fx-zoom-through-cut

Join two talking-head shots with a whip "zoom-through" transition — the first shot rushes in toward the speaker with a radial zoom blur and a little spin, hard-cuts at the peak, and the second shot bu

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.

Zoom-Through Cut — Claude Video FX 09/17

Over the last ~9 frames of shot A the frame accelerates toward the speaker's chest, smearing into a radial zoom blur with a slight clockwise spin, and A's caption blurs away with it. Hard cut. Shot B starts about 3.4× zoomed in, blurred and tilted, then decelerates out to normal framing over ~12 frames, and its caption fades in. By default A's captions use the gold serif style and B's use wide-tracked small caps, like the reference.

This effect can take a second clip (--second). Output: 1080×1920, 30 fps H.264 MP4 with the original audio.

When to use it

  • Moving between two takes, outfits or locations ("…or you can get the…").
  • Hiding a jump cut inside one long take (single-clip mode with cutAt).
  • A "but wait" or contrast beat where the second shot should feel like a reveal.

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 "$ENGINE/fx.mjs" words "<video>" prints a timestamped transcript of the whole file (cached); add --detail for every word's start → end. Pick the 3–12 second stretch the user means, or the one this effect suits best. Snap the range to speech: start ~0.1s before its first word, end ~0.2s after its last word, so nothing is clipped.
  2. Decide the deliverable.
    • The clip is the moment → render that range and deliver the MP4.
    • A moment inside a longer video → render the moment's range, then put it back with splice (step 7) and deliver the full video (mention the segment file too). If the range ends before the video does, add "window": [0, <range length − 0.4>]: the effect has fully left by the window end, so keep that after the last word the graphics belong to. Captions must match the rest of the video: either caption everything (render the captions effect over the whole file with the same "captions" block as this config and splice into that render) or set "captions": {"enabled": false} here and splice into the original. The video-fx skill covers multi-effect videos.
  3. Write the config as <video name> - zoom-through-cut.json next to the video (or in the folder the user names). The engine never modifies the source video; every output is a new file. Repair misheard names with "fixes" (e.g. {"cloud code": "Claude Code"}).
  4. Check one frame before the full render: node "$ENGINE/fx.mjs" still zoom-through-cut "<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; 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 "$ENGINE/fx.mjs" render zoom-through-cut "<video>" --start <s> --end <s> --config "<config.json>" [--second "<other video>" --second-start a --second-end b] --out "<folder>/<video name> - Zoom-Through Cut.mp4"
  6. Review: node "$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
cutAt "auto" single-clip mode: where the cut happens (seconds or "@word"; "auto" = a word boundary near the middle). Ignored with --second (the cut is where clip A ends)
pushFrames 9 frames shot A spends rushing in before the cut (8-10 feels like the reference)
pullFrames 12 frames shot B takes to settle after the cut (10-14)
pushScale 4 how far shot A zooms in by the cut (4 = 4x)
pullScale 3.4 how zoomed-in shot B starts (3.5 = 3.5x)
blur 0.55 strength of the radial zoom blur (0 = none, 0.6 = strong)
samples 12 blur quality: copies used for the blur (6-9)
rotate 7 degrees of spin across the transition (0 = straight zoom)
focus "chest" where shot A zooms: "chest" (default), "face", or [x, y] as 0-1 fractions
focusB null where shot B zooms out from (defaults to focus)
captionsA {} caption overrides for shot A, e.g. {"style": "serif"}
captionsB {"style":"tracked"} caption overrides for shot B, e.g. {"style": "tracked"}

Run node "$ENGINE/fx.mjs" info zoom-through-cut to print these with the full default config.

Writing the config

  • Two clips: render with --second "<clip B>" --second-start s --second-end s; the cut is where clip A ends, so trim clip A to end right after a phrase.
  • One clip: cutAt picks the cut, e.g. "@absolutely" (the cut lands as that word starts). "auto" picks a word boundary near the middle.
  • captionsA / captionsB override the caption look per shot, e.g. {"emphasis": ["Claude"]} for the gold word in shot A, or {"style": "pop"} in shot B.
  • Faster and harder: pushFrames 7, pullFrames 10, blur 0.65. Calmer: rotate 0 and blur 0.35.
  • focus sets where the zoom goes ("chest", "face" or [x, y]); use "face" for tight close-ups.

Example

Shot A line: "…edited completely using Claude code." Shot B line: "Meaning that if you wanted to build your own course selling platform…"

{
  "captionsA": { "emphasis": ["Claude"] }
}

Rendered with --start 0 --end 5.6 --second "<shot B>.mp4" --second-start 21 --second-end 27.

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 60% 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 0.6 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 72 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

  • End shot A on a finished phrase; the push eats the last ~0.3s, so a word that runs into the cut gets blurred away.
  • The blur is built from stacked copies of the frame; at the peak you may see faint rings in a paused frame, which read as motion blur at full speed. Raise samples (12–16) for cleaner stills, at some render cost.
  • Two very different exposures cut harder; that is often the point, but match brightness if you want it seamless.
  • Without a cut-out the zoom aims at the centre-chest of a typical framing; if the speaker sits off-centre, set focus to [x, y].
  • 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.