linyuebanzi-skills
Five illustration skills: article diagrams, educational infographics, voiced animations, video covers and image generation.
- 81 ★ on the repository
- Last commit
Extended access
Why this level
- Skills send texts and prompts to external image and voice services with your keys.
- Video runs scripts, `ffmpeg` and browser rendering.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/linyuebanzi-skillsDetects 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.
- Skills send texts and prompts to external image and voice services with your keys.
- Video runs scripts, `ffmpeg` and browser rendering.
This is third-party code. Review the repository files before installing.
What it does
A collection of Claude Code skills by the author of a Chinese AI blog. `linyuebanzi-inline-diagram` finds illustration spots in a 3000–8000 character technical text and makes 4–5 diagrams in one of eight styles. `linyuebanzi-edu-infographic` turns a school-subject topic into a vertical 9:16 infographic. `linyuebanzi-teaching-animation` builds a voiced video of about 90 seconds or a silent looping animation of about 32 seconds from a topic, rendered through HyperFrames. Two more skills: `linyuebanzi-video-cover-generator` makes short-video covers and `linyuebanzi-image-gen` does general image generation. Pictures come from external APIs and one of three keys is enough.
Who it is for. Technical bloggers and teachers who want diagrams, infographics and short teaching clips from Claude Code.
Good fit when
- A 5000-character article looks dull and you ask for diagrams in a notebook-sketch style.
- You need an infographic on the Pythagorean theorem for a math lesson.
- An explanation of Ohm law must become a video with voice-over and subtitles.
- A short clip needs a cover in the chosen style.
Not a fit when
- You have no key for any of the supported image-generation services.
- You need Russian text and captions: skills and examples are written for a Chinese audience.
- Node.js and ffmpeg are missing for video rendering.
Example request
Add four diagrams in a notebook-sketch style to this article and show where to insert them.Limitations
For pictures you need one of three keys: `MULERUN_API_KEY`, `APIMART_API_KEY` or `ATLASCLOUD_API_KEY`, and the service is detected automatically. Voice-over needs `MINIMAX_API_KEY`, and some accounts also need `MINIMAX_GROUP_ID`. Videos and animations need Node.js 22 or newer and ffmpeg, and HyperFrames is fetched through `npx`. The README, examples and voice-over target Chinese. The repository has no license file and the author states no reuse rights.
How to disable. Delete the `linyuebanzi-*` skill folders from the skills directory or remove them through `npx skills`. Remove the key variables from your environment.
FAQ
How do I install the collection?
With `npx skills add lqshow/linyuebanzi-skills`. The `-g` flag installs globally, `-s linyuebanzi-inline-diagram` takes one skill and `--list` shows what is available.
Which styles does the diagram skill have?
Eight: notebook, infographic, executive-tech, cozy-handdrawn, tech-doodle, cartoon-infographic, whiteboard-sketch and saas-flat. The skill asks for a style before generating.
How does the voiced video differ from the animation?
The video runs about 90 seconds in 1080p with Chinese narration and subtitles, the animation about 32 seconds, silent and looping. Both come from one 7-part storyboard.
Is a key needed for voice-over?
Yes, `MINIMAX_API_KEY`, and on some accounts `MINIMAX_GROUP_ID` too. Pictures use separate keys and one is enough.
Which Node.js version is required?
Node.js 22 or newer and ffmpeg for videos and animations. HyperFrames is fetched through `npx` automatically.
Discussion
No questions or reviews yet.
Related
SkillsSkills give Claude Code three ways to make images: code-drawn graphics, Three.js 3D scenes and Flux diffusion on Cloudflare.
Five image-generation skills: Qwen-Image prompts, logos with shared geometry, diary comics, transparent PNGs and process dioramas
Twenty-eight skills for Claude Code: voiced video, covers, WeChat layout, Excel, PPT, Dify, GitHub Trending
Two Claude Code skills for videos made entirely in code: hand-painted watercolour animation and kinetic typography reels
A Claude Code skill for hand-painted animation and lyric videos: frames drawn in code with p5.js, no image models
A skill that paints pictures with Python code and no image model: 77 styles from ink wash to cyberpunk, with reproducible results.
README in short
A collection of five skills with style previews and examples. Each is called from chat with a phrase such as "make an animation on this topic".