Remove AI Marks

by ShadowAqueduct

Remove AI Marks is an Automation skill for Claude Code, published by ShadowAqueduct in watermark-remover.

760 stars73 forkson ShadowAqueduct/watermark-removerAdded 2026/08/24Repository updated 2026/08/23

View source on GitHub Download repo ZIP

claude-aiclaude-codeclaude-code-pluginclaude-skillscodexcodex-clicodex-skillcodex-skillswatermark

Install in seconds

Install Remove AI Marks

Copy Remove AI Marks into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/ShadowAqueduct/watermark-remover/tree/main/skills/remove-ai-marks ~/.claude/skills/remove-ai-marks

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/ShadowAqueduct/watermark-remover.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/remove-ai-marks/SKILL.md in ShadowAqueduct/watermark-remover
Installs to: ~/.claude/skills/remove-ai-marks
Collection: One of 2 skills cataloged from this repository
Category: Automation — 1523 skills

What Remove AI Marks does

Remove AI marks strips hidden Unicode, statistical rewrite signals, and file metadata from owned text and common document/image formats. Use it when cleaning AI-generated content, C2PA/content credentials, or provenance data in files you control.

Remove AI Marks is cataloged under Automation on DirSkills. Remove AI Marks comes from a repository tagged claude-ai, claude-code, claude-code-plugin, claude-skills and codex.

Documentation

README

Excerpt

Remove AI marks

Hygiene for text (Unicode + statistical rewrite) and files (C2PA / AI metadata on common containers).

Read when needed:

references/mark-classes.md — Unicode / sampling / C2PA / containers
references/vendor-notes.md — Claude, Gemini/SynthID, OpenAI, open-LLM
references/removal-matrix.md — which layer when
references/ethics.md — intended use
references/how-claude-marks.md — Anthropic-specific detail
references/markdiffusion.md — optional MarkDiffusion image harness

This skill is a thin HTTP client. All deterministic cleaning lives in this repo’s service/. The agent host does not need Python, venvs, or cleaner binaries. Call the service with curl. Never run cleaning scripts on the host.

Reach the service

This is the opening of the README. Read the full README on GitHub.

Commands Remove AI Marks provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/health
/capabilities
/openapi
/inspect
/detect
/clean
/data

Frequently asked about Remove AI Marks

What else does ShadowAqueduct publish alongside Remove AI Marks?
Remove AI Marks is one of 2 skills that DirSkills catalogs from ShadowAqueduct/watermark-remover, the repository it ships in. Its siblings there include Clean User-Facing Text. Each one is a separate skill with its own page in this directory, installs the same way Remove AI Marks does, and is maintained by ShadowAqueduct in that same repository. The rest of the collection is listed on the ShadowAqueduct/watermark-remover page.
How does Remove AI Marks compare to other Automation skills?
Remove AI Marks ranks #1024 by stars among the 1523 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Remove AI Marks against them. Open each page to compare what they document and how they install.