onetake builds short motion films about a product from the product itself. The agent deconstructs a reference clip into numbers, proposes three concepts that differ in their central picture, writes a beat sheet for rhythm and carry, and composes one HTML file where every value is a function of time, using a library of measured moves.
Frames are rendered with shutter motion blur at 1080p30 for drafts and 4K60 for finals, sound is synthesized in one shared room, and a verification script fails films whose beats replace each other. The repository is licensed for noncommercial use, with a separate paid commercial option.
What You Get
- A single HTML composition driven by a seek function, built on a library of about 39 measured moves
- A draft render at 1080p30 and a final render at 4K60 with real motion blur
- A synthesized or recorded sound score timed from the composition’s own events
- Optional narration with word timings, subtitles and extra languages from the same composition
- A verification report on rhythm, continuity, motion curves and framing
Common Use Cases
- Making a 15 second launch video for an app, a page or an agent skill
- Building a narrated feature demo from screenshots without recording the screen
- Producing the same film in several languages from one composition
- Finding out why an existing motion video feels like a slideshow and fixing it
What Makes It Unique
Most video tools stack scenes. This skill designs the boundaries and measures them: a probe script scores what carries across each cut and the film fails when beats simply replace each other. It also forbids defaulting to a template story or a previous look, requires three distinct concepts, and ships case studies recording what each rejected cut taught.
Under The Hood
The skill ships Python scripts, a JavaScript motion library and templates. The agent runs Python scripts that drive headless Chromium with Playwright to record real pages and capture frames, uses ffmpeg to encode video, and renders in parallel browser processes. Narration uses local speech tools, and recorded sound sources are downloaded separately by the user. It writes footage, stills, audio and video files to your working folders, and the package it needs must be installed on your machine.