Niwo Render Everything skill
A skill turns a PDF, article or chat into a short-video bundle: voice-over text, footage, ffmpeg cuts and a ZIP for Niwo.
- 273 ★ on the repository
- Last commit
Extended access
Why this level
- The skill downloads files from the web, runs `ffmpeg` and contacts a server for its version.
- Material goes to the third-party Niwo service when the archive is uploaded.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/niwo-render-everythingDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill downloads files from the web, runs `ffmpeg` and contacts a server for its version.
- Material goes to the third-party Niwo service when the archive is uploaded.
This is third-party code. Review the repository files before installing.
What it does
Niwo Render Everything is a skill for agents with a terminal. It takes a PDF, article, web page, Word file or a chat topic, agrees the voice-over text with the user, finds and downloads real images and video, cuts clips with `ffmpeg`, fills `content.json` and `manifest.json` and packs everything into a ZIP. The skill does not produce the final video. The archive is uploaded to the Niwo service (`niwo.studio/video-studio`), which renders it. Before work the skill runs `skill_update.py` and checks its version against the server.
Who it is for. Short-video authors who need to turn source material into a draft bundle fast, and users of Niwo.
Good fit when
- A report or article needs a video about its key points.
- Real footage and B-roll are downloaded at once, not left as links.
- Voice-over is agreed before shots are assembled.
- Second-by-second cutting goes to `ffmpeg`, not a manual storyboard.
- A bundle is prepared for the Niwo service before upload.
Not a fit when
- A finished video is needed without a third-party render.
- The agent cannot download files or run `ffmpeg`, as in most mobile chats.
- Rights to the downloaded images and clips have not been checked.
Example request
Turn this PDF into a short-video bundle: propose voice-over text, download footage and assemble the ZIP.Limitations
Documentation and much of the skill are in Chinese. The final video is created only in the Niwo service, currently in closed beta. Network access, `ffmpeg`, `ffprobe` and ZIP packing are required. The skill downloads third-party images and video, and the user checks rights to them. README compatibility is tested on ChatGPT and Codex, and the other agents are untested. Downloading large clips takes a lot of time and disk space.
How to disable. Remove the skill with `npx skills remove niwo-render-everything` or delete its folder from the agent skills directory, and erase generated bundles.
FAQ
Does the skill make the video itself?
No. It prepares a bundle with text, footage and cuts, and the video renders in Niwo after the ZIP is uploaded.
Which agents fit?
Those that download files, run `ffmpeg` and pack a ZIP: Codex, Cursor, Claude Code, WorkBuddy and ChatGPT work mode. Ordinary chats do not.
How is the skill updated?
With `npx skills update niwo-render-everything -y`. Before each job the skill checks its own version.
Is a Niwo account needed?
Rendering requires an upload to `niwo.studio/video-studio`. The service is in closed testing, with accounts issued to members of its user group.
What does it need to run?
The agent needs network access with file downloads, `ffmpeg` with `ffprobe` and ZIP packing.
Discussion
No questions or reviews yet.
Related
SkillsA skill that turns a topic into a narrated 4K video: research, script, local TTS, Remotion composition and an FFmpeg mix
A skill that turns your narration and real assets into a 20–60 second video in the style you pick, rendered locally as MP4.
A skill that makes video in pure code: narrated explainers and website promos in 35 visual styles, in 16:9 and 9:16.
The video-explainer skill turns a script into a vertical 9:16 explainer: narration, captions, Remotion and a pre-render review
A skill that turns a Bilibili, Douyin or YouTube video link into timestamped notes through local transcription
A skill that turns narration text into a 20-second chunky-pixel explainer at 1920×1080 with voice-over and an editable project.
README in short
The version is checked once per task, with exit codes 0, 3, 10 and 20 deciding whether to continue, offer an update or stop.