This skill reads a Chinese article, picks the few paragraphs that carry a key judgment, process or turning point, and turns each into one white-background, hand-drawn 16:9 illustration. The recurring character is Xiaohei, a solid black figure with dot eyes and thin legs, who must take part in the main action of every picture.
It first produces a shot list (where each image goes, its theme, the structure type and suggested labels), and when you ask for images it generates them one at a time with the built-in image tool and saves them in your workspace. The instructions are in Chinese.
What You Get
- A shot list with placement, theme, structure type, Xiaohei’s action and suggested Chinese labels
- One 16:9 PNG per chosen anchor point, generated separately
- Files saved as numbered PNGs under an assets folder named after the article
- A short delivery note listing each image’s purpose and which ones are safest
- Image edits such as removing a stray title or a wrongly written character
Common Use Cases
- Illustrate a Chinese blog post or newsletter with a consistent hand-drawn look
- Turn a method or workflow document into a few explanatory pictures
- Plan illustrations first, without generating anything, and review the shot list
- Remove an unwanted heading from a generated image and keep the rest
What Makes It Unique
The skill is about one mascot with fixed rules and one drawing style, and it tells the agent to reinvent the metaphor for each article and never copy the sample compositions. It includes a QA checklist that rejects images where the mascot is only decoration, the page is too full, or the result looks like a slide.
Under The Hood
SKILL.md is the entry point and points to reference files for style, the mascot, composition patterns, a prompt template and a QA checklist, which the agent reads as needed. The skill has no scripts. The agent reads your article, link or Notion page, calls the built-in image generation tool once per picture, checks each result against the checklist, regenerates when it fails, and copies the final PNGs into an assets folder in your workspace without overwriting existing files.