Who it is forA creator who wants to continue an existing film with a new passage and keep its style and timing consistent.
The problemAdding a scene to a finished film risks breaking its timing, determinism and visual style.
The outcomeA revised Window Seat film with the new scene, checked for determinism and inspected as frame strips.
What you need first
- Git, to clone the repo
- npm, since the setup runs npm install and npm run setup
- Claude Code, the coding agent the README names for making new works
- A web browser, to open the index.html files and press play
Steps
git clone https://github.com/sevenevesai/riso-windowseatcd riso-windowseat/toolsnpm install && npm run setup && npm test- Read films/window-seat/FILM.md so you know the existing timeline and its design decisions.
- Open Claude Code in the repo root and ask for the change, for example "Extend Window Seat with a snowy mountain pass after the lake."
- Check the new passage in the frame strips and contact sheets rendered by tools/ and open the index.html to play it.
Prompt for your agent
In the riso-windowseat repo, extend films/window-seat/ with <new scene description> using the riso-film skill and its gates. Expect an updated index.html and a revised FILM.md. Verify with the determinism hook and the frame strips that the existing timeline from 0 to 78 s still holds.
Caveat. The repo states that the piano in Window Seat is licensed CC BY 3.0, so any change to its audio must keep that attribution intact.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page