PDF Processing Guide

What it does

When your agent uses it

• Extracting text from a PDF report or paper
• Converting a Markdown or HTML file into a PDF
• Merging several PDFs into one or splitting out page ranges
• Reading a scanned PDF that needs OCR

Example prompts

• “Extract the text from invoice-march.pdf and save it to invoice-march.txt.”
• “Merge cover.pdf, part-one.pdf and part-two.pdf into one book.pdf.”
• “Turn README.md into a PDF with pandoc.”

Requirements

• pdftotext from poppler-utils, for text extraction
• Python with PyMuPDF, and ReportLab for creating files
• pandoc or wkhtmltopdf for Markdown or HTML conversion

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Always check if tools are installed before using them
2. 2Handle encoding issues - PDFs may contain various character encodings
3. 3Large PDFs: Process page by page to avoid memory issues
4. 4OCR for scanned PDFs: Use pytesseract if text extraction returns empty

What it can do on your machine

Read from SKILL.md and the folder at commit ce8f9f1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pip
  • pdftotext
  • python3
  • pandoc
  • brew
  • apt

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

PDF Processing Guide loads about 646 tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 123 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~34

When it runs · the whole SKILL.md, loaded when a task matches

~646

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shareAI-lab/learn-claude-code at commit ce8f9f1, republished under its MIT licence (© shareAI-lab). 123 words, ~646 tokens.

name

pdf

description

Process PDF files - extract text, create PDFs, merge documents. Use when user asks to read PDF, create PDF, or work with PDF files.

# 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())
"

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)

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

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

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()

# Using wkhtmltopdf
wkhtmltopdf input.html output.pdf

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

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")

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")

© shareAI-lab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/pdf of shareAI-lab/learn-claude-code.

Open the folder on GitHubat commit ce8f9f1

Used in 6 other repositories

We found 6 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 5 other GitHub owners. This page covers the copy in shareAI-lab/learn-claude-code, which our catalogue first saw on October 7, 2026.

• shareAI-lab/mini-claude-codeskills/pdf
• Chris-debug-0225/learn-claude-code-javaskills/pdf
• wulawulu/learn-claude-code-rsskills/pdf
• Turing-Neo/Turing-coding-agentpackages/turing/skills/pdf
• keyuchen21/agentic-engineering-handbooktutorials/agent-loop/skills/pdf
• juliepy/AI-Engineer-from-scrach06-harnes/learn-claude-code/skills/pdf