Generate Video: Turn a Brief Into a Finished AI Video
Drop in your script and clips, get back an edited, captioned, ready-to-post video.
It reads your brief and the clips or images you provide, pulls key lines into on-screen captions, assembles the edit, and hands back a finished vertical video file.
Any AI assistant that can read a SKILL.md file (Claude, Claude Code, Cursor, or Codex). No separate app, no account, no subscription, and no API key required from you to get started.
Works with
Generate Video is an AI video maker skill you drop into your own AI assistant to turn a short brief into a finished, edited clip. Instead of learning a timeline editor, you hand it your script (or copy) plus the video and image assets you already have, and it does the assembly for you: it lifts the strongest lines into clean on-screen captions, layers your footage and photos with fade transitions, syncs narration if you provide an audio track, and renders a vertical video ready for Reels, TikTok, or Shorts. It is a text to video and clips to video workflow built for people who want the output, not the software. Works inside Claude, Claude Code, Cursor, and Codex, and it always confirms with you before it renders.
- Go from a written brief to a finished, edited video without opening a video editor
- Get a vertical 9:16 file sized for Instagram Reels, TikTok, and YouTube Shorts
- Automatic on-screen captions pulled from the strongest lines in your copy
- Your own clips and images assembled with clean fade transitions, no manual timeline work
- Optional narration synced to the edit when you add an audio track
- A repeatable process any team member can run from plain instructions
- 1Drop the skill into your assistant
Add the SKILL.md file to Claude, Claude Code, Cursor, or Codex. There is nothing to install, no account to create, and no API key needed from you to begin.
- 2Give it your brief and assets
Point it at a short script or copy plus the clips and images you want to use. An audio or narration file is optional. If anything it needs is unclear, it asks before doing anything.
- 3It plans the edit
The skill reads your copy, extracts the key phrases for captions, and organizes your footage and photos into a sequence with fade transitions.
- 4It confirms before rendering
You approve the plan first. The skill never renders or overwrites an existing video without checking with you, so you stay in control.
- 5It assembles and renders
It builds the edit, layers captions over your media, syncs narration if provided, and produces the video for you while reporting progress.
- 6You get the finished file
You receive a ready-to-post vertical MP4. If no audio was supplied, it delivers a clean silent cut and tells you so you can add sound later.
- A finished vertical 9:16 MP4 video sized for Reels, TikTok, and Shorts
- On-screen text captions drawn from your script or copy
- An edited sequence of your clips and images with fade transitions
- Optional synced narration when you provide an audio track
- A clean silent cut when no audio is supplied, flagged for you
Captioned social cut
Turn a caption or script into a short, captioned vertical video using stock or your own clips, ready to post.
Narrated explainer
Add a voiceover track and the skill syncs the narration to your footage and captions for a talking-style explainer.
Batch from multiple briefs
Point it at several briefs, each with its own assets, and it renders a separate finished video for each one.
SKILL.md · README.txt · LICENSE.txt — Single-seat commercial use. Do not resell or redistribute the file. Compatible with Claude, Claude Code, Cursor, Codex.
What is the Generate Video skill?
It is a SKILL.md file you add to your AI assistant that turns a brief plus your clips and images into a finished, captioned, edited vertical video. You supply the script and assets, and it handles the assembly and rendering.
Does it work with Claude, Cursor, and Codex?
Yes. It runs in any assistant that reads a SKILL.md file, including Claude, Claude Code, Cursor, and Codex. The workflow is the same across all of them.
Do I need to install anything or have an API key?
No separate app and no account are required, and you do not need an API key from you to get started. You just drop the skill file into your assistant and give it your brief and media.
Do I need video editing or coding skills?
No. You describe what you want and provide your script and clips in plain terms. The skill picks the captions, sequences the media, and renders the video, so you never touch a timeline.
What format is the output video?
A vertical 9:16 MP4 sized for Instagram Reels, TikTok, and YouTube Shorts, with captions layered over your footage and images.
Will it change or overwrite my files?
No. It confirms the plan with you before rendering and does not overwrite an existing finished video without telling you first.
An AI skill is a small, reusable instruction file (a SKILL.md) that teaches an AI assistant to do one job well. Generate Video is exactly that: a Claude skill / AI agent skill you drop into your own assistant and run on demand, with no app, no subscription and no lock-in. You own the file forever.
It runs in Claude, Claude Code, Cursor, Codex and any assistant that reads a SKILL.md or a system prompt. Because it is just text, it is fully portable, and if it needs something to run, generate video asks you for it first instead of inventing.
Creators reach for it as a podcast clips AI and an AI podcast clip generator, to turn a podcast into Shorts and to pull podcast highlights automatically, finding the best podcast moments without scrubbing the whole episode.
- Download the file after checkout you get the SKILL.md plus a short README and your license.
- Add it to your AI drop SKILL.md into your skills folder (for example
.claude/skills/) or paste its contents as a custom instruction. - Run it ask your AI to use Generate Video, give it what it asks for, and it does the work.
Get this skill plus every other one in a single agent bundle, ready to drop into your AI.
Ready to run Generate Video?
Generate Video
It reads your brief and the clips or images you provide, pulls key lines into on-screen captions, assembles the edit, and hands back a finished vertical video file.
SKILL.md (plain text, nothing runs on your machine) plus a README and your license.Checkout opens soon. Get early access and I will send you the link the moment it is live.
✓
You are on the list.I will email you the moment it is live.
