An AI-driven automation skill for generating stylized XiaoHongShu social media images using template-based browser rendering.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install visnote-image-creator
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 visnote-image-creator 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 VisNote Images Creator?
The VisNote Images Creator is a sophisticated technical asset within the ecosystem of Openclaw Skills designed to streamline social media content production. It bridges the gap between raw text descriptions and high-quality visual assets by leveraging Playwright-driven browser automation and a dynamic template registry. By analyzing user intent, the skill identifies whether a user needs a high-impact cover, a detailed tutorial layout, or a comparison chart, and then orchestrates the entire rendering process.
This skill is particularly valuable for creators and marketers who need to maintain a consistent visual identity on platforms like XiaoHongShu without manual design overhead. It ensures that every generated image adheres to professional design standards while remaining fully customizable through simple natural language commands.
VisNote Images Creator Use Cases
- Creating attention-grabbing cover images for XiaoHongShu posts using high-contrast templates.
- Generating consistent body content for tutorials, OOTD shares, or quote-based posts.
- Automating the creation of 'Before and After' comparison visuals for lifestyle or home renovation content.
- Producing batch images for social media campaigns based on a single content outline.
How VisNote Images Creator Works
- Verifies the presence of a valid API key and membership status via a local configuration check.
- Performs a natural language analysis of the user's request to extract titles, subtitles, tags, and specific style preferences.
- Fetches the latest design configurations from the remote template registry API to ensure access to current styles.
- Implements a tag-based selection logic to match the content type with the most effective template (e.g., prioritizing 'Cover' tags for main images).
- Merges extracted user data with template default values to ensure a complete and valid data schema for rendering.
- Constructs and executes a Node.js command that uses Playwright to render the design in a headless browser and export it as a high-resolution PNG.
VisNote Images Creator Setup
To begin using this capability within your Openclaw Skills workflow, you must first configure your credentials. Create a config.json file in your project root with your VisNote API key:
cat > config.json << 'EOF'
{
"apikey": "your_api_key_here"
}
EOF
Additionally, ensure the runtime environment has the necessary browser dependencies installed:
npm install playwright
npx playwright install chromium
VisNote Images Creator Data Schema & Taxonomy
The skill manages data through a structured JSON schema that maps user inputs to template fields. This ensures that even partial user input results in a professional-looking output by falling back to template defaults.
| Field | Description | Type |
|---|---|---|
templateId |
The unique ID of the design layout (e.g., 'yellow', 'academic-notes') | String |
title |
The primary headline of the image, supporting manual line breaks | String |
subtitle |
Secondary text providing context or additional details | String |
tag |
Social media category tags (e.g., 'Daily Sharing', 'Tutorial') | String |
color |
Custom branding color in Hex format | String |
author |
User handle or credit often preceded by the @ symbol | String |
VisNote Images Creator Advanced Features
- Context-Aware Caching: Reuses the template registry within a single conversation to speed up follow-up requests and reduce API overhead.
- Intelligent Field Merging: Automatically overrides default template values (like placeholder images or text) only when the user provides specific alternatives.
- Batch Processing Support: Capable of generating an entire carousel of images (Cover + Content Body) in a single workflow with staggered execution to prevent server timeouts.
- Smart Tagging: Automatically formats user-provided keywords into platform-appropriate tags like 'Useful Content' or 'OOTD Sharing'.
SKILL.md
Loading
Related Openclaw Skills
HostLink
HostLink enables secure, authenticated execution of host-level commands directly from within an OpenClaw container.
Video Narration
An automated workflow that transforms silent screen recordings into polished, narrated product demos using neural text-to-speech.
Daily Poem
A literary AI assistant that delivers curated daily poems, translations, and technical rhythm analysis across Chinese and English traditions.
System Monitor
A lightweight, local monitoring tool for tracking real-time health metrics and hardware performance on Linux and ARM-based gateway hosts.
Continuous Learning v2.1: Instinct-Based Architecture
An advanced learning system that transforms AI coding sessions into reusable knowledge through atomic instincts and confidence scoring.
Novel Writer
A sophisticated prompt construction engine that synthesizes chapter outlines, character dossiers, and voice profiles into actionable instructions for AI writing agents.
Featured*
