fx-checklist

Add an animated checklist overlay to a talking-head video — a frosted dark-glass card ("ALL YOU NEED TO DO", "0 of 3" — the counter follows however many steps you give it) whose steps type in as they

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.

Checklist — Claude Video FX 07/17

A dark frosted-glass card with a slight 3D tilt springs in above the speaker's head (or over the chest on close-ups). The header reads ALL YOU NEED TO DO with a "0 of N" counter (N = number of steps) and a segmented yellow progress bar; the rows start as grey skeleton bars. When a step is spoken its text types in with a caret, then its circle fills yellow with a check and a little burst, the counter ticks up and that bar segment fills.

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

  • "All you need to do is…", "three steps", "here's the process" moments.
  • Listing requirements, features or a recipe while talking to camera.
  • Recapping what was just covered at the end of a video.

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 "$ENGINE/fx.mjs" words "<video>" prints a timestamped transcript of the whole file (cached); add --detail for every word's start → end. Pick the 3–12 second stretch the user means, or the one this effect suits best. Snap the range to speech: start ~0.1s before its first word, end ~0.2s after its last word, so nothing is clipped.
  2. Decide the deliverable.
    • The clip is the moment → render that range and deliver the MP4.
    • A moment inside a longer video → render the moment's range, then put it back with splice (step 7) and deliver the full video (mention the segment file too). If the range ends before the video does, add "window": [0, <range length − 0.4>]: the effect has fully left by the window end, so keep that after the last word the graphics belong to. Captions must match the rest of the video: either caption everything (render the captions effect over the whole file with the same "captions" block as this config and splice into that render) or set "captions": {"enabled": false} here and splice into the original. The video-fx skill covers multi-effect videos.
  3. Write the config as <video name> - checklist.json next to the video (or in the folder the user names). The engine never modifies the source video; every output is a new file. Repair misheard names with "fixes" (e.g. {"cloud code": "Claude Code"}).
  4. Check one frame before the full render: node "$ENGINE/fx.mjs" still checklist "<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 "$ENGINE/fx.mjs" render checklist "<video>" --start <s> --end <s> --config "<config.json>" --out "<folder>/<video name> - Checklist.mp4"
  6. Review: node "$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
title "ALL YOU NEED TO DO" small header text on the card
items "auto" "auto" (3 short steps pulled from the transcript) or a list. Each item is a string, or {"text": "Drop your clips", "at": "@drop", "doneAt": "@trigger"}. "at" = when it types in (default: when its first key word is spoken), "doneAt" = when it ticks (default: checkAfter seconds after typing finishes).
count 3 how many items to generate when items is "auto"
inAt 0.1 when the card appears (seconds or "@word"); it always appears a moment before the first item
outAt null optional: when the card flies away (null = stays to the end)
checkAfter 0.3 seconds between an item finishing typing and its tick
typeSpeed 32 typing speed in characters per second
position "auto" "auto" (above the head if there is room, else over the chest), "top", "bottom", or a 0-1 fraction for the card's top edge
width 0.84 card width as a fraction of the frame width
accent "#F5E15A" colour of the ticks, progress bar and glow
doneTextColor "#F1E7A6" text colour of finished items
tilt 6 3D tilt of the card in degrees (0 = flat)
captionsAvoid true move the captions above/below the card if they would overlap it

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

Writing the config

  • items: 2–5 short steps, 2–4 words each, written as commands ("Drop your clips", "Trigger the skill"). Take them from what the speaker actually says, tightened. Leave "auto" only as a fallback (it pulls rough phrases from the transcript).
  • Give each item an at on the word where that step is said ("@drop"); items always type one after another, so close timings are safe. Use doneAt only if the tick must land on a specific word.
  • title is the small header; keep it under ~22 characters, uppercase reads best.
  • position is automatic: above the head when there's room (wide shots), over the chest on close-ups, and captions move out of the way. Force "top" / "bottom" only if it covers something important.
  • Set outAt if the list should leave before the clip ends (it also leaves automatically when the effect window ends early).

Example

Line: "This new Opus model should be capable of doing three absolutely mind-blowing things."

{
  "title": "WHAT OPUS CAN DO",
  "items": [
    { "text": "Run an agent swarm", "at": "@three" },
    { "text": "Rebuild any website", "at": "@absolutely" },
    { "text": "Generate images", "at": "@mind" }
  ],
  "outAt": -0.4
}

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

  • Long step text shrinks to fit the row; past ~24 characters it gets small, so shorten the wording instead.
  • If two steps are said within a second, the second waits for the first to finish typing; raise typeSpeed (e.g. 45) for rapid-fire lists.
  • On very busy backgrounds raise contrast by darkening the footage a touch elsewhere, or keep the card over a plain wall with position: "top".
  • The card needs the cut-out pass only to find the head; if the speaker is off-centre and the card lands on the face, set position to a number (0–1 of the height).
  • 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.