whiteboard-handdrawn-explainer-illustration

Whiteboard Hand-Drawn Explanatory Diagram

Effect Preview

Turn the topic, viewpoint, article paragraph, concept, process, system architecture, or methodology given by the user into a restrained, clear whiteboard hand-drawn explanatory diagram suitable for PPT.

Top-Level Conventions

Default aspect ratio：16:9
Default language: Chinese
Default output: directly generate an image
Underlying tool: use the system imagegen skill's default built-in image_gen tool
Default style: whiteboard background, black marker lines, a small amount of blue key annotations, like a teacher explaining a complex system on a whiteboard
Prompt only: only when the user explicitly says "only the prompt / only give the prompt / do not generate an image" should you output the complete prompt without calling the image generation tool

Applicable Scenarios

Prioritize for:

Explanatory diagrams for technical concepts, system architecture, product logic, Agent workflows, and AI application processes
Concept explanation illustrations in articles, courses, PPTs, and speeches
Process, relationship, grouping, path, and causality diagrams that need to look like "a teacher drew them on a whiteboard"
16:9 infographics that need to be restrained, rational, and clearly focused

If what the user wants is realistic photography, commercial posters, 3D rendering, complex UI collages, cute illustrations, heavily colored infographics, or Xiaohongshu covers, do not use this skill.

Reference Files

references/visual-style.md: fixed visual specifications, prompt templates, and prohibitions. Must be read before writing the final imagegen prompt or generating an image.

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 says "illustration/draw/generate/whiteboard hand-drawn", do not repeatedly ask follow-up questions; directly do the visual translation and generate the image

Step 2: Extract key points according to the Pareto principle

Extract the most important 20% of information from the user's content; do not move entire paragraphs of the main text into the diagram.

Prioritize extracting:

Topic: what this diagram is meant to explain
Core relationships: modules, objects, roles, inputs and outputs, preceding and following paths
Reading path: where to start reading, how the arrows flow
Key annotations: choose only 1 to 3 words, nodes, or connecting lines that need blue emphasis
Text in the diagram: keep only 3 to 8 short Chinese labels; avoid long sentences and paragraphs

Common structure choices:

Process: left-to-right or top-to-bottom arrow path
Architecture: central module + surrounding modules + inputs and outputs
Comparison: left and right columns or top and bottom layers
Methodology: 3 to 5 steps or groups
Complex system: large framed sections, nodes connected by lines, a small number of annotations

Step 3: Read the fixed art style

Before writing the final imagegen prompt, read references/visual-style.md, and merge its lines, composition, colors, Chinese text, and prohibited items into the prompt.

Step 4: Write the final imagegen prompt

The prompt must include:

Whiteboard hand-drawn explanatory diagram, 16:9
Black marker lines, with a small amount of blue for key annotations
Like a teacher explaining a complex system on a whiteboard
Lines are natural but not sloppy; arrows, frames, and grouping relationships are clear
The visual is restrained and rational, suitable for technical concept explanations and PPT illustrations
Follow the Pareto principle; extract only the key points and do not include large blocks of text
Chinese short labels are accurate and clear, with no typos, garbled text, or extra text

Step 5: Call imagegen

When direct image generation is needed:

Use the finalized prompt to call the built-in image_gen
Generate only the image requested by the user at one time; if the user requests multiple images, generate them separately
After generation, do not output a long explanation; keep it brief

Output Modes

Generate the image directly by default

Call image_gen to generate the image. Keep the reply brief and do not output a long analysis.

Prompt only

If the user explicitly requests only the prompt, output:

# 白板手绘说明图提示词

## 信息提炼

- 主题：[提炼后的主题]
- 结构：[流程/架构/对比/方法论/复杂系统]
- 蓝色重点：[1 到 3 个重点]

## 最终提示词

[可直接用于 imagegen 的完整提示词]

Do / Don't

Understand the content first, then turn it into a whiteboard explanation diagram
By default, directly call imagegen to generate the image
Use arrows, frames, and grouping relationships to express structure
Keep black lines as the main element, and use blue only for key annotations
Keep 16:9, suitable for placing into a PPT
Keep plenty of whitespace and a clear reading path

Don't

Do not put the user's original text onto the image in full paragraphs
Do not use dense text, small-text annotations, or complex tables
Do not use colorful gradients, 3D, shadows, skeuomorphic textures, or commercial poster styles
Do not draw it as comic-character-led, cute sticker style, or children's illustration style
Do not add logos, watermarks, real App screenshots, or unrelated decorations