AGENT SKILL
processing-pdfs
Processes PDF files. Extracts text and tables, fills forms, merges and splits documents, batch-processes files, converts to images, and generates PDFs programmatically. Use when working with .pdf files. Do NOT use for Word documents, spreadsheets, or presentations.
使用场景文档处理
- License 许可
- MIT
- 最近更新
- 2026-07-19
- Stars
- ★ 245
- Forks
- 35
01 前言 Front Matter
- name
- processing-pdfs
- description
- Processes PDF files. Extracts text and tables, fills forms, merges and splits documents, batch-processes files, converts to images, and generates PDFs programmatically. Use when working with .pdf files. Do NOT use for Word documents, spreadsheets, or presentations.
- allowed-tools
- Bash, Read, Write, Edit, Glob
- argument-hint
- <file.pdf | task>
- user-invocable
- false
02 资源文件 12
- 参考文档FORMS.md9.2 KB
- 参考文档REFERENCE.md16.3 KB
- 参考文档references/advanced.md1.1 KB
- 参考文档references/recipes.md3.3 KB
- 脚本scripts/check_bounding_boxes_test.py8.6 KB
- 脚本scripts/check_bounding_boxes.py3.1 KB
- 脚本scripts/check_fillable_fields.py362 B
- 脚本scripts/convert_pdf_to_images.py1.1 KB
- 脚本scripts/create_validation_image.py1.6 KB
- 脚本scripts/extract_form_field_info.py6.0 KB
- 脚本scripts/fill_fillable_fields.py4.7 KB
- 脚本scripts/fill_pdf_form_with_annotations.py3.5 KB
03 SKILL.md 正文
PDF Processing
Essential PDF operations using Python libraries and CLI tools.
Decision Matrix
| Task | Best Tool | Reference |
|---|---|---|
| Merge / split / metadata / rotate | pypdf | recipes.md |
| Extract text (layout preserved) | pdfplumber | recipes.md |
| Extract tables | pdfplumber | recipes.md |
| Create new PDF | reportlab | recipes.md |
| Batch CLI ops | qpdf / pdftk | recipes.md |
| OCR scanned PDFs | pytesseract + pdf2image | advanced.md |
| Add watermark / extract images / encrypt | pypdf / pdfimages | advanced.md |
| Fill PDF forms | pdf-lib / pypdf | FORMS.md |
| Advanced pypdfium2 / pdf-lib JS | — | REFERENCE.md |
Quick Start
from pypdf import PdfReader
reader = PdfReader("document.pdf")
print(f"Pages: {len(reader.pages)}")
text = "".join(page.extract_text() for page in reader.pages)
Workflow
- Identify task — text extraction? table? creation? form? Pick row from matrix above.
- Load reference — recipes.md covers 90% of tasks; advanced.md for OCR / encrypt; FORMS.md for forms.
- Implement — copy-adapt recipe; verify output.
- Validate — open in a viewer or grep extracted text.
Library Selection
| Library | Use for |
|---|---|
| pypdf | Merge, split, metadata, encryption, rotation |
| pdfplumber | Text extraction with layout, tables |
| reportlab | Generate PDFs programmatically |
| pdf2image + pytesseract | OCR scanned documents |
| qpdf / pdftk (CLI) | Batch ops, no Python needed |
