Startup Ideas Bank
A slick video-making skill, but it is still a tool looking for a buyer who pays.
AI roast score: 62/100 (C)
The idea
This is not a company yet. It is a very polished pile of shot cards for people who already know how to make product videos and already have a reason to pay for them.
In the founder's own words
Vincentwei1021/video-shotcraft — AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 106 shot recipe cards, 161 motion previews, a production-ready template
video-shotcraft
An agent skill for crafting cinematic product videos: 104 shot recipe cards · 161 styles · 161 motion previews · a production-ready template
English | 中文 | 日本語
video-shotcraft is an AI agent skill that turns Claude Code or Codex into a
motion-design studio: point it at your product and it storyboards, animates, and
sound-designs a cinematic promo, marketing, launch, or demo video with
Remotion — real page captures, 2.5D camera moves,
beat-synced cuts, and film-grade SFX included.
🖼️ Browse all 161 motion previews in the live Gallery »
🎬 Showcase
The 38-second Gallery intro below was itself produced with this skill —
storyboard, shot implementation, and sound design were all done by an agent
following the toolkit's methodology:
skill-demo-upload-v2.mp4
▶️ Watch in HD on YouTube
Browse every shot card and motion preview online: Gallery
— search, filter, switch between variants, and copy selected shot-card names.
🚀 Quick start
The most direct way: hand the repo link to your agent.
In Claude Code / Codex or a similar agent, just say:
Install this skill for me: https://github.com/Vincentwei1021/video-shotcraft
The agent will clone the repo and link it into your skills directory. Or install
with the skills CLI / manually:
npx skills add Vincentwei1021/video-shotcraft
git clone https://github.com/Vincentwei1021/video-shotcraft.git
cd video-shotcraft
ln -s " $( pwd ) " ~ /.claude/skills/video-shotcraft # Claude Code
# or
ln -s " $( pwd ) " ~ /.codex/skills/video-shotcraft # Codex
Then make requests like:
Use video-shotcraft to create a promo for my desktop product.
Use the deck-deal-flyin and row-embed shot cards to present this feature.
Design a product close-up inspired by spotlight-hero-card.
If no shot card is specified, the skill introduces the built-in video template
first and asks whether to use it; you can also pick shots in the
Gallery before starting.
📼 Video template: Ink Press
The skill ships with Ink Press — a validated, complete promo template:
36.2 seconds, 1920×1080, 30fps, 10 shots in a paper-ink-amber style, with 2.5D
real-page camera moves, title cards, transitions, and a fully pinned cinematic
SFX pass:
template-final-upload.mp4
▶️ Watch in HD on YouTube
To use it, just tell your agent:
Use video-shotcraft to make a promo for my product with the Ink Press template.
The agent swaps in your product's screenshots, copy, and branding to reproduce
the same quality — the fastest, most reliable path to a finished film.
More templates are on the wa
The roast
You built a nice toolbox for a narrow job: making cinematic product videos inside Claude Code or Codex. The problem is that the pitch screams craft, not pain. “106 shot recipe cards,” “161 motion previews,” and a “production-ready template” are assets, but they are not proof that anyone will buy this instead of using a freelancer, a template pack, or a general video tool. Your own setup makes the risk sharper. You are a solo founder, you are using software only, and your biggest unknown is whether people will pay. That means the real business question is not whether the output looks good. It is whether enough creators, developers, or marketing teams will trust an agent skill to replace a human motion designer or a simpler video tool. Right now the buyer is still fuzzy, and fuzzy buyers do not convert. The global angle also cuts both ways. Global software can scale, yes, but it also means you are fighting everyone at once: template sellers, AI video tools, and design platforms. Your moat claim is speed and data, but the pitch does not yet show why your shot library will stay ahead once others copy the format. Without a clear wedge, this can become a nice open-source demo that gets admired and ignored.
Red flags
- The product is impressive, but the buyer is still vague: creators, professionals, and developers are three different peo
- Your biggest unknown is whether people will pay, which means the core business is still unproven, not the feature set.
- The moat is claimed as speed and data, but the pitch does not show why 106 shot cards and 161 previews cannot be copied
Verdict
Narrow the buyer, prove they will pay for one repeatable video outcome, and stop selling a library as if it were a business.
Start with your own startup idea →
More ideas roasted by AI
- This is a clever developer tool, but right now it is mostly architecture poetry with no proof that anyone will care. 62/100
- A gimmicky 3D scroll world for every brand? More fluff than substance. 62/100
- Interesting tech, but unclear on market fit and execution. 62/100
- PyroSense AI sells fire prediction to industries that will only pay once someone proves it works, and nobody has proven that yet. 48/100
- A well-built, free, open-source TV launcher with no revenue plan and an install that needs developer mode and a laptop. 38/100
- You built a clever way to run Blizzard's game on phones, and Blizzard and Nintendo own every lever that can shut it down. 22/100