fx-paper-cut

Turn a talking-head shot into a handmade scrapbook collage — the speaker becomes a paper sticker with a torn white border over crayon scribbles, torn yellow paper and X marks, while ransom-note letter

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.

Paper Cut — Claude Video FX 13/17

The background is swapped for off-white paper with a faint grid, a big blue crayon scribble across the top, a torn yellow strip with navy scribbles and red ticks, pink scribbles, X marks and loop doodles. The speaker, still talking, is cut out as a paper sticker with a thick, slightly ragged white border and a drop shadow, slapping into place. Ransom-note letters on mixed chips (blue, white, black, yellow; serif, slab, typewriter) land one by one, a red marker ring draws itself around them, then a smaller word pops in below. All the scribbles boil on threes like stop-motion.

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

  • Calling out a number or claim: "100%", "3X", "$0", "FREE".
  • A playful, creator-diary or "behind the scenes" moment that should feel handmade.
  • A 2–5 second beat in the middle of a talk to reset attention (use window).

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 "$ENGINE/fx.mjs" words "<video>" prints a timestamped transcript of the whole file (cached); add --detail for every word's start → end. Pick the 3–12 second stretch the user means, or the one this effect suits best. Snap the range to speech: start ~0.1s before its first word, end ~0.2s after its last word, so nothing is clipped.
  2. Decide the deliverable.
    • The clip is the moment → render that range and deliver the MP4.
    • A moment inside a longer video → render the moment's range, then put it back with splice (step 7) and deliver the full video (mention the segment file too). If the range ends before the video does, add "window": [0, <range length − 0.4>]: the effect has fully left by the window end, so keep that after the last word the graphics belong to. Captions must match the rest of the video: either caption everything (render the captions effect over the whole file with the same "captions" block as this config and splice into that render) or set "captions": {"enabled": false} here and splice into the original. The video-fx skill covers multi-effect videos.
  3. Write the config as <video name> - paper-cut.json next to the video (or in the folder the user names). The engine never modifies the source video; every output is a new file. Repair misheard names with "fixes" (e.g. {"cloud code": "Claude Code"}).
  4. Check one frame before the full render: node "$ENGINE/fx.mjs" still paper-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 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 "$ENGINE/fx.mjs" render paper-cut "<video>" --start <s> --end <s> --config "<config.json>" --out "<folder>/<video name> - Paper Cut.mp4"
  6. Review: node "$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
headline "auto" the ransom-note word or number, e.g. "100%", "3X", "FREE" ("auto" = a number from the transcript, else the strongest word)
subline "auto" smaller second word under the ring, e.g. "EDITED" ("auto" = the next strong word, "" = none)
headlineAt 0.35 when the first letter lands (seconds or "@word")
sublineAt null when the subline starts (null = right after the ring)
stagger 4 frames between letters
circle true draw the red marker ring around the headline (true/false)
headlineX 0.07 left edge of the headline as a 0-1 fraction of the width (when headlineAlign is left)
headlineY 0.145 vertical centre of the headline, 0-1 of the height
headlineAlign "left" "left" or "center"
headlineSize 118 maximum letter size in px at 1080 wide (long words shrink to fit)
headlineWidth 0.8 maximum headline width as a fraction of the frame
sublineScale 0.62 subline letter size relative to the headline
stickerScale "auto" "auto" (fits the head to headTopTarget) or a number like 0.75
headTopTarget 0.34 auto scale: where the top of the head should land, 0-1 of the height
stickerX 0.44 horizontal centre of the sticker, 0-1 of the width
stickerRotate -1.5 sticker tilt in degrees
borderWidth 15 white sticker border thickness in px
tornEdge 12 how ragged the border edge is (0 = clean)
boilEvery 3 re-jitter the scribbles every N frames
elements {"grid":true,"blueScribble":true,"tornPaper":true,"pinkSc… turn collage pieces on/off: {"grid", "blueScribble", "tornPaper", "pinkScribble", "marks", "loops"}
colors {"paper":"#F1EEE6","grid":"#C3CEDA","blue":"#8C9EDA","blu… palette: paper, grid, blue, blueDark, yellow, navy, pink, red, ring, border

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

Writing the config

  • headline: 1–6 characters reads best (a number, %, or one short word). Take it from what the speaker says ("one hundred percent" → "100%"). Words up to ~8 letters shrink to fit.
  • subline: one short word that completes the thought ("EDITED", "FREE", "DONE"), or "" for none.
  • headlineAt: anchor to the spoken word, e.g. "@percent" or "@course-0.1", so the letters land as it is said. The ring and subline follow automatically.
  • The collage replaces the whole background, so use it for a beat, not a whole video: pass "window": [start, end] (seconds in the clip) for a hard cut in and a quick fade back to the footage.
  • Captions are off by default (the letters are the text). Turn them on with "captions": {"enabled": true}; the box style suits the look.
  • Nudge the sticker with stickerScale (0.6–0.9), stickerX and headTopTarget if the head collides with the letters.

Example

Line: "If you wanted to build your own course selling platform, all you have to do is download this GitHub repo."

{
  "headline": "100%",
  "subline": "FREE",
  "headlineAt": "@course",
  "captions": { "enabled": false }
}

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 box, centred at 88% of the frame height.

Option Default What it does
enabled false false hides captions (or pass --no-captions)
style "box" 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 0.88 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

  • If the head overlaps the ring, lower the sticker ("headTopTarget": 0.4) or move the letters up ("headlineY": 0.12).
  • Fast hand moves leave soft, semi-transparent edges in the cut-out; that reads fine as paper, but keep the beat short if hands fly around a lot.
  • People sitting at a desk get cut where the desk is; the white border makes that edge look like a deliberate scissor cut.
  • "auto" text picks a number from the transcript, otherwise the strongest word — always replace it with something meaningful when you know the topic.
  • Turn collage pieces off with "elements": {"loops": false, "marks": false} for a cleaner page; change the palette under colors for brand colours.
  • 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.