← Back to Skills Marketplace
91
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install pdf-watermark-remover
Description
Remove image-based watermarks from PDF files (e.g. "Made with Gamma", Canva, Notion watermarks). This skill should be used when the user wants to remove wate...
Usage Guidance
This skill appears coherent and local-only, but take these precautions before using: 1) Always run it on copies/backups of your PDFs — modifying raw content streams and XObjects can corrupt files or remove non-watermark images if thresholds are too broad. 2) Test and tune the --x-threshold/width/height options on sample pages before batch-processing many documents. 3) It only handles image-based watermarks (not text-based watermarks); use redaction for text watermarks. 4) Ensure you have permission to remove watermarks (legal/ethical considerations). 5) Install pymupdf in a controlled environment (virtualenv) and review outputs before sharing them.
Capability Analysis
Type: OpenClaw Skill
Name: pdf-watermark-remover
Version: 1.0.0
The skill provides a utility to remove image-based watermarks from PDF files by surgically deleting drawing instructions from content streams and removing XObject references. The Python script `scripts/remove_watermark.py` uses the legitimate `pymupdf` library and standard regex operations to perform these modifications locally. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection instructions in `SKILL.md`.
Capability Assessment
Purpose & Capability
Name/description match the included script and SKILL.md: the skill needs Python and pymupdf and the code implements content-stream/XObject edits to remove image watermarks. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
SKILL.md instructs the agent to analyze and run the included script against local PDF files and to tune detection thresholds. It does not direct reading unrelated files, exfiltrating data, or contacting external endpoints.
Install Mechanism
No install spec or remote download is used. The only runtime dependency is pymupdf which the SKILL.md documents (pip install). The skill is instruction+script-only and nothing is fetched from arbitrary URLs.
Credentials
The skill requests no environment variables, credentials, or config paths. The few required runtime items (Python 3.8+ and pymupdf) are proportional to the task.
Persistence & Privilege
always is false and the skill does not request persistent system modifications or modify other skills' settings. It operates on user-supplied input/output files only.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pdf-watermark-remover - After installation, invoke the skill by name or use
/pdf-watermark-remover - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
首次发布：从PDF内容流中删除图片水印绘制指令，零视觉残留
Metadata
Frequently Asked Questions
What is PDF Watermark Remover?
Remove image-based watermarks from PDF files (e.g. "Made with Gamma", Canva, Notion watermarks). This skill should be used when the user wants to remove wate... It is an AI Agent Skill for Claude Code / OpenClaw, with 91 downloads so far.
How do I install PDF Watermark Remover?
Run "/install pdf-watermark-remover" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is PDF Watermark Remover free?
Yes, PDF Watermark Remover is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does PDF Watermark Remover support?
PDF Watermark Remover is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created PDF Watermark Remover?
It is built and maintained by EARFQUAKE (@ucrossmym1nd); the current version is v1.0.0.
More Skills