watermarks-remover
Skill1 starsChanged 48 days agoMITView on GitHub
Strip multi-vendor AI provenance marks, invisible Unicode characters (ZWSP, ZWNJ, Bidi, variation selectors), statistical text watermarks, and C2PA/EXIF/XMP metadata from files (PNG, JPEG, PDF, DOCX, MD, TXT).
- Sends data out
In this repository125 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skill-authoringSkill
- apple-notesSkill
- apple-remindersSkill
- findmySkill
- imessageSkill
- agy-customizationsSkill
- antigravity-guideSkill
- awesome-skills-masterSkill
- claude-codeSkill
- codexSkill
- computer-useSkill
- context-modeSkill
- dogfoodSkill
- hermes-agentSkill
- opencodeSkill
- rag-local-lancedbSkill
- skills-sh-registrySkill
- yuanbaoSkill
- libretranslate-markdown-i18nSkill
- mt-markup-preserving-translationSkill
- architecture-diagramSkill
- ascii-artSkill
- ascii-videoSkill
- baoyu-infographicSkill
- claude-designSkill
- comfyuiSkill
- design-mdSkill
- excalidrawSkill
- humanizerSkill
- manim-videoSkill
- p5jsSkill
- popular-web-designsSkill
- portfolio-github-pagesSkill
- pretextSkill
- sketchSkill
- songwriting-and-ai-musicSkill
- touchdesigner-mcpSkill
- jupyter-live-kernelSkill
- suap-iff-apiSkill
- desktop-themingSkill
- hermes-desktop-pluginsSkill
- docker-single-port-multi-instanceSkill
- hybrid-desktop-server-opsSkill
- himalayaSkill
- codebase-inspectionSkill
- git-conventional-commitsSkill
- github-authSkill
- github-code-reviewSkill
- github-issue-pr-attribsSkill
- github-issuesSkill
- github-profile-readmeSkill
- github-pr-workflowSkill
- github-repo-managementSkill
- github-starred-kbSkill
- hermes-installed-catalogSkill
- readme-templateSkill
- cv-latex-multilingualSkill
- latex-cv-maintenanceSkill
- gif-searchSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 63
Use the included helper script to strip invisible Unicode code points from any text or file:
- Very specific: line 77
When connected to a watermarks-remover HTTP service (http://127.0.0.1:8765):
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Multi-Vendor AI Watermark & Provenance Remover
Purity rules: Open hygiene and privacy tool for user-owned content. No proprietary keys or closed endpoints embedded.
This skill strips multi-vendor AI provenance marks from text and document files, covering invisible Unicode injection (Layer A), statistical sampling watermarks (Layer B), and signed C2PA / EXIF / XMP container metadata.
When to Use
- Stripping invisible Unicode characters (
ZWSP,ZWNJ,VS16, BiDi controls) from AI-generated text or copy. - Cleaning signed C2PA / Content Credentials and EXIF/XMP metadata from images and documents.
- Sanitizing Markdown, DOCX, PDF, or text files for clean publishing and privacy hygiene.
- Triggered by requests like "remove AI watermarks", "clean invisible unicode", "strip C2PA", or
/remove-ai-marks.
Architecture & Layers
┌────────────────────────────────────────────────────────────────────────────┐
│ INPUT ARTIFACT │
└──────────────────────┬───────────────────────────────┬─────────────────────┘
│ │
[Text / Code / Markdown] [Media & Document Files]
│ │
▼ ▼
┌───────────────────────────────┐ ┌───────────────────────────┐
│ LAYER A: Invisible Unicode │ │ LAYER C: Container Meta │
│ (ZWSP, Tags, BiDi, Selectors) │ │ (C2PA, EXIF, XMP, OOXML) │
│ -> scripts/clean_unicode.py │ │ -> exiftool / zip scrub │
└───────────────┬───────────────┘ └─────────────┬─────────────┘
│ │
▼ │
┌───────────────────────────────┐ │
│ LAYER B: Statistical Tokens │ │
│ (SynthID, Green-list LLM) │ │
│ -> Paraphrase / Rewrite │ │
└───────────────┬───────────────┘ │
│ │
└───────────────┬───────────────┘
▼
CLEANED ARTIFACT1. Quick Layer A Text Cleaning (Deterministic)
Use the included helper script to strip invisible Unicode code points from any text or file:
# Clean a file in-place
python3 skills/autonomous-ai-agents/watermarks-remover/scripts/clean_unicode.py -i document.md
# Pipe through stdin / stdout
cat input.txt | python3 skills/autonomous-ai-agents/watermarks-remover/scripts/clean_unicode.py > clean.txt2. Remote / Service Cleaning (HTTP API)
When connected to a watermarks-remover HTTP service (http://127.0.0.1:8765):
WM="${WATERMARKS_SERVICE_URL:-http://127.0.0.1:8765}"
# 1. Inspect file for invisible marks and metadata
curl -s -X POST "$WM/inspect" -H 'Content-Type: application/json' \
-d "{\"file\": \"$(base64 < notes.md | tr -d '\n')\", \"name\": \"notes.md\"}"
# 2. Clean file and receive sanitized payload
curl -s -X POST "$WM/clean" -H 'Content-Type: application/json' \
-d "{\"file\": \"$(base64 < notes.md | tr -d '\n')\", \"name\": \"notes.md\"}"3. Metadata Stripping (C2PA / EXIF)
# Strip EXIF and C2PA metadata from images
exiftool -all= -overwrite_original image.png
# Re-encode image to drop auxiliary signed chunks
ffmpeg -i input.png -map_metadata -1 -c:v png output.pngReferences
- Mark Classes Guide — Breakdown of edit-based, statistical, and container marks.
- Vendor Notes — Claude, Gemini (SynthID), OpenAI, and open LLM notes.
- Standalone Python cleaner:
scripts/clean_unicode.py.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

