Gemini Watermark Remover
Removes the Google Gemini visible watermark from AI-generated images using reverse alpha blending. Use when the user asks to remove a Gemini watermark.
Install
$ agentstack add skill-useaitechdad-agent-skills-gemini-watermark-remover-agent-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-useaitechdad-agent-skills-gemini-watermark-remover-agent-skill) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Gemini Watermark Remover
This skill removes the semi-transparent "G sparkle" watermark from the bottom-right corner of images generated by Google Gemini. It uses a mathematically exact Reverse Alpha Blending formula, not AI inpainting, guaranteeing zero loss to the original image content.
Workflow
- Verify dependencies: Ensure the Python script can run. The dependencies are
numpyandPillow. If they are not installed, instruct the user to install them or runpip install -r scripts/requirements.txtif you have permission. - Execute the script: Run
python scripts/remove_watermark.py [--output ] [--json]to process the image. - Interpret the result: If
--jsonis provided, the script outputs a JSON string containing metadata about the removal (e.g., whether the watermark was detected and removed, the estimated size, and residual score). Read this JSON and communicate the outcome to the user.
Examples
If the user says: "Remove the watermark from mygeminiimage.png and save it to clean.png" You run: python scripts/remove_watermark.py my_gemini_image.png --output clean.png
Constraints
- This tool only removes the visible Gemini watermark. It does not remove standard stock photo watermarks or invisible SynthID watermarks.
- The script must be run from Python, not Node.js.
- Do not attempt to modify the image using ImageMagick or other generic tools; this requires the pre-calculated alpha maps in
scripts/alpha_maps/.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: useaitechdad
- Source: useaitechdad/agent-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.