Log in
WorkflowBy HypernaturalVersion 4, updated

Shorts from long video

hn/workflow-shorts-from-long-video

Turn a stream, tutorial, podcast or any long screen-plus-webcam recording into a series of 30–50 s 9:16 shorts built only from that recording: the speaker's face in one half, eased punch-ins on the right part of their screen in the other, captions on the seam in their own shorts style, and word-cued motion graphics with a different sound for each kind. Covers watching the recording and the speaker's existing shorts, a transcript with word times, picking the moments (hook, whole sentences, payoff), the rough cut, zoom targets, the base render in ffmpeg, the graphics in hn4a-compositor shown live on the first short, sound effects and loudness. Nearly free: local cuts and renders plus a few cents of sound effects. For one long walkthrough from paired screen and webcam takes, use workflow-screen-recording-video.

SKILL.md

The person brings a long screen-plus-webcam recording (their own, or one they have permission to edit), two or three of their existing shorts as style references if they have any, how many shorts they want and any must-have moments. You deliver that many 9:16 shorts of 30–50 s, built only from the recording: the face in one half of the frame, an animated punch-in on what they're showing in the other, captions in their own shorts style, and motion graphics with sound on every beat.

Everything is local and free except a handful of sound effects (about $0.01 each). The picks and the style to match go where you keep the job's notes; rounds and deliverables follow the core skill.

Steps

  1. Watch, transcribe and pick the moments (guide-select-highlights-from-long-footage, route A): contact sheets of the recording and of the person's reference shorts (record the style to match with the job's notes: cut pace, caption face, case and colours, keyword colour, title cards), a sentence menu from the word times, and per short a hook a cold viewer gets, 5–9 whole sentences on one idea and a payoff, as sentence numbers plus the screen moment for each. Gate: the person approves the moments.
  2. Rough cut (ffmpeg, free). Each piece's edges in its pauses (guide-select-highlights-from-long-footage, Process 4). Render 1080×1920 split-screen pieces (the face crop and the screen crop, each scaled to 1080×960 and stacked), join them, and write a timeline.json (piece, source start and end, start in the short, text). Gate: the person watches the cuts for content.
  3. Zoom targets: for each piece, read exact rectangles (a header, a button, a stat) off grid-labelled frames at its start and end (ffmpeg-eased-punch-in, Inputs).
  4. The base video (ffmpeg-eased-punch-in): the face half plus one eased push or pan on the screen half per piece.
  5. Graphics (guide-add-titles-and-motion-graphics, hn4a-compositor-motion-graphics): one spec per short over the base video, its audio the spec's first track. Layers, bottom first: base video, per-piece graphics, the seam line, captions, title, progress bar, end card.
    • Captions: seam chunks (guide-caption-a-video) in the style's caption face, the keyword colour on a keyword list, centred on the seam.
    • Seam: a 6 px line in the accent colour with a glow, drawn under the captions.
    • Title: the short's name in the style's title face with a hard black shadow, popping in for the first 2 s; the same title at the end in the face half, sized to fit one line (about 1000 px ÷ its letter count, at most 80 px).
    • Per-beat graphics, cued 0.1 s before their word: pill badges (accent for features, red for problems), white name labels that wipe in, emoji pops with a small rotate, hand-drawn circles and arrows drawn on over 0.45 s, numbered labels for steps, and a typed-on card for any text they read out that's too small to read on screen. Badges last at most 2.4 s; place graphics by fractions of the screen half so they follow it when the face switches sides.
    • Progress bar (guide-pace-a-short-for-social, Pacing). Gate: the live spec (hn4a-compositor, Live spec, then render) on the first short; a yes on the look before building the rest.
  6. Sound (guide-add-sound-effects, elevenlabs-sound-effects): one sound per graphic type. Chime, pop and click rotating on badges; a game-show buzz on red badges; a click on labels; a marker scribble on drawn circles and arrows; a bubble pop on emoji; an 8-bit blip on the title and end card; one quiet whoosh (volume 0.2) only when the face changes sides; about 0.35 for the rest. Generate each once (0.5–0.7 s) and reuse across shorts.
  7. Render, level, deliver. hn4a-compositor render, one short a call, then loudness to the shorts platforms' level with the video copied untouched (guide-pace-a-short-for-social; ffmpeg-normalize-loudness; renders come out near −21). Check the frame count against duration × 30, that audio is present, and a 2 fps contact sheet. Deliver per the core skill: deliver the shorts.

Choices this workflow makes

  • The face changes halves once a short at most, on a beat.
  • Zooms in ffmpeg; the compositor only draws over the base.
  • Captions on the seam, so neither half loses its picture.
  • Built from the recording only: nothing generated, nothing that misstates what the speaker said.

Dead ends

  • An animated crop on a compositor video layer: the picture didn't fill its box (a strip at the top, or the face stretched across both halves). Render zooms in ffmpeg.
  • Swapping the face's side every piece: jumpy; the person asked for less.
  • A whoosh on every graphic: one sound repeated 8+ times grates within 20 s.
  • Static punch-ins on a whole UI window: unreadable on a phone.
  • Long renders dropped with the tool connection. Render one short a call and confirm the file exists before moving on.

Worked example

A 12-minute screen-plus-webcam recording about an app's dashboard became three shorts of 40, 43 and 43 s, 1080×1920 at 30 fps. The webcam box was already about 9:16 (445×790 px), so the face half was a 2.4× upscale: soft but acceptable (offer an upscale if the person minds). Style from three reference shorts: condensed caps captions with one keyword colour, a pixel-style title face.

The person's notes over two rounds (paraphrased), each now a default above:

NoteFix
Switch the face's half less oftenOnce a short at most
Zoom tighter on the important thingPush onto one element
Far more motion graphicsPer-beat badges, labels, emoji, drawn arrows
Open on the orienting lineOrientation first, then the clever line
Vary the sound effectsOne sound per graphic type
Put the line behind the captionsSeam drawn under the captions

Cost: $0.08 in sound effects; everything else ran locally.

Related workflows

FAQs

Turn a stream, tutorial, podcast or any long screen-plus-webcam recording into a series of 30–50 s 9:16 shorts built only from that recording: the speaker's face in one half, eased punch-ins on the right part of their screen in the other, captions on the seam in their own shorts style, and word-cued motion graphics with a different sound for each kind. Covers watching the recording and the speaker's existing shorts, a transcript with word times, picking the moments (hook, whole sentences, payoff), the rough cut, zoom targets, the base render in ffmpeg, the graphics in hn4a-compositor shown live on the first short, sound effects and loudness. Nearly free: local cuts and renders plus a few cents of sound effects. For one long walkthrough from paired screen and webcam takes, use workflow-screen-recording-video.

Install Hypernatural Desktop, a free Mac app, and connect it to Claude Code, Codex or Claude Desktop. Then describe the video you want and your agent finds the workflow itself, or paste this page's link (https://hypernatural.ai/skill/hn/workflow-shorts-from-long-video) and it installs hn/workflow-shorts-from-long-video and follows it.

It runs ElevenLabs sound effects. Hypernatural Desktop has every one of them built in, so there are no API keys to set up, though you can bring your own.

The workflow is free. You only pay for the AI generations it runs, and your agent shows you the price of every batch before it spends anything. Editing, captions and titles run on your Mac at no cost.

It calls 12 smaller skills for its steps, including Hn4a compositor, Python read word timings and Ffmpeg eased punch in. Each one is listed on this page, and your agent loads them as the job needs them.

Yes. Ask your agent to adjust it for your job, or to save its own version. You can publish your version under your own handle so anyone can install it.

Go make something cool.

Install the app, open your agent, describe the video. That's the whole onboarding.

Sticker HypernaturalSticker BannerSticker TVBoy