Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill provides tools for AI content creators to strip visible and invisible generation labels from images and video. It supports the removal of marks from providers such as Gemini, Sora, and Veo.
Beyond cleaning outputs, the tool allows professionals to identify AI provenance signals. It uses hash-bound oracle checks from Google, OpenAI, Microsoft, and Meta to verify if a file was AI-generated or carries specific provider metadata.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
I’m using
Install the visible-processing CLI and agent skill
Installs: The remove-ai-watermarks CLI with the visible extra, plus the repository's documented agent-skill installation. · Claude Code, Codex, Cursor
Before you start
Python 3.11 through 3.14.
uv and npx available in the terminal.
Run these commands in a terminal to install the CLI with visible-processing dependencies and then the agent skill.
uv tool install "remove-ai-watermarks[visible]" # CLI for visible marks and metadata
npx skills add wiltodelta/remove-ai-watermarks # agent skill for Claude Code, Codex, Cursor, and other agents
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.
Make sure remove-ai-watermarks is installed in your agent before trying this task.
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.
A checkout of the remove-ai-watermarks repository, with the repository root as the working directory.
The project documents and coverage reference listed in the skill.
Make sure signal-discovery is installed in your agent before trying this task.
Use the signal-discovery skill from the remove-ai-watermarks repository root. Read its required project references, then inventory the current image and video visible-mark registries, metadata readers and strippers, local invisible decoders, vendor routes, supported containers, and identify signal families. Compare that inventory with the coverage matrix and report discrepancies. Keep this first pass read-only, without refreshing corpora or running provider uploads.
A checkout of the remove-ai-watermarks repository containing docs/provider-oracles.md and scripts/provider_oracles.py.
One provider to review: Google, OpenAI, Microsoft, or Meta.
Make sure provider-oracles is installed in your agent before trying this task.
Use the provider-oracles skill to review the available verification surfaces for one provider I name. Read docs/provider-oracles.md and use the repository tooling for surface discovery. Summarize the documented surface priority and any setup gaps. Do not upload files, log in, or submit verification requests.
Claude
Codex
Cursor
Gemini CLI