fx-digital-zoom

Add punch-in "digital zoom" cuts with a radial zoom blur to a talking-head video, timed to the key words, the way short-form editors fake a second camera angle. Renders an MP4 for Reels, TikTok or Sho

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.

Digital Zoom — Claude Video FX 05/17

The frame snaps 25–35% closer on an emphasised word, with a 4–6 frame radial zoom blur that sells the move, then holds. On the next emphasised word it snaps back out (or further in). Captions pop on word by word in white bold, with the key word in yellow.

This effect works on the footage as-is (no cut-out needed), so it prepares quickly. Output: 1080×1920, 30 fps H.264 MP4 with the original audio.

When to use it

  • A one-take talking head that needs energy without b-roll.
  • Landing a punchline or the key noun of a sentence ("video editing").
  • Faking a second camera angle between sentences.

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 "$ENGINE/fx.mjs" words "<video>" prints a timestamped transcript of the whole file (cached); add --detail for every word's start → end. Pick the 3–12 second stretch the user means, or the one this effect suits best. Snap the range to speech: start ~0.1s before its first word, end ~0.2s after its last word, so nothing is clipped.
  2. Decide the deliverable.
    • The clip is the moment → render that range and deliver the MP4.
    • A moment inside a longer video → render the moment's range, then put it back with splice (step 7) and deliver the full video (mention the segment file too). If the range ends before the video does, add "window": [0, <range length − 0.4>]: the effect has fully left by the window end, so keep that after the last word the graphics belong to. Captions must match the rest of the video: either caption everything (render the captions effect over the whole file with the same "captions" block as this config and splice into that render) or set "captions": {"enabled": false} here and splice into the original. The video-fx skill covers multi-effect videos.
  3. Write the config as <video name> - digital-zoom.json next to the video (or in the folder the user names). The engine never modifies the source video; every output is a new file. Repair misheard names with "fixes" (e.g. {"cloud code": "Claude Code"}).
  4. Check one frame before the full render: node "$ENGINE/fx.mjs" still digital-zoom "<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 "$ENGINE/fx.mjs" render digital-zoom "<video>" --start <s> --end <s> --config "<config.json>" --out "<folder>/<video name> - Digital Zoom.mp4"
  6. Review: node "$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
punches "auto" "auto", or a list like [{"at": "@video", "scale": 1.3}, {"at": "@editing", "scale": 1.0}]. "at" takes seconds or "@word".
scale 1.3 zoom level for auto punch-ins (1.3 = 30% closer)
rest 1 zoom level between punches (1.0 = original framing)
minGap 1.1 seconds between auto punches
transitionFrames 5 frames the snap takes (3-6 feels like a punch)
blur true radial zoom blur during the snap (true/false)
focus "face" "face" to zoom toward the face, or [x, y] as 0-1 fractions of the frame

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

Writing the config

  • punches: "auto" punches on the words the captions highlight (the strongest noun per phrase), alternating in and out, never closer than minGap seconds. Good default.
  • For control, list punches: [{"at": "@editing", "scale": 1.3}, {"at": "@thousands", "scale": 1.0}]. Use the word the speaker stresses, not filler.
  • Keep scale between 1.15 and 1.4; above 1.4 footage goes soft. Keep at least ~1s between punches.
  • Set captions.emphasis to the same words you punch on so the yellow word and the zoom land together.

Example

Line: "I didn't have to spend thousands of dollars on video editing courses."

{
  "punches": [
    { "at": "@thousands", "scale": 1.28 },
    { "at": "@editing", "scale": 1.0 }
  ],
  "captions": { "emphasis": ["thousands", "editing"] }
}

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 pop, centred at 60% of the frame height.

Option Default What it does
enabled true false hides captions (or pass --no-captions)
style "pop" 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

  • Punch on the stressed syllable's word start ("@word"), not on a pause, or it reads as a glitch.
  • If the face drifts out of frame at high zoom, lower scale or set focus to [0.5, 0.3] (x, y fractions).
  • Turn blur off for a cleaner, more corporate cut.
  • Footage below 1080p will look soft when punched; keep scale ≤1.2 there.
  • 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.