This does what it says: removes watermarks from images using four different methods depending on your priority. The smart routing is nice, it auto-detects Google SynthID watermarks and uses the aggressive crop method that's proven to work, while falling back to ML-based inpainting for everything else. The inpaint method preserves dimensions and works on any watermark type, which matters more than you'd think when you're cleaning up stock photos or AI-generated images for production. Batch processing is built in, though you'll want to check dimensions first since some methods crop 120px off the corner. It's honest about tradeoffs: speed versus quality, cropping versus preservation.

skills.sh installs
128
last updated
Jun 3, 2026

Install

$ npx -y skills add horace4444/extend-my-claude-code --skill watermark-removal --agent claude-code

Installs into .claude/skills of the current project.

Files

Universal Watermark Removal

Remove watermarks from ANY image source using intelligent detection and proven methods. Smart routing: automatically detects Google SynthID and uses the proven aggressive method, falls back to ML inpainting for unknown watermark types.

Quick Start

Single Image - Smart Auto-Detection (Recommended)

# Smart detection: Google SynthID → aggressive method (proven), Unknown → inpaint (ML)
python .claude/skills/watermark-removal/scripts/remove-watermark.py \
  input.png \
  output.png

Single Image - Preserve Dimensions (Force ML)

# Force ML inpainting even for Google SynthID (preserves exact dimensions)
python .claude/skills/watermark-removal/scripts/remove-watermark.py \
  input.png \
  output.png \
  --method inpaint

Batch Processing (Get User Approval First!)

⚠️ IMPORTANT: Always ask user before batch processing, especially with crop/aggressive methods that alter dimensions.

# Recommended: Preserves dimensions
python .claude/skills/watermark-removal/scripts/batch-process.py \
  /path/to/input-dir \
  /path/to/output-dir \
  --method inpaint

Sponsors

Details

Repository
github.com/horace4444/extend-my-claude-code
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs