Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added detailed agent instructions for handling and delivering PNG files, including guidelines to send images as documents/files (not photos) to avoid compression or size limits on platforms like Telegram. - No changes to functionality; installation and usage remain the same.
What This Skill Does
Captures a full webpage screenshot and saves it as a PNG optimized for mobile viewing. Uses shot-scraper and Chromium under the hood, installed via uv.
Automates the full install and capture pipeline in one command, including browser setup, so there's no manual Playwright or browser configuration required.
When to use it
- Saving a recipe page as an image to read offline
- Archiving an article before it goes behind a paywall
- Sharing a webpage snapshot in a chat without sending a link
- Capturing a long product page for reference
- Converting a web report to an image for a presentation
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'Save this page as an image: https://example.com/article'
- 1Run url2png.sh with the provided URL
- 2Wait for shot-scraper to capture the full page using Chromium
- 3Locate the generated PNG in ~/Pictures
- 4Send the file to the user as a document to avoid compression
A full-page PNG of the webpage saved to ~/Pictures and delivered to the user
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.