pdf

Extracts text and tables from PDFs and outputs structured JSON or PDFs.

2|1|Updated Feb 9, 2026

Search Tags:#pdf #data-extraction #batch-processing #form-filling #pdf-processing #markdown-to-pdf

Ready to run

npx skills add https://github.com/costa-marcello/skillkit --skill pdf-costa-marcello

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/costa-marcello/skillkit/tree/main/skills/pdf
Command: npx skills add https://github.com/costa-marcello/skillkit --skill pdf-costa-marcello

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, weasyprint, markdown, pdf2image, Pillow, and includes scripts (resource) components.

What problem does it solve?

PDF workflows are fragmented and time-consuming, requiring manual extraction, form handling, and document assembly across multiple tools.

Core Features & Use Cases

Extracts text and tables from PDFs and converts to searchable formats.
Merges, splits, rotates, and creates PDFs from Markdown or other sources.
Fills both fillable and non-fillable forms and automates batch document workflows.
Use Case: Process a batch of invoices to extract line items, fill metadata, and generate a consolidated report.

Quick Start

Run the Extract Text workflow on a sample PDF to extract all content and save it to a text file.

Frequently Asked Questions about pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text and tables from a batch of PDF invoices?▼

PDF extraction for batch invoices is automated by this Skill, which parses text and tables from multiple files and outputs structured JSON data. It uses pypdf and pdfplumber to isolate line items and metadata for consolidated reporting.

What is the best way to convert markdown to PDF for report generation?▼

Converting markdown to PDF for report generation is handled directly by this Skill using the weasyprint library. It transforms markdown source files into formatted PDF documents, enabling automated document assembly without manual formatting steps.

Can I automate filling both fillable and non-fillable PDF forms?▼

Automating PDF form filling for both fillable and non-fillable forms is supported by this Skill. It references field extraction mappings to populate metadata across batch workflows, allowing you to complete forms without manual data entry.

Does this PDF processing workflow support merging and splitting files?▼

PDF processing workflows in this Skill fully support merging, splitting, and rotating PDF files. You can assemble new documents from existing sources or divide large PDFs into individual pages within the same batch processing pipeline.

Do I need Python libraries like weasyprint and pypdf installed to process PDFs?▼

Python libraries like weasyprint, pypdf, pdf2image, and Pillow are required dependencies for this Skill to process PDFs. The environment must include these packages to execute the extraction, form-filling, and markdown conversion scripts.