菜单
全面的 PDF 操作 工具包 for 提取文字 and 表格, 創建新的 PDFs, 合併/分割 文檔, and 處理表單. 當需要 to fill in a PDF form or 以程式方式 處理, 生成, or 分析 PDF 文檔 大規模.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
生成適用於金融機器學習的高質量特徵。包含分數階差分 (Fractional Differentiation) 與無前視偏差的滾動標準化。
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf 文檔 using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
| name | |
| description | 全面的 PDF 操作 工具包 for 提取文字 and 表格, 創建新的 PDFs, 合併/分割 文檔, and 處理表單. 當需要 to fill in a PDF form or 以程式方式 處理, 生成, or 分析 PDF 文檔 大規模. |
| trigger | when_needed |
| language | zh-TW |
| adapted_from | openskills/pdf |
| version | 1.0.0-antigravity |
| original_license | Proprietary. LICENSE.txt has complete terms |
技能版本: v1.0 (Antigravity 適配版)
原始來源: openskills/pdf
語言: 繁體中文
全面的 PDF 操作 工具包 for 提取文字 and 表格, 創建新的 PDFs, 合併/分割 文檔, and 處理表單. 當需要 to fill in a PDF form or 以程式方式 處理, 生成, or 分析 PDF 文檔 大規模.
此技能適用於以下情況：
本指南 covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see reference.md. If you need to fill out a PDF form, read forms.md and follow its instructions.
詳細內容請參閱：example_5.py
詳細內容請參閱：example_6.py
詳細內容請參閱：example_7.py
詳細內容請參閱：example_8.py
詳細內容請參閱：example_9.py
詳細內容請參閱：example_10.py
詳細內容請參閱：example_11.py
詳細內容請參閱：example_12.py
詳細內容請參閱：example_13.py
詳細內容請參閱：example_14.py
詳細內容請參閱：script_14.sh
詳細內容請參閱：script_15.sh
詳細內容請參閱：script_16.sh
詳細內容請參閱：example_15.py
詳細內容請參閱：example_16.py
# Using pdfimages (poppler-utils)
pdfimages -j input.pdf output_prefix
# This extracts all images as output_prefix-000.jpg, output_prefix-001.jpg, etc.
詳細內容請參閱：[example_17.txt](examples/example_17.txt)
## 快速參考
| Task | Best Tool | Command/Code |
|------|-----------|--------------|
| Merge PDFs | pypdf | `writer.add_page(page)` |
| Split PDFs | pypdf | One page per file |
| Extract text | pdfplumber | `page.extract_text()` |
| Extract tables | pdfplumber | `page.extract_tables()` |
| Create PDFs | reportlab | Canvas or Platypus |
| Command line merge | qpdf | `qpdf --empty --pages ...` |
| OCR scanned PDFs | pytesseract | Convert to image first |
| Fill PDF forms | pdf-lib or pypdf (see forms.md) | See forms.md |
## 後續步驟
- For advanced pypdfium2 usage, see reference.md
- For JavaScript libraries (pdf-lib), see reference.md
- If you need to fill out a PDF form, follow the instructions in forms.md
- For troubleshooting guides, see reference.md
---
## 專案整合
此技能已適配 Antigravity 系統：
- 遵循 `skills/_base/coding_style.md` 編碼規範
- 與 `skills/_base/architecture.md` 架構模式一致
- 符合 Constitution v3.1 語言規範 (繁體中文)
### 相關技能
可搭配以下技能使用：
- `systematic-debugging` - 系統化除錯
- `verification-before-completion` - 完成前驗證