← Back to Skills Marketplace
pdf-tool
by
Martin-SH-Ni
· GitHub ↗
· v1.0.0
· MIT-0
135
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install pdf-tool
Description
Split, merge, watermark, and extract text from PDF files — PyPDF2 based.
README (SKILL.md)
PDF Tool（PDF批量处理工具）
PDF拆分/合并/水印/文本提取 | PyPDF2驱动
功能 | Features
- ✅ 合并PDF — 多个PDF合并为一个
- ✅ 拆分PDF — 按页数范围拆分
- ✅ 添加水印 — 文字水印保护内容
- ✅ 提取文本 — 提取PDF中的纯文本内容
使用场景 | Use Cases
| 模式 | 说明 |
|---|---|
| merge | 多份合同合并为一本 |
| split | 按章节拆分成独立PDF |
| watermark | 添加"机密"水印 |
| extract_text | 提取合同正文内容 |
使用方式 | Usage
输入参数:
mode 操作模式: split / merge / watermark / extract_text
files 文件路径列表（merge/split用）
output 输出文件路径
watermark 水印文字（watermark模式用）
输出:
success 是否成功
text/msg 结果信息
示例 | Example
# 合并
result = pdf_tool(mode="merge", files=["a.pdf", "b.pdf"], output="merged.pdf")
# 提取文本
result = pdf_tool(mode="extract_text", files=["contract.pdf"])
print(result["text"][:500])
依赖 | Dependencies
PyPDF2 >= 3.0.0
版本 v1.0
Usage Guidance
This skill is coherent with its stated purpose, but a few practical checks are recommended before installing: (1) confirm how your agent platform will satisfy the declared dependency (PyPDF2 >= 3.0.0) and what version will be installed; (2) run the tool on copies of sensitive PDFs and in an environment you control, since malformed PDFs can trigger library vulnerabilities or cause crashes; (3) verify your agent/platform does not automatically upload files or logs to remote services if you plan to process confidential documents; (4) because this is instruction-only (no code to inspect), review any platform-level behavior that might execute or install additional packages on your behalf.
Capability Analysis
Type: OpenClaw Skill
Name: pdf-tool
Version: 1.0.0
The skill bundle contains metadata and documentation for a PDF processing tool (PDF Tool) using PyPDF2. The SKILL.md file provides clear, functional instructions for merging, splitting, and watermarking PDFs without any evidence of prompt injection, malicious directives, or suspicious external references.
Capability Assessment
Purpose & Capability
Name/description (split/merge/watermark/extract text) matches the instructions and declared dependency on PyPDF2. The operations described are what you'd expect for a PDF utility.
Instruction Scope
SKILL.md only describes taking file paths, a mode, and optional watermark text; it does not instruct reading unrelated files, environment variables, or sending data to external endpoints. The scope is limited to local PDF processing.
Install Mechanism
This is an instruction-only skill with no install spec. It declares a dependency (PyPDF2 >= 3.0.0) but does not provide an installation mechanism; the platform or integrator must ensure PyPDF2 is present. This is not malicious but worth verifying before use.
Credentials
No environment variables, credentials, or config paths are requested. The absence of secrets or unrelated credentials is proportionate to the stated purpose.
Persistence & Privilege
Flags show no elevated persistence (always:false). The skill does not request persistent privileges or modify other skills or system-wide config.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pdf-tool - After installation, invoke the skill by name or use
/pdf-tool - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
首发
Metadata
Frequently Asked Questions
What is pdf-tool?
Split, merge, watermark, and extract text from PDF files — PyPDF2 based. It is an AI Agent Skill for Claude Code / OpenClaw, with 135 downloads so far.
How do I install pdf-tool?
Run "/install pdf-tool" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is pdf-tool free?
Yes, pdf-tool is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does pdf-tool support?
pdf-tool is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created pdf-tool?
It is built and maintained by Martin-SH-Ni (@martin-sh-ni); the current version is v1.0.0.
More Skills