A high-performance image processing toolkit powered by ImageMagick for seamless resizing, format conversion, and optimization.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install vision
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 vision 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 Vision — Image Processing, Resize, Convert & Watermark?
Vision is a comprehensive image processing skill designed to give AI agents professional-grade manipulation capabilities. Built on the industry-standard ImageMagick engine, this Openclaw Skills contribution allows users to perform complex graphical tasks through simple natural language commands or CLI scripts.
Whether you are preparing assets for frontend development, optimizing media for the web, or protecting intellectual property with watermarks, Vision provides a reliable and fast workflow. It eliminates the need for manual photo editing software by automating repetitive tasks like batch resizing and format transcoding (e.g., PNG to WebP) directly within your development environment.
Vision — Image Processing, Resize, Convert & Watermark Use Cases
- Scaling high-resolution photos down to web-friendly widths or specific percentages.
- Converting legacy image formats like PNG or JPG to modern, high-compression WebP files.
- Automating the application of copyright text or branding watermarks across multiple assets.
- Compressing image file sizes to improve website loading speeds without significant quality loss.
- Extracting or identifying image metadata and EXIF information for digital asset management.
How Vision — Image Processing, Resize, Convert & Watermark Works
- The AI agent receives a natural language request or a structured command containing image processing parameters.
- Vision triggers a bash-based execution layer that interfaces with local ImageMagick binaries.
- The skill validates the input file existence and ensures all required dependencies (bash 4+ and ImageMagick) are available.
- Processing is executed based on the specified flag (resize, convert, optimize, or watermark).
- The transformed file is generated in the target directory, and the agent provides a confirmation or the path to the new asset.
Vision — Image Processing, Resize, Convert & Watermark Setup
To integrate this component of Openclaw Skills, ensure your environment meets the system requirements and follow these steps:
Prerequisites:
- bash 4+
- ImageMagick (ensure
convertandidentifyare in your PATH)
Installation: Clone the repository and verify the script permissions:
git clone https://github.com/bytesagain/ai-skills
chmod +x scripts/script.sh
Basic Usage:
bash scripts/script.sh resize --input photo.jpg --width 800
Vision — Image Processing, Resize, Convert & Watermark Data Schema & Taxonomy
Vision handles data through a straightforward input/output model. It primarily interacts with local filesystems and produces output based on the following taxonomy:
| Attribute | Description | Type |
|---|---|---|
--input |
The path to the source image file | String/Path |
--width |
Target width in pixels (for resizing) | Integer |
--percent |
Scale factor relative to original size | Integer (1-100) |
--to |
Target extension/format (webp, png, jpg) | String |
--quality |
Compression level for optimization | Integer (0-100) |
--text |
Content for the watermark layer | String |
--position |
Gravity location for watermarks (e.g., southeast) | Enum |
Vision — Image Processing, Resize, Convert & Watermark Advanced Features
- Smart quality optimization that balances file size and visual fidelity.
- Flexible watermark positioning using standard gravity coordinates (e.g., southeast, center).
- Support for percentage-based scaling, allowing for uniform batch processing across varied resolutions.
- Seamless integration into Openclaw Skills workflows for automated media pipelines.
- Multi-format support including PNG, JPG, and WebP transcoding.
SKILL.md
Loading
Related Openclaw Skills
Campaign Manager
A high-performance command-line interface for planning marketing campaigns, tracking ROI, and managing budget allocations.
MarsBit Crypto News Skill
A specialized skill providing real-time Web3 news and market-moving intelligence via a hosted MCP endpoint.
Cairo Smart Contract Setup (OpenZeppelin)
Automate the scaffolding and configuration of Starknet projects using Cairo and OpenZeppelin standards.
Gold Price Auto Report
An automated monitoring tool that tracks and reports domestic and international gold prices every hour.
GH Monitor
An automated monitoring extension for GitHub that tracks issues, pull requests, and CI/CD workflow runs via the GitHub CLI.
Reliable API Client
An enterprise-grade Node.js API client implementing the gold standard for multi-endpoint failover, key rotation, and resilient request handling.
Featured*
