An automated utility for processing and adding custom text watermarks to single or multiple images simultaneously.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-watermark
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 image-watermark 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 Image Watermark?
The Image Watermark tool is a powerful automation skill designed for handling batch image modification seamlessly. Built as part of the broader Openclaw Skills ecosystem, it allows users to feed one or multiple images along with specified text inputs to programmatically overlay watermarks. This ensures copyright protection, asset branding, and data security without compromising the visual fidelity of the original files.
Leveraging Python's robust image manipulation capabilities, this skill dynamically adapts text scaling based on the targeted image's native resolution. It supports variable text opacity configuration and flexible structural placement presets to align perfectly with professional delivery workflows.
Image Watermark Use Cases
- Digital Asset Protection: Quickly stamp copyright or brand text across a large directory of product photos or proprietary imagery.
- Enterprise Security: Label internal documents, mockups, or sensitive screenshots with custom employee details before distribution.
- Social Media Management: Standardize brand identifiers across multi-image media carousels in seconds.
How Image Watermark Works
- Trigger Recognition: The agent listens for trigger keywords such as 'add watermark', 'image watermark', or 'batch watermark' alongside an image payload.
- Parameter Parsing: The system extracts required fields like text content and optional configuration variables such as position coordinates, opacity metrics, and font scaling profiles.
- Layer Composition: Utilizing Pillow, the tool instantiates a transparent RGBA layer matching the dimensions of the original image file.
- Layout Calculations: The text dimensions are evaluated, scaling the font dynamically to match 5% of the overall width, and rendering it in tile, centered, or corner alignment configurations.
- Image Assembly: The alpha channel text layer is blended cleanly into the underlying media and converted into a standard web-safe distribution format (JPG/PNG).
- Batch Delivery: Processed files are collected, archived into a unified bundle if multi-file inputs were provided, and routed directly back to the active user.
Image Watermark Setup
Prerequisites
Ensure your system context has Python 3 and the necessary system fonts installed before executing the skill.
Linux System Dependency Installation
sudo apt update && sudo apt install -y fonts-wqy-zenhei
Python Library Configuration
pip3 install Pillow
Image Watermark Data Schema & Taxonomy
Input Configuration Schema
| Input Parameter | Required | Description / Accepted Formats |
|---|---|---|
| Image Files | Yes | Single or multi-file input arrays supporting PNG or JPG files |
| Watermark Text | Yes | String content specifying the explicit text to be applied as the watermark overlay |
| Watermark Position | No | Layout profile selection: tile (45-degree pattern), center, or corner (Default: tile) |
| Opacity | No | Transparency slider input bounded between 0% and 100% (Default: 30%) |
| Font Size | No | Font rendering scale selection: auto, small, medium, or large (Default: auto dynamically sizing at 5% width) |
Output Constraints
- Output Format: Enforced generation of high-quality PNG or JPEG format copies tracking up to 95% quality retention.
- Packaging Logistics: Serial single executions or structured archive packages containing unified output directories delivered straight via messaging hooks.
Image Watermark Advanced Features
- Dynamic Responsive Scaling: Calculates localized mathematical layout bounding boxes on the fly, preventing text distortion or microscopic sizing on high-resolution canvas layers.
- Tiled Matrix Rotation: Computes coordinates across an extended grid outside visible canvas space, allowing a seamless 45-degree rotated repetition pattern across the imagery background.
- Multi-File Batch Aggregation: Seamlessly transitions from processing a single graphic asset to iterating over an entire collection, systematically compiling them into structural archives for unified delivery.
SKILL.md
Loading
Related Openclaw Skills
Claude Code Agent SDK
A developer-centric SDK to build, configure, and deploy production-grade AI agents with Claude Code as a library in Python and TypeScript.
Daily News Auto-Collector & Report Generator
An automated news aggregation tool that leverages AI-driven web search and 24-hour filters to generate noise-free daily briefings.
Daily News Automated Collector & Reporter v2.0
An AI-powered automated daily news collection and synthesis agent skill utilizing strict 24-hour freshness web search filtering.
Meeting Minutes Assistant
An intelligent productivity tool that transforms disorganized audio transcriptions into structured meeting minutes with discussion summaries, decisions, and clear action item tables.
Google MediaPipe
Google MediaPipe is a cross-platform, on-device machine learning framework enabling highly optimized real-time vision, text, audio, and generative AI inference.
bee-languages-get
A high-performance retrieval tool for obtaining a list of active site languages from the Bee Website Builder API to power dynamic localization workflows.
Featured*
