Image Processing Expert

Problem

Image work often involves small but repeated tasks: reducing file size for upload, cropping a photo to a square, fixing orientation, converting JPG to PNG, adding watermarks to assets, or generating QR codes. Doing this manually can be tedious, and users may accidentally modify originals. Image Processing Expert targets these high-frequency tasks, using natural language to trigger local image operations while keeping source files intact.

How It Works

The skill centers on practical image workflows:

• Basic processing: compression, cropping, rotation or flipping, resizing, and format conversion.
• Annotation and encoded output: text or image watermarks, plus QR code and barcode generation.
• Batch operations: repeated tasks such as compressing, converting formats, or renaming multiple images.
• Local constraints: processing stays local, does not rely on external APIs, and writes results to an output directory with a processing summary.

Typically, you confirm that dependencies are available, then describe the goal in plain language, such as “compress this image,” “crop it to a square,” or “convert JPG to PNG.” The skill parses the request, runs the relevant module, and translates technical errors into clear messages, for example explaining that a transparent channel was removed when saving to an incompatible format.

Scope and Notes

It is best for lightweight image tasks and non-technical users, covering common formats, sizes, watermarks, batch processing, and QR or barcode output. It is not intended for complex visual understanding, design layout, AI retouching, or cloud-based collaboration. It assumes local dependencies and writable output paths, and it avoids modifying original files, making it suitable when source assets must remain untouched.