AI增强专家。提供智能摘要、翻译、问答功能。支持8大AI平台。Use when you need AI-powered PDF analysis, summarization, translation, or Q&A.
深度分析PDF内容,包括文本提取、表格识别、图片分析。Use when you need to understand PDF content, extract text/tables/images, or perform OCR. Automatically activates for content analysis tasks.
批量处理专家。处理大量PDF文件的合并、拆分、转换等操作。Use when you need to process multiple PDF files at once.
PDF比较专家。对比两个PDF文件的差异,包括文本、布局、图片。Use when you need to compare two PDF files and identify differences.
PDF压缩专家。减小PDF文件大小,优化存储和传输。Use when you need to reduce PDF file size for storage or transmission.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
ai_api_keyAI提供商API密钥(如使用Claude则设置ANTHROPIC_API_KEY)
${user_config.ai_api_key}ocr_engine默认OCR引擎 (tesseract/paddleocr)
${user_config.ocr_engine}output_dir默认输出目录
${user_config.output_dir}ai_provider默认AI提供商 (claude/openai/gemini/deepseek/qwen/zhipu/moonshot/ollama)
${user_config.ai_provider}output_format默认输出格式 (text/markdown/json)
${user_config.output_format}Uses power tools
Uses power tools
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
🚀 全能型 PDF 处理 Claude Code 插件
一个插件,覆盖所有 PDF 场景 — 解析、编辑、转换、AI 增强、OCR、安全
痛点:处理 PDF 需要组合多个工具 — pypdf 提取文本、pdfplumber 提取表格、PyMuPDF 合并拆分、还要单独配置 OCR 和 AI...
解法:PDF-Master 一个插件搞定全部,28+ 种操作,开箱即用。
| 特性 | 说明 |
|---|---|
| 🧩 一站式 | 无需组合多个工具,一个插件覆盖所有 PDF 场景 |
| 🤖 8 大 AI 平台 | Claude / OpenAI / Gemini / DeepSeek / Qwen / 智谱 / Moonshot / Ollama |
| 🔍 双引擎 OCR | Tesseract + PaddleOCR,覆盖 100+ 语言 |
| 🔒 企业级安全 | AES-256 加密、敏感信息涂抹、签名验证 |
| 📐 LaTeX 渲染 | pdflatex / xelatex / lualatex 三大引擎 |
| ✅ 生产就绪 | 343 测试用例 + CI/CD + 完整文档 |
| 功能 | PDF-Master | pypdf | PyMuPDF | pdfplumber |
|---|---|---|---|---|
| 文本提取 | ✅ | ✅ | ✅ | ✅ |
| 表格提取 | ✅ | ❌ | ❌ | ✅ |
| 图片提取 | ✅ | ✅ | ✅ | ❌ |
| 合并/拆分 | ✅ | ✅ | ✅ | ❌ |
| 水印/旋转 | ✅ | ✅ | ✅ | ❌ |
| 加密/解密 | ✅ | ✅ | ✅ | ❌ |
| OCR 识别 | ✅ | ❌ | ❌ | ❌ |
| AI 摘要 | ✅ | ❌ | ❌ | ❌ |
| AI 翻译 | ✅ | ❌ | ❌ | ❌ |
| AI 问答 | ✅ | ❌ | ❌ | ❌ |
| 表单填充 | ✅ | ✅ | ❌ | ❌ |
| LaTeX 渲染 | ✅ | ❌ | ❌ | ❌ |
| PDF 压缩 | ✅ | ❌ | ✅ | ❌ |
| PDF 修复 | ✅ | ❌ | ✅ | ❌ |
| PDF 比较 | ✅ | ❌ | ❌ | ❌ |
| 批量处理 | ✅ | ❌ | ❌ | ❌ |
| 数字签名 | ✅ | ❌ | ❌ | ❌ |
| PDF/A 转换 | ✅ | ❌ | ❌ | ❌ |
| 安全审计 | ✅ | ❌ | ❌ | ❌ |
| 书签管理 | ✅ | ❌ | ❌ | ❌ |
| 链接管理 | ✅ | ❌ | ❌ | ❌ |
| 注释管理 | ✅ | ❌ | ❌ | ❌ |
| PDF → Word | ✅ | ❌ | ❌ | ❌ |
# 1. 添加 marketplace
/plugin marketplace add ZSHYC/pdf-master
# 2. 安装插件
/plugin install pdf-master@zshyc-pdf-master
# 3. 重新加载插件
/reload-plugins
# 4. 使用插件技能(命名空间格式)
/pdf-master:pdf extract document.pdf
/pdf-master:pdf summarize document.pdf
# 克隆仓库
git clone https://github.com/ZSHYC/pdf-master.git
cd pdf-master
# 安装核心依赖
pip install -r requirements.txt
# 使用 --plugin-dir 测试
claude --plugin-dir .
# 复制到项目目录
cp -r pdf-master .claude/plugins/
# 在 .claude/settings.json 中启用
{
"enabledPlugins": {
"pdf-master@local": true
}
}
# 加载插件后,使用 /pdf 命令
/pdf extract document.pdf # 提取文本
/pdf merge file1.pdf file2.pdf -o merged.pdf
/pdf summarize document.pdf # AI 摘要
/pdf ocr scanned.pdf # OCR 识别
# 方式一:环境变量
export ANTHROPIC_API_KEY="your-key"
# 方式二:配置文件(推荐)
cp config/config.yaml.example config/config.yaml
# 编辑 config/providers.yaml
# 方式三:CLI 工具
python skills/pdf/scripts/pdf_config.py add
# 文本提取(支持布局保留)
python scripts/extract_text.py input.pdf -o output.txt
# 表格提取(JSON/CSV/Excel)
python scripts/extract_tables.py input.pdf -o tables.json
# 图片提取
python scripts/extract_images.py input.pdf -o images/
# 元数据提取
python scripts/extract_metadata.py input.pdf
# 合并 PDF
python scripts/merge_pdfs.py file1.pdf file2.pdf -o merged.pdf
# 拆分 PDF
python scripts/split_pdf.py input.pdf -p 1-5 -o output.pdf
# 旋转页面
python scripts/rotate_pdf.py input.pdf --angle 90 -o output.pdf
# 添加水印
python scripts/watermark_pdf.py input.pdf --image stamp.png -o output.pdf
# PDF → 图片
python scripts/convert_pdf_to_images.py input.pdf -o images/
# PDF → Excel
python scripts/pdf_to_excel.py input.pdf -o output.xlsx
# PDF → Markdown
python scripts/pdf_to_markdown.py input.pdf -o output.md
# PDF → Word (多后端支持)
python scripts/pdf_to_word.py input.pdf -o output.docx # 自动选择最佳后端
python scripts/pdf_to_word.py input.pdf -o output.docx --backend pdf2docx # 图片+格式完整保留
python scripts/pdf_to_word.py input.pdf -o output.docx --backend docling # 学术论文高精度解析
PDF → Word 后端对比 (2026年最新)
| 后端 | Stars | 特点 | 适用场景 |
|---|---|---|---|
| pdf2docx | 3.4k | 图片+格式完整保留 | 图文混排文档 |
| Docling (IBM) | 57.8k | 深度学习高精度解析 | 学术论文、表格结构 |
| pdfplumber | 10.1k | 简单文本提取 | fallback兜底 |
# 智能摘要
python scripts/summarize_pdf.py document.pdf --provider claude
# 文档问答
python scripts/qa_pdf.py document.pdf --question "主要观点是什么?"
# AI 翻译
python scripts/translate_pdf.py document.pdf --to en --provider openai
# Tesseract OCR
python scripts/ocr_pdf.py scanned.pdf -o output.txt --engine tesseract --lang chi_sim+eng
npx claudepluginhub zshyc/pdf-master --plugin pdf-masterAnthropic's production PDF skill — extract text and tables, fill forms and generate PDFs. Essential for financial statements, contracts and scanned invoices.
Official Anthropic skills for PDF, Word, PowerPoint, and Excel document processing.
Parse PDF / Office / image files into clean Markdown via MinerU — zero-dependency, AI-Native, auto-routing between the free Agent API and the token-gated Standard API, with 15 content-tool delivery sinks.
Professional document processing suite: 3 comprehensive skills for Word (.docx), Excel (.xlsx), and PDF files - create, edit, analyse, and process documents with advanced features like tracked changes, forms, tables, OCR, and formulas
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction. Originally from OpenAI's curated skills catalog.
Office document manipulation plugins for Claude Code