Agent Skills › anymouschina/TapCanvas › pdf

pdf

GitHub

提供PDF文件处理技能，包括文本提取、创建、合并、拆分及元数据读取。支持通过命令行工具（如pdftotext, pandoc）或Python库（PyMuPDF, ReportLab）实现，涵盖从Markdown/HTML生成PDF及OCR扫描版处理的最佳实践。

apps/agents-cli/skills/pdf/SKILL.md anymouschina/TapCanvas

Trigger Scenarios

用户需要提取PDF中的文本内容用户希望将Markdown或HTML转换为PDF 用户需要合并或拆分PDF文档

Install

npx skills add anymouschina/TapCanvas --skill pdf -g -y

More Options

Non-standard path

npx skills add https://github.com/anymouschina/TapCanvas/tree/main/apps/agents-cli/skills/pdf -g -y

Use without installing

npx skills use anymouschina/TapCanvas@pdf

指定 Agent (Claude Code)

npx skills add anymouschina/TapCanvas --skill pdf -a claude-code -g -y

安装 repo 全部 skill

npx skills add anymouschina/TapCanvas --all -g -y

预览 repo 内 skill

npx skills add anymouschina/TapCanvas --list

SKILL.md

Frontmatter

{
    "name": "pdf",
    "description": "处理 PDF 文件：提取文本、创建 PDF、合并文档等；适用于用户要读\/生成\/合并 PDF 或进行 PDF 相关处理。"
}

PDF Processing Skill

You now have expertise in PDF manipulation. Follow these workflows:

Reading PDFs

Option 1: Quick text extraction (preferred)

# Using pdftotext (poppler-utils)
pdftotext input.pdf -  # Output to stdout
pdftotext input.pdf output.txt  # Output to file

# If pdftotext not available, try:
python3 -c "
import fitz  # PyMuPDF
doc = fitz.open('input.pdf')
for page in doc:
    print(page.get_text())
"

Option 2: Page-by-page with metadata

import fitz  # pip install pymupdf

doc = fitz.open("input.pdf")
print(f"Pages: {len(doc)}")
print(f"Metadata: {doc.metadata}")

for i, page in enumerate(doc):
    text = page.get_text()
    print(f"--- Page {i+1} ---")
    print(text)

Creating PDFs

Option 1: From Markdown (recommended)

# Using pandoc
pandoc input.md -o output.pdf

# With custom styling
pandoc input.md -o output.pdf --pdf-engine=xelatex -V geometry:margin=1in

Option 2: Programmatically

from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("output.pdf", pagesize=letter)
c.drawString(100, 750, "Hello, PDF!")
c.save()

Option 3: From HTML

# Using wkhtmltopdf
wkhtmltopdf input.html output.pdf

# Or with Python
python3 -c "
import pdfkit
pdfkit.from_file('input.html', 'output.pdf')
"

Merging PDFs

import fitz

result = fitz.open()
for pdf_path in ["file1.pdf", "file2.pdf", "file3.pdf"]:
    doc = fitz.open(pdf_path)
    result.insert_pdf(doc)
result.save("merged.pdf")

Splitting PDFs

import fitz

doc = fitz.open("input.pdf")
for i in range(len(doc)):
    single = fitz.open()
    single.insert_pdf(doc, from_page=i, to_page=i)
    single.save(f"page_{i+1}.pdf")

Key Libraries

Task	Library	Install
Read/Write/Merge	PyMuPDF	`pip install pymupdf`
Create from scratch	ReportLab	`pip install reportlab`
HTML to PDF	pdfkit	`pip install pdfkit` + wkhtmltopdf
Text extraction	pdftotext	`brew install poppler` / `apt install poppler-utils`