Remove Watermark

Remove light-colored text watermarks from white-background document images (exam papers, scanned documents). No API key needed - pure local image processing....

This skill appears internally consistent and purely local, but take these practical precautions before use: 1) Run it on copies of your images (it may whiten pixels or irreversibly alter text if parameters are aggressive). 2) Ensure Pillow/numpy (and scipy for full mode) are available in a controlled environment or virtualenv; the SKILL.md's 'uv run --with ...' is just a runtime helper and platform-specific. 3) The agent will 'read' images during the Visual Analysis step — avoid feeding sensitive or confidential documents if you don't want their contents exposed to the model. 4) Confirm output locations before running: the script creates a sibling directory like <input_dir>_clean by default, which may place files outside the input directory. 5) Legal/ethical: removing watermarks can violate copyrights or institutional rules (e.g., exam papers). Only use for legitimate purposes. If you need higher assurance, review the script locally (it's included) and run it in a sandboxed environment.

Type: OpenClaw Skill Name: remove-watermark Version: 0.1.0 The skill provides local image processing capabilities to remove watermarks from document images using standard libraries like Pillow, NumPy, and SciPy. The Python script (scripts/remove_watermark.py) implements legitimate thresholding and contrast enhancement logic without any network calls, suspicious file access, or obfuscation. The SKILL.md instructions are focused on guiding the agent through a multi-step verification and retry process, which is consistent with the stated purpose and lacks any malicious prompt injection or exfiltration attempts.