fx-phone-mockup

Float a realistic iPhone next to the speaker in a talking-head video, with an app conversation that plays itself out — message, typing dots, a recommendation card, a finger tap on "Approve" and a repl

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.

Phone Mockup — Claude Video FX 06/17

A titanium iPhone (dynamic island, status bar, home indicator) springs in from the side beside the speaker's head with a slight 3D tilt, soft shadow and gentle float, while the footage pans a little the other way to keep the face clear. On screen, a dark chat-assistant app plays out: header with avatar, a message, typing dots, a recommendation card with stat tiles, then a touch indicator taps the white button, which turns green with a check and a reply bubble pops in.

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

  • Showing what an app, bot or automation does while explaining it.
  • "It just sends me a message and I hit approve" moments.
  • Putting a real screenshot or screen recording into a phone frame (screen).

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 "$ENGINE/fx.mjs" words "<video>" prints a timestamped transcript of the whole file (cached); add --detail for every word's start → end. Pick the 3–12 second stretch the user means, or the one this effect suits best. Snap the range to speech: start ~0.1s before its first word, end ~0.2s after its last word, so nothing is clipped.
  2. Decide the deliverable.
    • The clip is the moment → render that range and deliver the MP4.
    • A moment inside a longer video → render the moment's range, then put it back with splice (step 7) and deliver the full video (mention the segment file too). If the range ends before the video does, add "window": [0, <range length − 0.4>]: the effect has fully left by the window end, so keep that after the last word the graphics belong to. Captions must match the rest of the video: either caption everything (render the captions effect over the whole file with the same "captions" block as this config and splice into that render) or set "captions": {"enabled": false} here and splice into the original. The video-fx skill covers multi-effect videos.
  3. Write the config as <video name> - phone-mockup.json next to the video (or in the folder the user names). The engine never modifies the source video; every output is a new file. Repair misheard names with "fixes" (e.g. {"cloud code": "Claude Code"}).
  4. Check one frame before the full render: node "$ENGINE/fx.mjs" still phone-mockup "<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 "$ENGINE/fx.mjs" render phone-mockup "<video>" --start <s> --end <s> --config "<config.json>" --out "<folder>/<video name> - Phone Mockup.mp4"
  6. Review: node "$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
side "auto" "auto" (the side with more room), "left" or "right"
size 0.33 phone width as a fraction of the frame width (0.3-0.4)
y "auto" "auto" (level with the head) or a 0-1 fraction for the phone's top edge
tilt 12 3D tilt in degrees (0 = flat facing camera)
nudge "auto" "auto" pans the footage away from the phone so the face isn't covered, or a 0-0.12 fraction of the frame width (0 = no pan)
app.name null app name in the header
app.status null line under the app name (e.g. Online)
app.avatarColor null avatar / accent colour
message "Found one fix for you." the assistant's first message
card.label null small tracked label on the card
card.title null the card's headline (1-2 short lines)
card.tiles null up to 3 stat tiles: [{"label": "Ad 1", "value": 0.9, "color": "#6FD38A"}] (value 0-1 = bar fill); [] hides them
button "Approve" primary button label that gets tapped
secondary "Not now" secondary text next to the button ("" hides it)
approvedLabel "Approved" button label after the tap
reply "Done. Budget moved to Ad 1." reply bubble that appears after the tap ("" for none)
screen null optional image or video file shown on the screen instead of the chat UI
inAt 0.05 when the phone flies in (seconds or "@word")
messageAt "auto" "auto" or when the first message appears
cardAt "auto" "auto" (about 30% in) or when the card appears
tapAt "auto" "auto" (on words like approve/click/tap/done, else ~65% in) or when the button is tapped
outAt null optional: when the phone flies back out (null = stays)
app {"name":"Ads Assistant","status":"Online","avatarColor":"…
card {"label":"RECOMMENDATION","title":"Pause Ad 3, move the b…

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

Writing the config

  • Rewrite the chat for the user's product: app.name, message (the bot's first line), card.title (the key recommendation/result, ≤ ~40 characters), button / approvedLabel, and reply.
  • card.tiles are 3 mini stats (label + 0–1 bar value); make them match the story or set [] to hide them.
  • Time it to speech: cardAt when the speaker introduces the result, tapAt on the action word ("@approve", "@download", "@post"). "auto" puts the tap on words like approve/click/tap/done, else ~65% in.
  • For a real app, pass screen with a screenshot or vertical screen recording path; the chat UI is replaced and the phone frame stays.
  • side defaults to the side with more room; use size 0.3 for tight close-ups, 0.38 for wide shots.

Example

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

{
  "side": "left",
  "app": { "name": "Repo Scout", "status": "Watching GitHub", "avatarColor": "#8AB4FF" },
  "message": "Found an open-source course platform.",
  "card": {
    "label": "NEW REPO",
    "title": "Gumroad is now fully open source",
    "tiles": [
      { "label": "Stars", "value": 0.95, "color": "#8AB4FF" },
      { "label": "Forks", "value": 0.6, "color": "#8AB4FF" },
      { "label": "Issues", "value": 0.25, "color": "#E5706B" }
    ]
  },
  "button": "Download",
  "secondary": "Later",
  "approvedLabel": "Cloned",
  "reply": "Cloned to ~/course-platform",
  "cardAt": "@course-0.3",
  "tapAt": "@download"
}

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 72% 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 0.72 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

  • On tight close-ups the phone may touch the cheek; lower size to 0.3 or raise nudge to 0.12 (pans the footage further away).
  • Keep card.title to two lines; longer text pushes the buttons down.
  • A screen recording in screen should be vertical (9:16-ish); landscape media gets cropped to fill.
  • Leave at least ~0.8s after tapAt so the approved state and reply are seen.
  • 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.