An autonomous visual capture tool designed to snapshot websites, dashboards, and terminal outputs for professional documentation and social media content.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install rey-screenshot
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 rey-screenshot 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 Screenshot (Autonomous Capture)?
The Screenshot skill enables AI agents to perform autonomous visual documentation and content creation. By leveraging the Openclaw Skills framework, this tool allows for self-initiated captures of web pages, specific UI elements, and CLI environments. It is specifically engineered for developers and creators who need to generate high-quality visual assets for platforms like X (Twitter), Instagram, and Product Hunt without manual effort.
Beyond basic screen grabbing, this skill integrates sophisticated viewport management and post-processing capabilities. It ensures that every capture is optimized for its intended platform, whether it is a high-resolution OGP card for a blog or a perfectly cropped hero section for a marketing campaign. With built-in security rules for data redaction, it provides a safe and professional way to automate visual storytelling.
Screenshot (Autonomous Capture) Use Cases
- Generating automated product screenshots for landing pages and Product Hunt launches.
- Capturing real-time agent dashboards and metrics to share progress updates on social media.
- Creating visual before-and-after comparisons for UI/UX improvements and bug fixes.
- Producing annotated step-by-step visual guides for technical documentation and GitHub README files.
- Capturing pretty terminal outputs and code snippets for educational content.
How Screenshot (Autonomous Capture) Works
- The agent determines the target URL or local service that requires a visual snapshot.
- A browser action is triggered via the Openclaw Skills interface to load the target with specific viewport dimensions.
- The skill identifies whether a full-page, viewport-only, or element-specific (CSS selector) capture is required.
- Visual assets are rendered and saved to a structured local directory with standardized timestamp naming conventions.
- Optional post-processing is executed to crop, annotate, or compress the image based on the destination platform's requirements.
- Security filters are applied to ensure no sensitive credentials or private data are exposed in the final output.
Screenshot (Autonomous Capture) Setup
To get started with this skill, ensure the OpenClaw browser tool is active in your environment. For post-processing capabilities, install ImageMagick:
sudo apt-get install imagemagick
Create the default storage directory for your captures:
mkdir -p /mnt/hdd/rey/images/screenshots/
Screenshot (Autonomous Capture) Data Schema & Taxonomy
The skill organizes captured assets using a timestamp-based taxonomy to prevent collisions and ensure easy retrieval.
| Property | Value |
|---|---|
| Storage Directory | /mnt/hdd/rey/images/screenshots/ |
| Filename Pattern | screenshot-YYYY-MM-DD-HHMMSS.png |
| Default Format | PNG (for UI and text clarity) |
| Platform Presets | X/Twitter (16:9), Instagram (1:1, 9:16), Note.com (1280x720) |
| Metadata | Timestamps and target selectors are logged per session |
Screenshot (Autonomous Capture) Advanced Features
- Multi-platform viewport presets for instant optimization for X, Instagram, and OGP cards.
- Element-level targeting allowing the agent to capture specific components rather than the whole screen.
- Autonomous security logic that triggers redaction for sensitive data like API keys and passwords.
- Support for terminal-to-image rendering for high-quality CLI documentation.
- Automated post-processing hooks for adding watermarks, text overlays, and dimension adjustments.
SKILL.md
Loading
Related Openclaw Skills
Polymarket Trader
An advanced AI trading skill for Polymarket that automates market discovery, strategic betting, and risk-mitigated hedging via the Polygon network.
Network Scanner
A robust network discovery and port auditing tool for mapping local devices and identifying security vulnerabilities using nmap.
Nano Banana Pro: AI Image Generation
A professional-grade image generation skill powered by Gemini that excels at rendering Japanese text and creating platform-optimized visuals.
Intelligent Model Router
An automated model routing skill that dynamically switches between Claude Sonnet 4.5 and Opus 4.6 based on task complexity to balance cost and quality.
Skill Creator for Openclaw
An interactive framework designed to build, validate, and deploy standardized Openclaw Skills according to official best practices.
Social Scheduler (rey-social-scheduler)
A multi-platform social media management tool for automated scheduling, bulk posting, and engagement analytics across major networks.
Featured*
