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.claude/skills/fx-couch-wall/SKILL.md
GitHubVideo Studio: run every command from the Video Studio folder;
ENGINEisengines/video-fx/engine(set up already:node "engines/video-fx/engine/fx.mjs" doctorshould 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 injobs/<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 everystill/renderof that range. To pick moments, readprojects/<id>/transcript/words.jsoninstead offx.mjs words. Usewords(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 usestyles/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) orfinal.mp4(approved); log each effect with its time range inedits.jsonso the review page can take notes on it. Sounds: these renders have none; add them after withstudio/sfx.mjslike 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 intomodels/(URL inengines/video-fx/install.mjs);node fx.mjs browser. Don't runinstall.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 "$ENGINE/fx.mjs" doctor. If any line shows ✖, stop and follow the setup steps in the video-fx skill (or tell the user to run the kit installer). Never edit files inside the engine to make a single video work; everything is controlled through the config JSON.
Workflow
- Read the video.
node "$ENGINE/fx.mjs" words "<video>"prints a timestamped transcript of the whole file (cached); add--detailfor 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. - 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 thecaptionseffect 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. Thevideo-fxskill covers multi-effect videos.
- Write the config as
<video name> - couch-wall.jsonnext 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"}). - Check one frame before the full render:
node "$ENGINE/fx.mjs" still couch-wall "<video>" --start <s> --end <s> --config "<config.json>" --at <seconds into the clip> --out "<folder>/check.png"then look at the PNG. The first still or render of a new range also makes the transcript and the cut-out (about 1s of processing per 9 frames, cached per exact --start/--end, so settle the range first); after that, it's fast. The CLI prints where every"@word"lands — fix any line marked!(word not found, default time used). - Render:
node "$ENGINE/fx.mjs" render couch-wall "<video>" --start <s> --end <s> --config "<config.json>" --out "<folder>/<video name> - Couch Wall.mp4" - Review:
node "$ENGINE/fx.mjs" sheet "<output.mp4>" --fps 4writes<output>-sheet.pngnext to the MP4 (use--fps 2for clips over 10s,--from/--toto zoom into a moment). For small text, grab a full-size frame:node "$ENGINE/fx.mjs" frame "<output.mp4>" --at <s>. Re-render if anything is off. - Splice (moments inside a longer video):
node "$ENGINE/fx.mjs" splice "<video>" --segments "<segment.mp4>@<start s>" --out "<folder>/<video name> - edited.mp4". It re-encodes the whole video to high-quality H.264 under the original (first) audio track. - Tell the user the output path(s), the time range used and what the effect shows.
--start/--end cut the source down to that range (times in seconds of the original file); everything in the config is relative to the start of that range. "window": [from, to] (seconds into the range) runs the effect for only part of it, with untouched footage outside. Add --draft for a quick half-resolution preview.
Options
| Option | Default | What it does |
|---|---|---|
at |
0.15 |
when the tiles start popping in (seconds or "@word") |
fillDuration |
0.55 |
seconds from first to last tile (0.4-0.8 feels snappy) |
outAt |
null |
optional: when the wall pops away (null = holds to the end; it also leaves automatically when an effect window ends early) |
media |
[] |
optional list of image/video file paths for the tiles (your real thumbnails/clips); they repeat if there are fewer than tiles. Empty = stills of this clip |
labels |
["6 ways to make money with AI this week","Can you tell??"] |
white headline stickers placed on a few tiles, e.g. ["6 ways to make money with AI", "Can you tell??"]. Empty list = none |
views |
null |
optional list of view-count strings ("1.07M", "534K"); null = plausible random counts |
showViews |
true |
show the ▷ view-count badge on most tiles |
columns |
3 |
number of tile columns (3 = reference look, 4 = denser) |
gap |
8 |
gap between tiles in px (at 1080 wide) |
radius |
10 |
tile corner radius in px |
wallBottom |
"auto" |
"auto" (from the speaker's head) or a 0-1 fraction: how far down the frame the wall reaches |
drift |
0.035 |
slow push-in of the wall while it holds (0 = static, 0.04 = subtle) |
Run node "$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 leavenullfor 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: 4makes smaller, denser tiles for close-up framing;3matches the reference.- Keep the effect window short (2–5 s). Use
"window": [start, end]oroutAtso 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.styleto"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.