fx-pull-back-reveal

Make a talking-head shot pull back to reveal it's playing inside an editor app that is rendering it — agent panel ticking through steps, render bar with waveform and frame counter, a big serif % count

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.

Pull-back Reveal — Claude Video FX 11/17

The full-frame footage smoothly shrinks into an editor window on a cream desk (title bar with the file name, the video keeps playing inside with its captions). A white agent panel slides in on the left and ticks through its steps with spinners and green checks; under the video a render bar with a waveform fills while a frame counter climbs. Near the end a big black serif number rolls up to 100 with a blue % badge, then the window border, bar and badge flip to green.

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

  • The reveal that the video itself was made by an AI tool or skill.
  • Showing a process completing ("it transcribes, cuts, captions and renders").
  • Ending a video on a satisfying "done" beat.

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 "$ENGINE/fx.mjs" words "<video>" prints a timestamped transcript of the whole file (cached); add --detail for every word's start → end. Pick the 3–12 second stretch the user means, or the one this effect suits best. Snap the range to speech: start ~0.1s before its first word, end ~0.2s after its last word, so nothing is clipped.
  2. Decide the deliverable.
    • The clip is the moment → render that range and deliver the MP4.
    • A moment inside a longer video → render the moment's range, then put it back with splice (step 7) and deliver the full video (mention the segment file too). If the range ends before the video does, add "window": [0, <range length − 0.4>]: the effect has fully left by the window end, so keep that after the last word the graphics belong to. Captions must match the rest of the video: either caption everything (render the captions effect over the whole file with the same "captions" block as this config and splice into that render) or set "captions": {"enabled": false} here and splice into the original. The video-fx skill covers multi-effect videos.
  3. Write the config as <video name> - pull-back-reveal.json next to the video (or in the folder the user names). The engine never modifies the source video; every output is a new file. Repair misheard names with "fixes" (e.g. {"cloud code": "Claude Code"}).
  4. Check one frame before the full render: node "$ENGINE/fx.mjs" still pull-back-reveal "<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 "$ENGINE/fx.mjs" render pull-back-reveal "<video>" --start <s> --end <s> --config "<config.json>" --out "<folder>/<video name> - Pull-back Reveal.mp4"
  6. Review: node "$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
pullAt 0.1 when the pull-back starts (seconds or "@word")
pullDuration 0.75 seconds the pull-back takes
doneAt "auto" "auto" (about 0.7s before the end) or when the render completes and turns green
counterAt "auto" "auto" (about 0.9s before done) or when the % counter starts rolling
returnAt null optional: when to zoom back to full frame (null = stay in the window; it returns automatically if the effect window ends before the clip)
filename "final-cut.mp4" file name in the window's title bar
tab "Assistant" label on the right of the title bar
workingLabel "Working on" panel header text
skill "edit" pill next to the panel header (the skill / command name)
steps ["Transcribed 1 clip","Picked the take","Cut 3 shots","Ca… list of step labels that tick off in order; {frames} is replaced by the frame count
frames "auto" "auto" (the clip's frame count) or a number for the render counter
accent "#3E6AE1" colour of the progress fill, skill pill and dots
background "#F1EEE6" desk colour around the window
windowX 0.29 left edge of the window, 0-1 of the width
windowWidth 0.6 window width, 0-1 of the width
videoAspect 0.64 width/height of the video area inside the window (0.5625 shows the full 9:16 frame)
panelX 0.045 left edge of the agent panel, 0-1 of the width

Run node "$ENGINE/fx.mjs" info pull-back-reveal to print these with the full default config.

Writing the config

  • steps: 3–6 short past-tense steps describing what the tool did (≤ ~24 characters each); {frames} inserts the render frame count.
  • filename and skill should name the user's real file and tool/command.
  • pullAt a beat before the reveal line ("@edited-0.2"); keep at least ~2.5s after it so the steps and counter can play out. doneAt defaults to ~0.7s before the end.
  • Add returnAt (e.g. -0.6) to zoom back to full frame before the clip ends; it also returns automatically when the effect window ends early.

Example

Line: "The video that you're currently watching was edited completely using Claude Code. I didn't have to hire an expensive editor."

{
  "pullAt": 0.3,
  "filename": "daily-update.mp4",
  "skill": "video-editor",
  "steps": ["Transcribed the take", "Cut the pauses", "Added captions", "Graded the colour", "Rendered {frames} frames"],
  "returnAt": -0.5
}

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

  • Under ~3s of window time the beats feel rushed; give it 4–7s.
  • Step labels longer than the panel are truncated with an ellipsis — shorten them.
  • Captions render inside the window, scaled down with the video; keep captions.y around 0.7 so they stay inside the cropped area.
  • videoAspect 0.5625 shows the whole 9:16 frame in the window (taller window); the default 0.64 crops a little top and bottom like the reference.
  • 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.