Short-Form AI Video Prompt · Claude Skill

AI video prompts
that actually
render right.

Tool-calibrated. Camera-specific. Platform-ready.

Vague prompts waste generation credits. This skill writes structured prompts calibrated to your tool, platform, and scene.

Short-Form AI Video Prompt is a Claude AI skill that writes structured AI video prompts for Kling, Seedance, and Higgsfield — calibrated to scene, platform, tool, and camera energy.

⚡ Replaces 5–8 hours of scripting and tool calibration — runs in under 10 minutes.
Get this skill — $19
Output preview — Short-Form AI Video Prompt
Kling 3.0 · Product Reveal
Single-shot product reveal. Director-framed.
Prompt (9s · 9:16 · Kling 3.0)

Camera slowly dollies in on a matte black glass bottle resting on a wet stone surface. Soft morning light rakes across from the left, catching water droplets. The bottle label sharpens into focus at 4 seconds. Shallow depth of field. Photorealistic. Film grain. No camera shake.

Negative prompt: morphing, watermark, text overlay, jittery motion, overexposed highlights, lens flare
Single concern per prompt — camera motion only. Label reveal timed explicitly. Physics named: water droplets, wet stone.
Seedance 2.0 · Multi-Shot
Three-shot brand narrative sequence.
Prompt (15s · 16:9 · Seedance 2.0)

Shot 1 (0–4s): Extreme close-up of hands wrapping a gift. Warm tungsten light. Fabric moves naturally as paper folds.

Shot 2 (5–9s): Medium shot — recipient opens the box, eyes widen. Soft bokeh background. Handheld with subtle shake.

Shot 3 (10–15s): Wide pull back to reveal a warmly lit living room. Tracking shot. Golden hour through window.

Style bible: warm grade, 24fps, cinematic aspect ratio, no flash cuts
Multi-shot native format for Seedance 2.0. Each shot has one motion concern. Style Bible appended for brand consistency.
Higgsfield · Lifestyle Reel
Camera stacking for a cinematic social ad.
Prompt (6s · 9:16 · Higgsfield Cinema Studio)

A runner breaks through early morning mist on a coastal path. Crane shot rises and pushes forward simultaneously. Hair physics. Breath visible in cold air. Desaturated teal grade, crushed blacks. Realistic physics. Golden rim light from horizon.

Negative prompt: slow motion, morphing body, watermark, overexposed sky, text
Multi-axis camera stacking (crane + push) enabled on Higgsfield. Physics named three ways: hair, breath, realistic. Lighting defines production value.
Platform variants · Aspect ratios
Same prompt, three platform formats.
Instagram Reel / TikTok → 9:16 vertical · 6–9s
YouTube Shorts → 9:16 vertical · up to 15s
LinkedIn / Brand site → 16:9 landscape · up to 15s
X (Twitter) → 16:9 or 1:1 · 6s recommended
Pinterest → 2:3 portrait · 6–9s
Aspect ratio and duration included in every prompt output. Wrong ratio wastes generation credits.
Full output
What you receive
✓ Primary prompt — tool-calibrated and camera-specific
✓ Negative prompt — prevents the most common AI video failures
✓ Multi-shot variant (where applicable to tool)
✓ Platform aspect ratio + duration specified
✓ Style Bible block — reusable across a video series
✓ Tool optimisation note — Kling / Seedance / Higgsfield
✓ Tool disclaimer — credit cost and model update caveat
1 / 5
How it works

How does Short-Form AI Video Prompt work?

  1. Tell Claude what you need — the skill asks 2-3 narrowing questions specific to the task.
  2. The skill runs live research and structures the output before writing a single word.
  3. An anti-slop quality gate checks the draft, then delivers a ready-to-use result for $19.
What you get

Why this prompt
renders right.

🎬
Tool-calibrated. Kling, Seedance, and Higgsfield each get a different prompt structure.
Tool-specific
📐
Platform and aspect ratio locked in every output. No wasted generation credits.
Platform-ready
🎥
Camera vocabulary built in. Dolly, crane, rack focus — models respond to specifics.
Cinematic language
🛡️
Negative prompt included. Blocks the frame morphing, watermarks, and jitter that ruin renders.
Anti-artifact gate
Who it's for

Built for anyone
making AI video.

✓
Social media managers producing short-form content at scale.
✓
Brand agencies running Kling or Seedance for client campaigns.
✓
Video creators and indie filmmakers using Higgsfield or Kling.
✓
D2C brand owners creating product reveal and lifestyle content.
Not what this is for
✕Long-form video — this is built for short-form up to 15 seconds.
✕Text-to-image prompts — output is optimised for video generation tools only.
✕Video editing or post-production — it writes the generation prompt, not the edit.

The complete guide to ai video prompt covers what makes a calibrated output different from a generic one.

The complete guide to short-form ai video prompts covers what makes a vertical video prompt versus a generic script.

"First Kling prompt came out better than anything I'd written myself. Saved two hours of credit-burning trial and error on the first use alone."
JC
Jordan C.
Social media manager, Los Angeles · Video/Pod Bundle
Get it now
AI video prompts
that render.
$19.

Instant download. Works with your free Claude account. 7-day refund if it's not what you expected.

Buy Short-Form AI Video Skill — $19 Video/Pod Bundle — $69
Video/Pod Bundle includes
Short-Form AI Video Prompt
Video Script
Podcast Episode Script
Podcast Show Notes & SEO
Webinar / Online Event Script
AI Animation Film Prompt
Save ~39% vs buying individually
$69 for all 6 skills
🛡️ 7-day money back guarantee · no questions asked
Quick answers

Do I need a paid Claude account for Short-Form AI Video Prompt?

No. The free Claude plan is enough to get started and see the skill working. A Pro plan unlocks longer outputs.

How do I install the Short-Form AI Video Prompt skill?

Download the .skill file, open Claude, go to Customize → Skills → Upload a skill, and drop the file in. It appears in your slash-command list immediately.

Can I edit or customise the output after I receive it?

Yes. The output is plain text you own and can edit freely. Most users tweak specific details or the call-to-action to fit their exact use case before sending or publishing.

How specific do my inputs need to be to get a good result?

The more specific your input, the more precise the output. The skill asks targeted questions to gather context — answering these in detail produces noticeably better results than generic one-line inputs.

Free skill
Try NovaKit before
you spend a dollar.

Get the LinkedIn Post Engine free — the same skill that runs live trend research before every post. Drop your email and it lands in your inbox in seconds.

💼
LinkedIn Post Engine
Social · normally $9 · free today
✓Live trend research before every post
✓Hook variants calibrated to what's converting this week
✓Works on a free Claude account

No spam. No account. Unsubscribe any time.