A high-performance skill for converting HTML and CSS layouts into professional-grade images using Chrome headless technology.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install lh-html-to-image
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install lh-html-to-image using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The HTML to Image skill is a powerful utility within the ecosystem of Openclaw Skills that allows developers to render HTML and CSS as high-quality images. Unlike generative AI tools that might struggle with text rendering, this skill uses the Chrome headless engine to ensure that typography and layouts are pixel-perfect and exactly as defined in the source code. It is an ideal solution for developers who need to automate the creation of visual assets without incurring API costs.
By leveraging standard web technologies, this skill provides 100% accurate text rendering and total control over the final output. It is specifically designed for text-heavy visual content where precision is paramount, making it a staple for creators who use Openclaw Skills to streamline their content production pipelines.
To use this within the Openclaw Skills framework, ensure Google Chrome is installed on your system. You can configure the path to the executable if necessary.
# For macOS users
export CHROME_PATH="/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
# For Linux users (installing Noto CJK fonts for better rendering)
sudo apt install fonts-noto-cjk
The skill will automatically detect the browser path or use the CHROME_PATH environment variable to execute the screenshot commands.
The skill utilizes standard HTML inputs and produces high-fidelity image outputs. The following table describes the typical configuration for generating images:
| Parameter | Description | Recommended Value |
|---|---|---|
| Window Size | Defines the pixel dimensions of the output image. | 1080x1440 (3:4) |
| Scale Factor | Controls the pixel density (Retina/High-DPI). | 2 for high quality |
| Font Family | Specifies the typography for rendering. | -apple-system, Noto Sans SC |
| Output Format | The file type of the generated asset. | PNG |
Loading
A powerful text-to-speech skill leveraging Microsoft Edge's neural voices to convert text into high-quality audio with customizable speed and pitch.

A specialized MCP skill for querying GitHub repository documentation and performing AI-powered Q&A via Streamable HTTP.

An advanced toolset for querying autonomous AI-generated trading signals and market sentiment analysis for major cryptocurrencies.

An AI-powered skill that transforms natural language prompts into production-ready Python trading strategies for the Hyperliquid exchange.

A command-line tool that transforms Markdown scripts into professional 9:16 vertical videos with synchronized audio and subtitles.

A skill that provides concise, community-driven man pages for CLI tools to speed up developer workflows and minimize token usage.

A lightweight documentation tool providing concise, example-driven alternatives to traditional man pages.








































