Core Positioning
Design and generate 16:9 horizontal body illustrations for Chinese articles. The goal is not to make commercial illustrations, PPT infographics, or cute cartoons, but to turn the key judgments, processes, structures, states, or metaphors in the article into a clean, eerie, creative, readable but not instructional hand-drawn explanatory image.
The default visual IP is "Little Black": solid black, white dot eyes, thin legs, blank expression, seriously doing something absurd but valid. Little Black must participate in the core action of the image and cannot merely stand beside it as decoration.
First read these references
Read as needed for the task; do not stuff the context all at once:
references/style-dna.md: style DNA, color, text, taboos.references/xiaohei-ip.md: Little Black IP's appearance, personality, action library, and taboos.references/composition-patterns.md: structure types, original metaphor methods, and anti-repetition rules.references/prompt-template.md: single-image generation prompt template.references/qa-checklist.md: post-generation check and iteration rules.assets/examples/: only for low-frequency visual calibration, not part of the default generation path. Do not copy the composition, objects, or annotations of these cases.
Workflow
1. Digest the body text
First read the body text, link, Notion page, Markdown file, or screenshot content provided by the user. Extract:
- What the core viewpoint is
- Which paragraphs carry cognitive turns
- Which content is suitable for explanation with images
- Which places are only suitable for text and do not need images
Do not distribute illustrations evenly. Prioritize "cognitive anchors," such as: core judgments, two breakpoints, input-output closed loops, branching, before-and-after comparison, one fish many uses, succession paths, common pitfalls, character state changes.
2. First produce an illustration strategy
If the user only says "analyze how to illustrate / think about where illustrations are needed," first provide a shot list. For each image, write clearly:
- After which paragraph it is placed
- The theme of the image
- The core meaning
- Structure type
- What Little Black does in the image
- Suggested elements
- Suggested Chinese annotation words
Default 4-8 images. For very short articles, 1-3 images; for long articles, do not easily exceed 9 images. Enough is enough; avoid turning the body text into an art album.
3. Single-image generation
If the user explicitly requests "generate / output / make images / generate for me," do not stop and wait for confirmation; use the built-in image_gen Generate each image separately. Do not combine multiple images into one.
Each image explains only one core structure. The prompt must include:
- 16:9 horizontal Chinese body illustration
- Pure white background
- Black hand-drawn line art
- A small amount of red/orange/blue Chinese handwritten annotations
- Lots of white space
- Little Black as the core action subject
- Prohibit PPT, commercial illustration, childish cuteness, complex architecture, type title in the upper left corner
Do not replicate past cases. Cases only provide style density and the way Xiaohei participates; you cannot directly reuse existing compositions such as "conveyor belt breakpoint / Xiaohei pulling a line / material fish / stamping toolbox / common pitfall path" unless the user explicitly requests a replication of a specific image. Each time, you must reinvent a strange yet valid metaphor from the current article.
4. Check and iterate
After generation, check references/qa-checklist.md. If the following problems occur, prioritize regeneration or local edits:
- Xiaohei is only decoration
- The image is too crowded
- It looks too much like a flowchart/PPT
- Too much Chinese or serious typos
- Titles such as "Common Pitfalls/Flowchart/System Architecture Diagram" appear in the upper left corner
- The style is too cute, childish, or rigid
- The background is not a clean white background
5. Save and deliver
If the user is working inside the workspace, copy the final image to:
assets/<article-slug>-illustrations/
Name them in order:
01-topic-name.png
02-topic-name.png
Keep the original generated files; do not overwrite existing assets unless the user explicitly requests replacement.
Output specifications
The strategy output before generation should be short and accurate. The delivery after generation should include:
- How many were generated
- The purpose of each image
- Save paths
- Which images are the most stable, and which are optional
Do not give lengthy explanations of style theory; let the images speak for themselves.