mcpbeat

PDF Processing

aiskillstore/pdf-processing

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.

This is a copy. The original lives at comeonoliver/pdf-processing.

2k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
404
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/aiskillstore/marketplace --skill pdf-processing

What comes with it

8 480 bytes besides the instruction
skill-report.json

The instruction itself

8 sections, as written by the author

PDF Processing Skill

This skill provides capabilities for working with PDF documents.

Quick Start

Use pdfplumber to extract text from PDFs:

import pdfplumber

with pdfplumber.open("document.pdf") as pdf:
    text = pdf.pages[0].extract_text()

Capabilities

Text Extraction

  • Extract text from single or multiple pages
  • Preserve layout and formatting
  • Handle multi-column documents

Table Extraction

  • Identify and extract tables
  • Convert to structured data (CSV, JSON)
  • Handle complex table layouts

Form Operations

  • Fill PDF forms programmatically
  • Extract form field values
  • Create fillable forms

Document Operations

  • Merge multiple PDFs
  • Split PDFs by page
  • Rotate pages
  • Add watermarks

Best Practices

  • Always check if the PDF is encrypted before processing
  • Handle OCR cases for scanned documents
  • Validate extracted data for accuracy
  • Use appropriate libraries (pdfplumber for extraction, PyPDF2 for manipulation)

How to use it

Copy the folder

Take aiskillstore/pdf-processing from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.