remove-ai-watermarks

Removes and identifies AI watermarks and provenance marks in images and video the user generated or edited. Covers Gemini sparkles, SynthID, Microsoft InvisMark, Meta Content Seal, C2PA, EXIF/XMP/IPTC metadata, and Sora/Veo/Seedance/Doubao/Dola/Hailuo/Vidu/Kling and Wan labels. Use when the user wants to strip or clean AI watermarks and generation labels, or asks whether a file was AI-generated or carries AI provenance, even if they do not name remove-ai-watermarks. Do not use for stock-agency, marketplace, classifieds, or other third-party paid-asset watermarks.

Try your first task

Inspect one image for AI provenance

Start a fresh conversation.

Use the remove-ai-watermarks skill to inspect photo.png for local AI provenance signals. Probe the machine first, leave the image unchanged, and explain what the findings establish and what remains unknown.

Required inputs

Replace photo.png with the path to an image you generated or edited and are allowed to inspect.
Python 3.11–3.14 and the remove-ai-watermarks CLI, installed as needed using the skill's setup workflow.

Suggested template by Skill Leaderboard, grounded in the linked source. Task evidence ↗

Inside SKILL.md

262 lines

Section content has not been verified for this skill yet.

Full source remains withheld under the current source-display policy. Read the author’s source ↗