Log in
WorkflowBy HypernaturalVersion 4, updated

News article to vertical short

hn/workflow-news-article-to-vertical-short

Turn one news article into a ~45 s vertical (9:16) explainer short: a sourced script with the conflict in the first 3 s, 9–10 stylized visual-metaphor scenes animated on H3 Max, a quick creator-style narrator, then karaoke captions, a title bar and stickers that slam in on the key words, composited with hn4a-compositor in a chosen brand. Covers picking the story with the person (and its risks), keeping only facts traceable to the source, no likeness of real people, three looks, stills, voice auditions on the whole script with word times, shot timings on the 24 fps grid, locking what must not change in the video prompts, the cut and the live layout gate. About $7 and an hour. For same-day news shorts, newsletter-to-video and social explainers about a story; for a post's own argument retold as a paper-cut story, use workflow-blog-post-to-animated-short.

SKILL.md

One public article in; a ~45 s 1080×1920 explainer out: a narrator over 9–10 stylized, animated scenes, with karaoke captions, a title bar and stickers that slam in on the key words. Every look is a gate the person sees before money is spent on it. About $7 (stills about $1, voice about $0.25, animation about $5) and an hour.

The job folder: source/ refs/ stills/ video/raw audio/ titles/ scripts/ rev1/. Record the story, the picks and the spend where you keep the job's notes; rounds and deliverables follow the core skill.

Steps

  1. Pick and source the story (llm-source-a-news-story): two or three of the day's stories put to the person with their fit and risk, then source/article.md with only the facts the script uses, each traceable to the article.
  2. Script and shot list (guide-make-a-script-from-source, a source to retell): about 110 words for 45 s at a creator read.
    • The hook is conflict, then counter (llm-write-a-hook).
    • Shape: hook → what the thing is → the big number → the catch → the cracks (2–3 facts) → the pushback → an open question to end on.
    • One shot a sentence, 9–10 shots of 2.5–6 s; the last can hold about 10 s. Each a visual metaphor, with no likeness of real people and no logos (llm-pick-a-visual-metaphor); recognizable people or places switch to guide-depict-real-people-and-places. Gate: script.md (the VO and a shot table: visual, animation).
  3. Look (guide-pick-a-stylized-look, Process steps 1–2): three style frames of shot 1 at 9:16. A good spread: paper collage (editorial), two-colour risograph (graphic), claymation (style-claymation: toy-like, the clearest "generated, not motion graphics" look, and it animates cleanly). Gate: a review_choose of the three looks.
  4. Stills, all at once, from the picked frame (guide-pick-a-stylized-look, Process step 4), "9:16 vertical. No text, numbers, logos or lettering anywhere." Gate: a review_choose per shot, all in the same turn.
  5. Voice (guide-voice-a-script, A narrator for a short): a quick conversational creator read, three whole-script auditions, each checked free; the pick is the take. Tags that suit a creator read: [confident, quick], [pointed], [matter-of-fact], [wry], [dryly], [thoughtful], [short pause]. Gate: a pick; if the person delegates it, take the fastest clean read.
  6. Shot windows from the alignment (ffmpeg-cut-clips-to-a-voiceover, --plan): split a long hook sentence pair into two shots; ask each clip at its window's length.
  7. Animate (guide-pick-a-stylized-look, Process step 5; h3-max-image-to-video, 768P, a fixed seed), all at once on a price. Hook shots: a fast push-in "with large amplitude" and a shudder on arrival, or a sudden action in the first second; reusing the ending's still for a hook shot sets up the payoff.
  8. Picture cut (ffmpeg-cut-clips-to-a-voiceover, 1080×1920, the clips at about 0.22), then −16 LUFS (ffmpeg-normalize-loudness), and its checks.
  9. Captions and graphics (guide-capture-a-brand when it should match a brand, guide-add-titles-and-motion-graphics): a build script with the helpers in hn4a-compositor-in-scene-titles over the picture cut, cues from the alignment.
    • Karaoke captions (guide-caption-a-video, the 9:16 karaoke row), uppercase, the respellings mapped back after uppercasing ("2030s", not "2030S"; the brand name, not its TTS respelling).
    • Title bar (hn4a-compositor-chyron, title_bar): the story's name across the top, the key number in the accent, on for the whole video.
    • Stickers: a chunky rounded tag (accent fill with dark type, or dark fill with an accent border), rotated ±3–7°, slamming in 0.08 s before its word and fading at the shot's cut, one or two a shot on the numbers and turns of the story, in y 300–1100. A near-empty progress bar for "only a sliver", chips over the two sides of the final comparison, a big "?" on the last word.
    • Dark gradients behind the top 360 px and the bottom 740 px. Stills at every sticker, checked for overflow and collisions. Gate: the live spec (hn4a-compositor, Live spec, then render), with the stills; then the render and its checks.
  10. Deliver per the core skill: deliver the cut. On a later round's reviews, pass the round before as previous. For an outreach or gift video, draft the note the person sends (llm-draft-a-gift-video-note).

Choices this workflow makes

  • Only facts in source/article.md reach the script. Every number on a sticker traces to the source.
  • Metaphors, not likenesses (llm-pick-a-visual-metaphor); a brand's logo stays off a piece that isn't theirs.
  • A creator read and the conflict up front, for social.
  • The audition is the take (guide-voice-a-script), so the word times come free with the pick.

Dead ends

  • Unlocked prompts, big lighting changes on 2.1 edit and a stills rejection with no note: all first met on this workflow; the fixes are in guide-pick-a-stylized-look (Avoid).
  • text-transform: uppercase on a sticker capitalised the units; wrap lowercase units in <span style="text-transform:none">.

Worked example

A same-day short about a city's stadium plan, from one public article. 1080×1920, 24 fps, 45 s, 10 shots, clay 3D picked from collage, risograph and clay style frames.

PartShotsPictureOver it
Hook1–2A clay stadium model slams onto a desk; a budget scale tipstitle bar, the year as a sticker
The thing and its number3–4A coin tower risingthe cost sticker
The catch and the cracks5–7The tower wobbles; a puppet on stringsfacts as stickers, a near-empty progress bar
Pushback and the question8–10Two sides of a scale, held 10 schips on each side, a "?" on the last word

Notes on the way: the first opener was a slow scene-setter and was replaced by the conflict-and-counter hook; the sky and an empty building changed mid-clip and were re-rendered with lock lines; one shot's stills came back rejected with no note and the shot whose metaphor didn't read was retaken first.

Spend: stills about $1, voice about $0.25 (three whole-script auditions), animation about $5 at 768P: about $7, in about an hour.

Related workflows

FAQs

Turn one news article into a ~45 s vertical (9:16) explainer short: a sourced script with the conflict in the first 3 s, 9–10 stylized visual-metaphor scenes animated on H3 Max, a quick creator-style narrator, then karaoke captions, a title bar and stickers that slam in on the key words, composited with hn4a-compositor in a chosen brand. Covers picking the story with the person (and its risks), keeping only facts traceable to the source, no likeness of real people, three looks, stills, voice auditions on the whole script with word times, shot timings on the 24 fps grid, locking what must not change in the video prompts, the cut and the live layout gate. About $7 and an hour. For same-day news shorts, newsletter-to-video and social explainers about a story; for a post's own argument retold as a paper-cut story, use workflow-blog-post-to-animated-short.

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-news-article-to-vertical-short) and it installs hn/workflow-news-article-to-vertical-short and follows it.

It runs Nano Banana 2.1, Nano Banana Pro, MiniMax H3 Max and ElevenLabs voice. 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 27 smaller skills for its steps, including Llm source a news story, Hn4a compositor and Pick a stylized look. 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