A specialized prompt engine that converts concise text into structured, hand-drawn style visual knowledge card descriptions for AI image generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install visual-note-prompt
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install visual-note-prompt using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Visual Note Prompt Generator?
The Visual Note Prompt Generator is a sophisticated tool designed for the Openclaw Skills ecosystem to bridge the gap between textual data and visual learning. It acts as a bridge, taking raw study points, conceptual summaries, or meeting notes and transforming them into precise, highly-structured prompts that AI image generators can interpret. By focusing on hand-drawn sketchnote aesthetics, it provides users with a standardized way to create beautiful, educational visuals from simple text.
Built to ensure consistency, this skill within the Openclaw Skills library adheres to strict layout and stylistic rules. It avoids common AI generation pitfalls by using descriptive spatial language rather than coordinates, ensuring that the resulting knowledge cards are both aesthetically pleasing and logically organized for maximum information retention.
Visual Note Prompt Generator Use Cases
- Transform academic study notes into visually engaging knowledge cards for better memorization.
- Generate standardized prompts for AI creators to produce consistent hand-drawn sketchnote assets.
- Create professional-looking doodle-style visuals for presentations, social media, or digital notebooks.
- Automatically segment long text summaries into a coordinated series of visual panels or card stacks.
How Visual Note Prompt Generator Works
- The user inputs a main title and specific content points into the Openclaw Skills interface.
- The skill analyzes the input to determine the total point count and character density to decide the required number of images.
- It identifies the preferred visual style (Classic hand-drawn or Futuristic Tech) and selects an optimal layout like Stacked Cards or Center Radiation.
- It maps the text content to specific canvas regions using descriptive language (e.g., "left balanced area") instead of percentages.
- The system generates a final, formatted prompt block including a specialized negative prompt to prevent the use of printed fonts or unwanted numerical data.
Visual Note Prompt Generator Setup
To integrate this capability into your environment, follow these steps within the Openclaw Skills framework:
# Navigate to your local skills directory
cd openclaw-agents/skills
# Clone or add the visual-note-prompt repository
git clone https://github.com/openclaw/visual-note-prompt.git
# Review the style library for customization
cat assets/style-library.md
Ensure your AI agent has access to the references/format-guide.md to maintain strict output boundaries.
Visual Note Prompt Generator Data Schema & Taxonomy
The skill organizes prompt generation using a rigid metadata taxonomy to ensure compatibility with image models.
| Field | Description | Requirement |
|---|---|---|
| [Style] | Defines the visual theme, colors, and line weight | Mandatory |
| [Layout] | Sets the 3:4 vertical aspect ratio and canvas structure | Mandatory |
| [Core Content] | Maps user text to specific descriptive canvas regions | Backticks used |
| [Negative Prompt] | Excludes percentages, print fonts, and coordinates | Mandatory |
| [Author] | Appends the signature and decorative icons | Mandatory |
Visual Note Prompt Generator Advanced Features
- Automatic multi-card serialization: Intelligently splits high-density content into a sequence of cards labeled [01/0X].
- Descriptive spatial engine: Uses natural language for positioning to avoid the layout errors typical of coordinate-based AI prompting.
- Extensible style library: Power users can modify
assets/style-library.mdto define new visual themes beyond Classic and Tech. - Print-font suppression: Integrated negative prompting specifically designed to force AI models to use imperfect, hand-drawn handwriting for a genuine sketchnote feel.
SKILL.md
Loading
Related Openclaw Skills
AI Agent Psychologist
A sophisticated self-alignment and communication calibration tool for AI agents based on state-of-the-art research in structured introspection and functional emotion theory.
CMS Config MyClaw
A streamlined CLI wizard for binding internal corporate communication channels to specific OpenClaw agents.
Dominos Brand Intelligence
A specialized information retrieval skill providing structured insights into Dominos brand history, services, and global market standing.
Declutter Coach
An AI-driven organization assistant designed to create actionable decluttering plans and minimalism strategies for any physical space.
Feishu Wiki Writer
A high-performance automation skill designed to write complex, large-scale documents to Feishu Wiki while eliminating synchronization conflicts.
Test Slug Check
A specialized development utility designed to validate slug naming conventions and automated publishing workflows for AI coding agents.
Featured*
