Skip to content
Skills Library
Marketing & content · Automation

render-split-screen-creator

/render-split-screen-creator

Assemble a split-screen creator ad from a config: an AI-creator lip-sync take fills the bottom half while real 16:9 product or demo clips play uncropped in the top half over a blurred fill of the same clip (never black bars), with a brand-colour divider between them. Scenes follow the voiceover timing and are joined hard, an end card holds about 3 seconds, then the finished cut is transcribed and word-level captions are burned in the chosen style. Free, deterministic assembly and captions; the voiceover comes from create-vo-elevenlabs, the creator anchor from create-image-gpt-image-fal, and th

Licence
MIT
Last repository change
25.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
6
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Assemble a split-screen creator ad from a config: an AI-creator lip-sync take fills the bottom half while real 16:9 product or demo clips play uncropped in the top half over a blurred fill of the same clip (never black bars), with a brand-colour divider between them. Scenes follow the voiceover timing and are joined hard, an end card holds about 3 seconds, then the finished cut is transcribed and word-level captions are burned in the chosen style. Free, deterministic assembly and captions; the voiceover comes from create-vo-elevenlabs, the creator anchor from create-image-gpt-image-fal, and th

Original author description

Assemble a split-screen creator ad from a config: an AI-creator lip-sync take fills the bottom half while real 16:9 product or demo clips play uncropped in the top half over a blurred fill of the same clip (never black bars), with a brand-colour divider between them. Scenes follow the voiceover timing and are joined hard, an end card holds about 3 seconds, then the finished cut is transcribed and word-level captions are burned in the chosen style. Free, deterministic assembly and captions; the voiceover comes from create-vo-elevenlabs, the creator anchor from create-image-gpt-image-fal, and th

How it works

  1. Choices
  2. Run
  3. Contract (the free assembly)
Original SKILL.md headings · 97 lines, 918 words
SKILL.md preview
---
name: render-split-screen-creator
description: "Assemble a split-screen creator ad from a config: an AI-creator lip-sync take fills the bottom half while real 16:9 product or demo clips play uncropped in the top half over a blurred fill of the same clip (never black bars), with a brand-colour divider between them. Scenes follow the voiceover timing and are joined hard, an end card holds about 3 seconds, then the finished cut is transcribed and word-level captions are burned in the chosen style. Free, deterministic assembly and captions; the voiceover comes from create-vo-elevenlabs, the creator anchor from create-image-gpt-image-fal, and the lip-sync take is supplied as an input. Use for the split-screen-creator format."
status: active
---

# render-split-screen-creator

Assemble a **split-screen creator** ad from a config: a two-zone vertical
(1080×1920, 9:16, ~40s) format where an **AI creator talking-head** anchors the
BOTTOM ~48% of the frame and **real 16:9 product/demo clips** run uncropped in
the TOP ~52%, a 3px brand-color divider between the zones. The creator delivers
the whole VO cold-to-camera and each top clip proves the claim its VO line makes.
This capability is the **FREE, deterministic assembly + captions** — the two-zone
composite (contain-fit + blurred-cover fill + divider + creator slice), the
hard-concat, the end card, and the word-level caption burn from the assembled cut.

`scripts/config.example.json` is one worked example (the fictional
Larderloop "whole Sunday" demo, ~40s 1080×1920 9:16, 6 scenes + an end card) — copy its
structure, never its creative values;
`scripts/PIPELINE.md` maps every config block to its source step and
`scripts/README.md` documents the free assembly.

## Choices

The creative calls are made upstream by the user (the calling format's recipe
`choices`) and arrive here as config. This capability never picks them.

- **`creator_gender` / `creator_age` / `creator_look`** — who the creator is
  (`creator.brief`); shapes the anchor and the voice upstream. Here it only
  affects framing checks. The worked example used a woman in her 30s.
- **`setting`** — where the creator films from (`creator.brief.vibe_setting`).
  The worked example used a lived-in kitchen with window daylight.
- **`tone`** — the script and VO delivery; upstream only. The worked example
  was a confident, fast explainer.
- **`caption_style`** — `captions.style` (`serif-accent`, `kinetic-pop`,
  `neon-glow`, `clean-bubble`). Burned here. The worked example shipped
  `serif-accent`.

If a creative field is empty in the config, ask for it — don't fall back to the
worked example's value.

## Run

This is the **FREE, deterministic** assembly + captions stage — it spends
nothing. The paid inputs are separate steps — the VO (`create-vo-elevenlabs`,
ElevenLabs `eleven_v3` with-timestamps, sliced into per-scene windows), the
**photoreal MEDIUM chest-up** AI-creator anchor (`create-image-gpt-image-fal`,
`gpt-image-2`) — shot at a natural webcam distance (headroom + shoulders, real
room), **not** a plain-background close-up headshot (see the anchor note below), and
the whole-VO lip-sync (a **paid VEED Fabric 1.0 @ 720p take — a no-atom step**,
`image_url` = the anchor, `audio_url` = the vo mp3, billed per second of VO and the largest spend; run its calls sequentially, `veed/fabric-1.0` storage-auths 403 under
parallel load). Given the creator lip-sync take + the per-scene VO timing + one
16:9 top clip per scene + the scene-1 hook graphic + the end-card clip,
`render-split-screen-creator` composites the two zones, hard-concats the scenes,
appends the end card, transcribes the assembled cut, and burns the captions → the
master. Re-cuts reuse the existing VO / lip-sync / clips and spend nothing.

## Contract (the free assembly)

- **Two-zone split, top ~52% / creator ~48%.** The TOP zone runs the real 16:9
  product/demo clip **contain-fit** (uncropped), the BOTTOM zone is the creator
  lip-sync framed **head-to-shoulders**: scale-to-width × a small **ZOOM** (~1.15–1.2)
  then crop the zone with a **downward offset** so the face sits upper-middle and the
  shoulders enter the bottom. (A plain cover + crop-toward-top shows only the head and
  cuts the shoulders — and it can't rescue an anchor that was shot too close; fix the
  anchor distance first.) Tune zoom/offset visually against the source video's creator
  framing — it's a FREE re-assemble, no VEED re-run. A 3px brand-color divider separates
  the zones. Canvas 1080×1920, `top_height` ~998. **Keep every stacked height EVEN**
  (998 + 4 divider + 918 = 1920) — libx264 rejects odd dimensions.
- **Anchor = photoreal MEDIUM shot, not a studio headshot.** The lip-sync only looks as
  good as the anchor. It must be photoreal/candid (real lived-in room, natural skin
  cues), framed chest-up at a natural webcam distance (headroom + shoulders), **not** a
  plain-background close-up and **not** a phone-selfie pose copied from another format
  (e.g. `ugc-walk-and-talk`). VEED Fabric handles photoreal fine (unlike Seedance).
- **Blurred-cover fill, never black bars.** The top clip's letterbox margins are
  filled with a darkened **blurred cover-scale of the same clip** — a flat
  charcoal/black bar reads cheap.
- **One claim per scene, shown as it's said.** Each top clip is windowed
  (`top_start`/`top_end`) to the on-message segment that proves its VO line.
  **Never loop a short clip** — set the window and the assembler speed-fits it to
  the scene (looping replays into a sparse/black tail).
- **The creator VO is the entire audio bed — no separate music.** Body audio =
  the concatenated creator VO slices, timed per the per-scene `timing.json`; the
  lip-sync drives the mouth.
- **Hard-concat the scenes; end card on the last SHARP frame.** Hard-cut concat
  (no dissolves); append the end card holding the last sharp frame ~3s. If the
  end-card clip fades to black, hold the last sharp second (`endcard.clip_end`),
  not the black tail.
- **Caption the ASSEMBLED cut, not the raw VO.** Concat drops inter-scene
  silence, so the ad timeline ≠ the VO timeline; only the final cut's audio
  yields correct caption timing. Transcribe the assembled cut with local Whisper,
  build word-level cues (sentence-aware chunking), burn the ASS in the style set
  by `captions.style` (`serif-accent`, `kinetic-pop`, …). Keep the `-precaption` cut + the
  `.ass` sidecar so captions restyle without re-rendering the composite. If the
  host ffmpeg lacks libass, render the cues as timed PIL PNG overlays (ffmpeg
  `overlay=…:enable='between(t,st,en)'`) at the same placement.
- **FFmpeg composite, deterministic, FREE.** Two-zone composite per scene,
  hard-concat, append the end card, mux the creator VO, `loudnorm I=-14` → a
  1080×1920 h264+aac master. No paid calls, no keys — the VEED Fabric lip-sync is
  a supplied input, produced upstream.
Files in this package (6)
  • SKILL.md 7 KB
  • skill.meta.json 1 KB
  • scripts/PIPELINE.md 6 KB
  • scripts/README.md 4 KB
  • scripts/config.example.json 10 KB
  • tests/smoke-test.md 2 KB

Versions

The database has no other skills named render-split-screen-creator.

Database snapshot: 13.11.2026 · package version a8d34a9aa71f (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100render-narrated-ugc-wardrobe-stitch
    Assemble a narrated-UGC \"stitch reply\" ad from a config: one voiceover carries a verbatim testimonial while about 30 short clips (one creator across about 5 outfits and 3 settings, plus product B-roll) are trimmed to windows cut from the voiceover's word timings and joined.…
  • 100render-song-mv
    Assemble a song-driven music-video ad from a config — a generated sung track carries the whole narration across N tableaux (one keyframe -> one i2v clip per lyric beat) with NO separate voiceover, captions synced to the song's OWN word timings (script-window, never Whisper) and…
  • 100split-screen
    Edits a talking-head clip into the classic half-and-half reel. Visuals and animation fill the top half (a step badge, a serif headline and a window showing the point), the speaker fills the bottom half, and bold uppercase captions sit on the seam between them. Use when the user…
  • 100talking-head-edit
    Your raw clip, fully edited: captions on every word, the screen splits into two windows to show what you're talking about, and demo videos play full screen. Your face is never re-coloured. Use when asked for talking-head edit video production or editing.
  • 100ai-ad-editor
    Turn a finished ad script into a finished short-form video ad (9:16, plus 4:5, 1:1 and 16:9 if wanted) from AI-generated clips, the user's own clip library (UGC), or both - voiceover, shot plan, library clip matching, characters, scene images, AI video clips, talking characters…
  • 96split-screen
    Split screen for a short - visuals on top, a host image below, captions on the seam - over one or more consecutive phases; the top visual swaps on spoken words. Use when the user asks for split screen, "host below", or a talking-host layout for a faceless short.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.