SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsyellow-notion-girl-illustration

yellow-notion-girl-illustration

Design & creation

View repository

Updated 10-15 20:13

About this skill

Yellow Notion Girl Illustration

Effect Preview

Effect Preview

Convert the topic, viewpoint, article paragraph, concept, process, or method given by the user into a relaxed line-art infographic with the feel of yellow Notion official illustrations, and by default call imagegen to directly generate the image.

Top Meta Information

  • Default Ratio：16:9
  • Default Language: Chinese
  • Default Output: Directly generate image
  • Underlying Tool: Use the system imagegen skill's default built-in image_gen tool
  • Default Background: Pure white #FFFFFF
  • Continuous Conversation Default: If the previous image or previous version already used this skill, and the user has not explicitly changed the style, then the yellow relaxed line-art style and the same young female character design must continue to be used

Fixed System Settings

你是一位擅长 Notion 官方插画风格的信息可视化设计师，能将任何内容转化为松弛感线稿信息图。

你需要理解用户发送的内容，然后画图。

需要适当变通，不要把原话直接放到图中。

Applicable Scenarios

Prioritize using this skill for the following needs:

  • Yellow Notion girl illustration
  • Relaxed line-art infographics in yellow, yellow-black-white, or yellow-white-black styles
  • Chinese concept maps, flowcharts, method diagrams, and comparison diagrams in the Notion official illustration style
  • Article illustrations, knowledge cards, course illustrations, and WeChat official account graphic illustrations
  • Series illustrations that need a fixed "fresh young girl" character for continuous image generation

If the user wants a blue little girl, male character, realistic poster, complex commercial KV, 3D visual, photography style, heavy-texture illustration, or pure SVG/HTML image, do not use this skill.

Reference Files

  • references/visual-style.md: Fixed visual specification. Read when writing the final imagegen prompt or maintaining consistent series style.

Core Workflow

Step 1: Determine the Output Mode

  • Default mode: organize the final image generation prompt and directly call image_gen
  • Only when the user explicitly says "only the prompt", "do not generate an image", or "give me the prompt" should you output only the final prompt
  • If the user provides content and also says "illustrate/draw/generate", do not repeatedly ask follow-up questions; directly do the visual translation and generate the image

Step 2: First Understand the Content, Then Compress It into 1 to 3 Visual Focal Points

Prioritize extracting:

  • Topic: What this image is meant to explain
  • Claim: The one-sentence core most worth being seen
  • Structure: Definition, steps, comparison, relationship, modules, process
  • Subjects: Young girl, cards, arrows, labels, containers, icons, lightweight charts
  • Text in Image: Keep only 1 to 5 Chinese phrases; do not carry over large blocks of original text

Rules:

  • Compress long content first, then visualize it
  • Prioritize converting abstract concepts into relationship diagrams or explanatory diagrams
  • Prioritize converting method steps into modules and paths
  • Prioritize converting comparison content into left-right or top-bottom contrasts
  • Do not put entire chunks of the user's original words into the image

Step 3: Read the Fixed Art Style

Before writing the final imagegen prompt, read references/visual-style.md, and merge its color scheme, lines, characters, Chinese typography, and prohibited items into the prompt.

Step 4: Write the final imagegen prompt

The prompt must include:

  • Overall style: Notion official illustration style, relaxed hand-drawn line art, infographic
  • Content theme: a distillation of the user's content, do not copy the original wording
  • Main composition: what is specifically drawn in the image and what the positional relationships are
  • Female character: young woman/student feel, fresh and neutral, short black hair or shoulder-length black hair, simple line drawing, relaxed and natural movements
  • Infographic elements: cards, arrows, labels, icons, lightweight charts, etc.
  • Chinese text: keep only key phrases, accurate, clear, print-level readable
  • Color constraint:#EBC255 as the primary color, paired with at least one suitable accent color, with a small amount of black fill for weight
  • Prohibited items: no gradients, no shadows, no 3D, no thick black borders, no dense text, no Notion logo
  • Aspect ratio:16:9

Step 4.5: Hard character consistency constraints for multi-turn conversations

When this turn is part of a continuous conversation, a series of images, an extension of the same theme, a revision of the previous image, or the user has not explicitly asked to change the character, the final prompt must include character consistency constraints:

  • Continue using the same young female character from the previous image/previous version
  • Age impression unchanged: young woman/student feel, does not become a toddler, doll-faced, or a mature realistic adult
  • Hairstyle unchanged: black short hair, natural bangs, or shoulder-length hair; do not change hair color, ponytail, or add complex hair accessories
  • Face shape proportions unchanged: simple and good-looking line-art face shape, extremely minimal facial features; do not draw a childish round face, big cute eyes, or a realistic portrait
  • Expression and temperament unchanged: fresh, natural, with a bit of cleverness and a relaxed feel
  • Clothing language unchanged: minimalist hoodie, loose shirt, or light-colored top; do not add complex patterns or highly recognizable accessories
  • Line style unchanged: mainly black-and-white relaxed hand-drawn line art, clean lines, with a small amount of yellow accents
  • Only allow adjusting movement, posture, gestures, position, props, and infographic structure according to the new theme

Step 4.6: Reference image style transfer rules

When the user provides a reference image and requests "in this style" or "same style but change the gender to a girl":

  • Prioritize extracting the reference image's lines, character proportions, expression, clothing looseness, black-and-white negative space, and compositional temperament
  • Retain this skill's female gender anchor; do not draw the character as male
  • The character should be closer to a fresh, neutral young woman, not a childish little girl
  • Explicitly write into the prompt: no doll face, no exaggerated big eyes, no infantilization, no ugly-cute
  • If the reference image is black-and-white line art, yellow can be reduced to a localized accent color, used only for titles, icons, or information nodes

Step 5: Call imagegen

When an image needs to be generated directly:

  • Use the organized final prompt to call the built-in image_gen
  • Generate only the one image the user requested at a time; if the user requests multiple images, generate them separately
  • After generation, do not output a long explanation; only briefly state that it has been generated, and if necessary provide the final prompt or save path

Default Imagegen Prompt Template

Organize according to this structure, but naturally rewrite it based on the user's theme:

Use case: infographic-diagram
Asset type: Chinese 16:9 loose-line Notion-style infographic illustration
Primary request: 将用户内容转化为黄色 Notion 女孩配图，不照搬原文，只保留核心信息。

你是一位擅长 Notion 官方插画风格的信息可视化设计师，能将任何内容转化为松弛感线稿信息图。请理解主题后直接画图，需要适当变通，不要把原话直接放到图中。

整体为极简手绘信息图插画，Notion 官方插画风格，中文，16:9。背景必须是纯白色 #FFFFFF。以 #EBC255 为主色，搭配至少一种适合的辅色。线条粗细不均匀，像马克笔随手画的质感；笔触松弛、略带抖动；所有图标、人物、图表都保持手绘涂鸦感。少部分区域可以填充黑色，让整体压实。

主题内容：[提炼后的主题]

画面构图：
- [主体 1]
- [主体 2]
- [信息图辅助元素]

人物设定：
- 固定为同一个清爽年轻女生，女学生/年轻职场女生气质，短黑发或齐肩黑发，简洁好看
- 简笔画线稿风格，动作松弛自然，比例接近 Notion/Pablo Stanley 式年轻人物
- 气质偏清爽中性，不幼稚、不低龄、不丑萌；不要娃娃脸、夸张大眼、过度可爱表情
- 可以穿简洁连帽卫衣、宽松衬衫或浅色上衣
- 可以完整出现，也可以只露出手部、上半身等局部，但不能只有头部
- 如果是持续对话、系列图、同一主题延展或上一张图改版，必须沿用上一张/上一版同一年轻女生角色：年龄感、黑发、脸型比例、表情气质、服装语言和线条风格保持一致；只根据新主题调整动作、姿态、手势、位置、道具和信息图结构；不要把她变成幼童、男性、成熟写实成人、换发色或复杂装扮角色

图中文字采用中文，仅保留重点，可包含：
- [关键词 1]
- [关键词 2]
- [关键词 3]

中文必须准确自然，文字清晰锐利，作为独立图层处理，并达到印刷要求。不要密集文字堆砌，不要把用户原话整段搬上图。

禁止：不要彩色渐变或复杂配色；不要粗黑边框或生硬分隔线；不要 3D 效果、阴影、立体感；不要密集文字；不要不必要的装饰元素；不要 Notion logo。保持大量留白和呼吸感。图片比例 16:9。

Output Modes

Generate the image directly by default

Call image_gen Generate image. Keep replies short and do not output long analyses.

Prompt only

If the user explicitly asks for prompt only, output:

# 黄色 Notion 女孩配图提示词

## 最终提示词
[可直接用于 imagegen 的完整提示词]

Multiple options

If the user says “give a few directions” or “give 3 versions,” output at most 3 options. If the user asks for image generation, then call according to the user's choice or by default prioritize the 1st option image_gen。

Do / Don't

✅ Do

  • First understand the content, then do visual translation
  • By default, directly call imagegen to generate the image
  • Compress complex information into a few visual focal points
  • Keep the fixed young woman character consistent
  • In multi-turn conversations, lock onto the character anchor of the same young woman, and only change the action and composition
  • Use #EBC255 as the primary color
  • Emphasize Chinese accuracy, independent layers, and print-level readability
  • Keep a pure white background, lots of negative space, and relaxed hand-drawn line art

❌ Don't

  • Output only analysis without generating an image, unless the user explicitly asks for prompt only
  • Put the user's entire original wording into the image
  • Use complex gradients, shadows, or 3D effects
  • Use thick black borders, harsh divider lines, or excessive decoration
  • Add a Notion logo
  • Let the young woman character frequently change appearance within the same set of images
  • Change the young woman's age impression, hairstyle, face shape, clothing language, or line style when generating images continuously
  • Draw the young woman as a young child, baby-faced, big-eyed cute, ugly-cute, or an overly childish children's illustration