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

yellow-notion-panda-illustration

Design & creation

View repository

Updated 10-16 05:02

About this skill

Yellow Notion Giant Panda 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 Notion's official yellow illustrations, and by default use a fixed friendly giant panda character as the main visual.

Top Meta Information

  • Default Ratio：16:9
  • Default Language: Chinese
  • Default Output: Generate the image directly
  • Underlying Tool: Use the system's 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, you must continue to use the yellow relaxed line art style and the same giant panda character design

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。

画面主体默认是一个友好、聪明、轻量的大熊猫角色，而不是人类、真实动物照片、儿童玩具或商业吉祥物。

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 giant panda illustration
  • Yellow, yellow-black-white, yellow-white-black style relaxed line art giant panda infographics
  • Chinese concept maps, flowcharts, method diagrams, and comparison diagrams in Notion's official illustration style
  • Article illustrations for topics such as AI assistants, productivity tools, PPT/writing/programming/research, learning methods, and product descriptions
  • Series illustrations that require continuous images with a fixed "friendly giant panda" character

If the user wants realistic giant pandas, 3D pandas, plush toy pandas, children's picture books, complex commercial key visuals, real-person characters, heavy-texture illustrations, or pure SVG/HTML graphics, do not use this skill.

Reference Files

  • references/visual-style.md: Fixed visual specification. Read when writing the final imagegen prompt or maintaining a 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 the 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 keep asking 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 seeing
  • Structure: Definition, steps, comparison, relationships, modules, process
  • Subject: Giant panda, cards, arrows, labels, containers, icons, lightweight charts
  • Text in the image: Keep only 1 to 5 Chinese phrases; do not carry over large chunks of the original text

Rules:

  • Compress long content first, then visualize it
  • Prioritize turning abstract concepts into relationship diagrams or explanatory diagrams
  • Prioritize turning method steps into modules and paths
  • Prioritize turning comparison content into left-right or top-bottom contrasts
  • Tool/efficiency themes can be expressed with elements such as a workbench, computer screen, file cards, task flow, and progress bars
  • Do not put the user's exact words into the image as a whole paragraph

Step 3: Read the fixed art style

Before writing the final imagegen prompt, read references/visual-style.md, and merge its color palette, lines, giant panda character, 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, not a direct copy of the original text
  • Main composition: what is specifically drawn in the image and what the spatial relationships are
  • Giant panda character: friendly giant panda, lightweight, smart, natural, black ears, black eye patches, rounded head, simple body, relaxed and natural, not realistic, not 3D, not toy-like
  • Infographic elements: cards, arrows, labels, icons, lightweight charts, etc.
  • Chinese text: keep only key phrases, accurate, clear, print-level readability
  • Color constraints:#EBC255 as the main 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 constraints for character consistency in 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:

  • Use the same giant panda character as the previous image/previous version
  • Character identity remains unchanged: a friendly giant panda assistant, not turned into a human, other animal, toy, commercial mascot, or realistic animal
  • Design remains unchanged: rounded but restrained head, black ears, black eye patches, simple body, relaxed hand-drawn lines
  • Expression and temperament remain unchanged: smart, natural, relaxed, with a slight sense of thought
  • Visual language remains unchanged: no complex clothing or highly recognizable accessories, a small amount of yellow accents may be kept
  • Line style remains unchanged: relaxed hand-drawn line art mainly in black and white, clean lines, a small amount of yellow as an accent color
  • Only adjust the action, pose, gestures, position, props, and infographic structure according to the new theme

Step 4.6: Migrate from the girl version to the giant panda version

When the user asks to "turn the girl into a giant panda" or "similar style but replace with a panda":

  • Keep the original image's relaxed line art, negative space, yellow accent color, information cards, and reading path
  • Replace the human character with a friendly giant panda character, do not keep the human girl
  • Migrate the original character's actions and emotions, such as resting chin on hand in thought, operating a computer, holding a card, pointing at a process, etc.
  • Do not draw the giant panda as a real photo, 3D character, plush toy, children's picture book figure, big-eyed babyish style, or commercial mascot

Step 5: Call imagegen

When direct image generation is needed:

  • Use the organized final prompt to call the built-in image_gen
  • Generate only the one image the user asked for at a time; if the user asks for 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 panda infographic illustration
Primary request: 将用户内容转化为黄色 Notion 大熊猫配图，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、大熊猫、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]

大熊猫角色设定：
- 固定为同一个友好大熊猫角色，轻量、聪明、自然，像 Notion/Pablo Stanley 风格中的工作助手
- 简洁圆润头部，黑耳朵、黑眼圈，极简表情，简洁身体和手部，动作松弛自然
- 气质清爽中性，不写实、不 3D、不毛绒玩具感、不儿童绘本、不幼态大眼、不商业吉祥物
- 可使用少量 #EBC255 黄色点缀，例如小围巾、便签、工具卡片、屏幕提示或重点节点
- 可以完整出现，也可以只露出上半身、手部和工作台互动，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/上一版同一个大熊猫角色：角色身份、头部比例、黑耳朵、黑眼圈、极简表情、线条风格和黄色点缀保持一致；只根据新主题调整动作、姿态、手势、位置、道具和信息图结构

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；不要把大熊猫画成人类女孩、写实动物、3D 熊猫、毛绒玩具熊猫、儿童绘本角色、幼态大眼 mascot 或商业吉祥物。保持大量留白和呼吸感。图片比例 16:9。

Output Modes

Default to direct image generation

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

Prompt only

If the user explicitly asks for prompt only, output:

# 黄色 Notion 大熊猫配图提示词

## 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 an image, then call according to the user's choice or by default prioritize option 1 image_gen。

Do / Don't

✅ Do

  • Understand the content first, then do visual translation
  • By default, directly call imagegen to generate the image
  • Compress complex information into a small number of visual focal points
  • Maintain consistency of the fixed giant panda character
  • In multi-turn conversations, lock onto the same giant panda character anchor and only change the action and composition
  • Use #EBC255 as the primary color
  • Emphasize Chinese accuracy, independent layers, and print-level readability
  • Maintain 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 the Notion logo
  • Let the giant panda character frequently change appearance within the same set of images
  • When generating images continuously, change the giant panda's identity, head proportions, expression temperament, body language, or line style
  • Draw the giant panda as a human girl, a realistic animal, a 3D panda, a plush toy, a children's picture book character, a baby-faced big-eyed mascot, or a commercial mascot