Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Updated version to 1.2.5 in SKILL.md to reflect the latest release. - No functional changes to code or documentation content. - Maintains all previous features and usage examples.
What This Skill Does
Pillow-based image processing utilities covering resize, crop, composite, format conversion, watermarks, brightness/contrast adjustments, and web optimization. Works with local files, URLs, bytes, or base64 input. Can be used standalone or as a post-processing step after AI image generation.
Handles the full image pipeline from loading to export in one consistent API rather than stringing together separate tools for each operation.
When to use it
- Batch-resizing a product image catalog to multiple sizes for a webstore
- Cropping AI-generated images to 1:1 or 16:9 for social media platforms
- Adding a logo watermark to hundreds of images before publishing
- Converting PNG screenshots to optimized WebP for faster page loads
- Compositing a cutout subject onto a new background image
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: resize all JPEGs in ./raw to 800px wide, add a watermark, and save as WebP
- 1Iterates over all .jpg files in ./raw using Path.glob
- 2Loads each image with ImageUtils.load
- 3Resizes to width=800 with maintain_aspect=True
- 4Applies text watermark at bottom-right with add_text_watermark
- 5Saves each result as .webp with quality=85 via ImageUtils.save
Processed WebP files written to ./output, each resized and watermarked