watermarks-remover
Remove multi-vendor AI provenance markers, including Unicode text, statistical rewriting hooks, and file metadata.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.8k
- Source
- skill-github
Overview
watermarks-remover is an Agent skill designed to remove multi-vendor AI provenance markers from text and files. It supports Unicode text cleanup, statistical rewriting hooks, and removal of C2PA/EXIF/XMP metadata. Compatible with PNG, JPEG, SVG, PDF, DOCX, ODT, HTML, and Markdown file formats. This skill helps users protect content privacy and maintain clean output. Implemented via a Python script with optional statistical rewriting hooks. Ideal for developers and researchers working with AI-generated content.
Capabilities
- ▪Remove hidden markers from Unicode text
- ▪Detect and remove statistical rewriting watermarks
- ▪Remove C2PA/EXIF/XMP metadata from files
- ▪Support for multiple file formats (PNG, JPEG, SVG, PDF, DOCX, ODT, HTML, Markdown)
Use cases
Setup
mkdir -p .grok/skills && ln -sfn "$(pwd)/skills/remove-ai-marks" .grok/skills/remove-ai-marks
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
What file formats are supported?
PNG, JPEG, SVG, PDF, DOCX, ODT, HTML, and Markdown.
Do I need additional tools?
c2patool and exiftool are optional but recommended for enhanced functionality.
Related skills
mantis
Provides security review capabilities for AI coding agents, automatically discovering, reproducing, and fixing vulnerabilities.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.