fx-couch-wall

Fill the room behind a talking-head speaker with a wall of short-form video thumbnails — portrait tiles with ▷ view counts and headline stickers pop in around them while they stay in front, like a cre

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.

Couch Wall — Claude Video FX 02/17

A masonry wall of 9:16-style thumbnails (rounded tiles, thin gaps) pops in tile by tile outward from the speaker's head in about half a second, covering the room behind them. Most tiles carry a white "▷ 1.07M" view-count badge, a few carry white headline stickers ("6 ways to make money with AI this week"). The speaker is cut out and stays in front; the wall drifts in very slowly while it holds. Captions are two-tier: a small setup line over one huge word ("selling a / COURSE").

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: "I've posted hundreds of videos", "this got millions of views".
  • Talking about content, courses, a channel or a body of work.
  • A punchy visual reset in the middle of a one-take talking head.

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 "$ENGINE/fx.mjs" words "<video>" prints a timestamped transcript of the whole file (cached); add --detail for every word's start → end. Pick the 3–12 second stretch the user means, or the one this effect suits best. Snap the range to speech: start ~0.1s before its first word, end ~0.2s after its last word, so nothing is clipped.
  2. Decide the deliverable.
    • The clip is the moment → render that range and deliver the MP4.
    • A moment inside a longer video → render the moment's range, then put it back with splice (step 7) and deliver the full video (mention the segment file too). If the range ends before the video does, add "window": [0, <range length − 0.4>]: the effect has fully left by the window end, so keep that after the last word the graphics belong to. Captions must match the rest of the video: either caption everything (render the captions effect over the whole file with the same "captions" block as this config and splice into that render) or set "captions": {"enabled": false} here and splice into the original. The video-fx skill covers multi-effect videos.
  3. Write the config as <video name> - couch-wall.json next to the video (or in the folder the user names). The engine never modifies the source video; every output is a new file. Repair misheard names with "fixes" (e.g. {"cloud code": "Claude Code"}).
  4. Check one frame before the full render: node "$ENGINE/fx.mjs" still couch-wall "<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 "$ENGINE/fx.mjs" render couch-wall "<video>" --start <s> --end <s> --config "<config.json>" --out "<folder>/<video name> - Couch Wall.mp4"
  6. Review: node "$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
at 0.15 when the tiles start popping in (seconds or "@word")
fillDuration 0.55 seconds from first to last tile (0.4-0.8 feels snappy)
outAt null optional: when the wall pops away (null = holds to the end; it also leaves automatically when an effect window ends early)
media [] optional list of image/video file paths for the tiles (your real thumbnails/clips); they repeat if there are fewer than tiles. Empty = stills of this clip
labels ["6 ways to make money with AI this week","Can you tell??"] white headline stickers placed on a few tiles, e.g. ["6 ways to make money with AI", "Can you tell??"]. Empty list = none
views null optional list of view-count strings ("1.07M", "534K"); null = plausible random counts
showViews true show the ▷ view-count badge on most tiles
columns 3 number of tile columns (3 = reference look, 4 = denser)
gap 8 gap between tiles in px (at 1080 wide)
radius 10 tile corner radius in px
wallBottom "auto" "auto" (from the speaker's head) or a 0-1 fraction: how far down the frame the wall reaches
drift 0.035 slow push-in of the wall while it holds (0 = static, 0.04 = subtle)

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

Writing the config

  • at: land the wall on the word that names the content ("@course", "@videos"), or 0.1–0.3s in.
  • media: if the user has real thumbnails or clips, list their file paths; that's the most convincing look. With nothing given, tiles are stills of the clip itself at different moments, crops and grades — fine for a demo, but say so to the user.
  • labels: 1–3 short hooks that sound like real video titles from the user's niche (≤ 7 words each). Use [] for none.
  • views: optional; give real numbers if the user has them, otherwise leave null for plausible counts.
  • captions.emphasis: the single word that should go huge in the two-tier caption ("course", "platform"). Two-tier captions read best when the emphasis word ends the phrase.

Example

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

{
  "at": "@build",
  "labels": ["How I sell my course", "Can you tell??", "My $0 tech stack"],
  "views": ["1.07M", "534K", "133K", "5,488", "15.3K", "2.2M", "847K", "61K"],
  "captions": { "style": "twoTier", "emphasis": ["course", "platform", "GitHub"] }
}

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 twoTier, centred at 62% of the frame height.

Option Default What it does
enabled true false hides captions (or pass --no-captions)
style "twoTier" 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 0.62 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

  • Only the person is cut out. Props in front of them (a microphone on an arm, a desk lamp) are treated as background and disappear under the tiles; warn the user if their mic sits in front of the wall area.
  • If the speaker's head is very high or low in frame, set wallBottom (0.45–0.7) so the wall stops around shoulder height.
  • columns: 4 makes smaller, denser tiles for close-up framing; 3 matches the reference.
  • Keep the effect window short (2–5 s). Use "window": [start, end] or outAt so the wall pops away before the clip ends if the video continues.
  • Two-tier captions with an emphasis word mid-phrase can read oddly; pick emphasis words that end a phrase, or switch captions.style to "pop".
  • 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.