't a studio job.
  • Brand: captions use the brand purple, not gold/yellow: every config gets "captions": {"accent": "#C4B5FD"} (plus any style/y settings), the same block in every segment of one video. Graphics that take a colour use styles/brand.json (accent #8B5CF6, accentLight #C4B5FD, accentDeep #4C1D95).
  • Content: headlines, checklist items, chart labels and phone messages come from what Bryan actually says or the Content OS script's cue tags; real numbers only. Generic app mockups only, never posing as a real company's product.
  • Deliver: the spliced full video goes to jobs/<id>/preview.mp4 (review) or final.mp4 (approved); log each effect with its time range in edits.json so the review page can take notes on it. Sounds: these renders have none; add them after with studio/sfx.mjs like any style.
  • If doctor shows ✖: in engines/video-fx/engine: npm install; uv venv .venv --python 3.12 + uv pip install --python .venv/Scripts/python.exe -r requirements.txt; the matting model into models/ (URL in engines/video-fx/install.mjs); node fx.mjs browser. Don't run install.mjs (it copies these skills into ~/.claude/skills).
  • Licences: Remotion is free for companies of up to 3 people; the cut-out model (Robust Video Matting) is GPL-3.0 and is downloaded, never committed.

Orbit — Claude Video FX 01/17

Six small portrait cards circle the speaker's chest on a tilted ring: Reel thumbnails with a white title chip and a ▷ view count, plus white text posts. The speaker is cut out of the shot, so cards on the far side slide behind their body while near cards pass in front, bigger and brighter. Far cards are smaller, darker and slightly soft. The cards whip in at the start and settle into a slow spin. Captions show a small white setup line with the key word in gold italic serif with sparkles.

This effect cuts the speaker out of the background (person matte, cached after the first run). Output: 1080×1920, 30 fps H.264 MP4 with the original audio.

When to use it

  • Social proof: past videos, results, testimonials, press mentions.
  • Listing many things ("all these tools", "every platform") while the speaker talks.
  • An eye-catching hook in the first two seconds.

The engine

Every Claude Video FX skill renders through one local Remotion engine:

ENGINE="engines/video-fx/engine"

The first time in a session, run node "$ENGINE/fx.mjs" doctor. If any line shows ✖, stop and follow the setup steps in the video-fx skill (or tell the user to run the kit installer). Never edit files inside the engine to make a single video work; everything is controlled through the config JSON.

Workflow

  1. Read the video. node "$ENGINE/fx.mjs" words "<video>" prints a timestamped transcript of the whole file (cached); add --detail for every word's start → end. Pick the 3–12 second stretch the user means, or the one this effect suits best. Snap the range to speech: start ~0.1s before its first word, end ~0.2s after its last word, so nothing is clipped.
  2. Decide the deliverable.
    • The clip is the moment → render that range and deliver the MP4.
    • A moment inside a longer video → render the moment's range, then put it back with splice (step 7) and deliver the full video (mention the segment file too). If the range ends before the video does, add "window": [0, <range length − 0.4>]: the effect has fully left by the window end, so keep that after the last word the graphics belong to. Captions must match the rest of the video: either caption everything (render the captions effect over the whole file with the same "captions" block as this config and splice into that render) or set "captions": {"enabled": false} here and splice into the original. The video-fx skill covers multi-effect videos.
  3. Write the config as <video name> - orbit.json next to the video (or in the folder the user names). The engine never modifies the source video; every output is a new file. Repair misheard names with "fixes" (e.g. {"cloud code": "Claude Code"}).
  4. Check one frame before the full render: node "$ENGINE/fx.mjs" still orbit "<video>" --start <s> --end <s> --config "<config.json>" --at <seconds into the clip> --out "<folder>/check.png" then look at the PNG. The first still or render of a new range also makes the transcript and the cut-out (about 1s of processing per 9 frames, cached per exact --start/--end, so settle the range first); after that, it's fast. The CLI prints where every "@word" lands — fix any line marked ! (word not found, default time used).
  5. Render: node "$ENGINE/fx.mjs" render orbit "<video>" --start <s> --end <s> --config "<config.json>" --out "<folder>/<video name> - Orbit.mp4"
  6. Review: node "$ENGINE/fx.mjs" sheet "<output.mp4>" --fps 4 writes <output>-sheet.png next to the MP4 (use --fps 2 for clips over 10s, --from/--to to zoom into a moment). For small text, grab a full-size frame: node "$ENGINE/fx.mjs" frame "<output.mp4>" --at <s>. Re-render if anything is off.
  7. Splice (moments inside a longer video): node "$ENGINE/fx.mjs" splice "<video>" --segments "<segment.mp4>@<start s>" --out "<folder>/<video name> - edited.mp4". It re-encodes the whole video to high-quality H.264 under the original (first) audio track.
  8. Tell the user the output path(s), the time range used and what the effect shows.

--start/--end cut the source down to that range (times in seconds of the original file); everything in the config is relative to the start of that range. "window": [from, to] (seconds into the range) runs the effect for only part of it, with untouched footage outside. Add --draft for a quick half-resolution preview.

Options

Option Default What it does
cards "auto" "auto", or a list of cards: {"src": "path/to/image-or-video", "title": "chip text", "views": "1.2M", "style": "reel" | "post"}. Every field is optional; a card without src shows a still of the clip
count 6 number of auto cards (3-9)
titles "auto" "auto" (phrases from the transcript), "none", or a list of title strings for the auto cards
views true true to show view counts on auto cards, false to hide them
at 0 when the cards fly in (seconds or "@word")
outAt null optional: when the cards fly away (null = stay; they leave automatically if the effect window ends before the clip)
speed 0.16 orbit speed in turns per second (0.16 = one lap every ~6s)
direction 1 1 = counter-clockwise seen from above (front cards move right), -1 = the other way
phase 0 starting angle in radians (rotate the ring so a favourite card starts in front)
radius 0.4 horizontal radius of the orbit as a fraction of the frame width
tilt 0.065 vertical radius (how tilted the ring looks) as a fraction of the frame height
height 0.42 where the ring sits on the body: 0 = face, 1 = bottom of the person (0.42 ≈ chest)
center "auto" "auto" or [x, y] fractions to place the ring centre yourself
cardSize 0.17 card width as a fraction of the frame width (front cards)
depthBlur 1.6 blur in px on the farthest cards
captionPlacement "auto" "auto" (above the head if there is room, else below the ring) or "keep" (use captions.y)

Run node "$ENGINE/fx.mjs" info orbit to print these with the full default config.

Writing the config

  • Best: real media. Put the user's screenshots, thumbnails or short clips in cards as file paths, e.g. [{"src": "~/Desktop/thumb1.png", "title": "1M views", "views": "1.2M"}]. Use 4–8 cards. Every field is optional.
  • Without media, the auto cards show stills of the clip itself. Give them titles that say something (results, topics, hooks from the transcript), 2–5 words each.
  • speed 0.1–0.2 turns per second. Slower reads better when the cards carry text.
  • height moves the ring on the body: 0.3 is the shoulders, 0.6 is the waist. On a wide shot of a seated person, 0.5 matches the reference reel.
  • Set captions.emphasis to the word that should turn gold. Only one gold word per phrase shows.

Example

Line: "The video that you're currently watching was edited completely using Claude Code."

{
  "count": 6,
  "titles": ["Edited with Claude Code", "No editor needed", "Raw clip to finished reel", "Auto captions", "Motion graphics", "Ready to post"],
  "speed": 0.14,
  "captions": { "emphasis": ["watching", "Claude"] }
}

Captions

Captions are on by default, word by word, timed from the transcript. Put caption settings under "captions" in the config. This effect's defaults: style serif, centred at 70% of the frame height.

Option Default What it does
enabled true false hides captions (or pass --no-captions)
style "serif" pop white bold words with a coloured key word · caps ALL CAPS · twoTier small line + one huge key word · serif small line + big gold italic serif word with sparkles · tracked small wide-spaced caps · box words on black chips, key word on a yellow chip
y 0.7 vertical centre of the caption, 0 = top, 1 = bottom
emphasis "auto" "auto" highlights the strongest word per phrase, "none", or a list like ["course", "editing"]
accent "#FFE14D" colour of highlighted words
size 64 font size in px at 1080 wide
maxWords / maxChars 4 / 22 how much text one caption phrase holds
uppercase false force capitals

Timing references

Any option that takes a time accepts seconds from the start of the range (1.5), seconds before the end (-1), or a spoken word: "@course" (first time it is said in the range), "@course#2" (second time), "@course+0.3" / "@course-0.2" (offset), "@course:end" (when it finishes), "@build_your_own" (a phrase; underscores for spaces). Matching ignores case and punctuation, runs after fixes, and falls back to "starts with" ("@edit" finds "editing"). Words are counted within the rendered range only. A word that isn't found silently uses the effect's default time, so read the timing lines the CLI prints.

Getting it right

  • In close-up framing, the back half of the ring hides behind the body. That's correct. For the classic look, use a wider shot where the person is smaller in frame.
  • Cards briefly cross-fade at the sides of the ring, where they switch from behind to in front. A low speed makes that read as a smooth pass.
  • Card text is small, so keep titles under about 25 characters.
  • Captions place themselves above the head on wide shots and below the ring on close-ups. Set "captionPlacement": "keep" plus captions.y to force a position.
  • If the effect window ends before the clip, the cards fly away on their own. Use outAt to send them off earlier.
  • The cut-out follows the person. Things in front of them (a mic, a hand passing over the mic) can partly stay or partly vanish for a few frames; pick a range where the hands are clear if it matters.
  • If the render fails, read the error: "Video not found" means a bad path; "Matting model missing" or Python errors mean the install is incomplete (run doctor); a timeout usually means the machine is overloaded, so render again with fewer apps open.