pdf

Extract text, tables, images, and OCR from PDF files.

190|27|Updated Apr 22, 2026
One-click install
npx skills add https://github.com/linxuan-sys/opencode-skills-chinese --skill pdf-linxuan-sys
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/linxuan-sys/opencode-skills-chinese/tree/main/pdf
Command: npx skills add https://github.com/linxuan-sys/opencode-skills-chinese --skill pdf-linxuan-sys

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, and includes scripts (resource) and references (resource) components.

What problem does it solve?

When PDFs are stuck in an image-like or non-editable format, manually extracting text, tables, and form data wastes significant time and easily causes mistakes.

Core Features & Use Cases

  • PDF text and table extraction using Python and command-line tools (e.g., pdfplumber, pdftotext).
  • PDF manipulation such as merge, split, rotate, watermarking, encryption/decryption, image extraction, and OCR for scanned documents.
  • PDF form handling for both fillable forms (field-based filling) and non-fillable forms (coordinate-based text annotations).

Use case example: Convert a scanned PDF application into searchable text via OCR, then add or annotate specific fields at exact page coordinates, producing an output PDF ready for review.

Quick Start

Ask the AI to extract text (and tables if needed) from invoice-q3.pdf and return the structured results you can reuse.

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 PDF using Python?

To extract text and tables from PDF files, you can use Python libraries like pdfplumber alongside command-line tools to parse documents and return structured data for reuse. This approach reliably converts non-editable PDF content into usable formats.

Can I fill out a non-fillable PDF form programmatically?

Yes, you can fill non-fillable PDF forms by deriving exact page coordinates and writing text annotations directly onto the document. This allows automated form completion even when standard fillable fields are absent.

Does pdfplumber support OCR for scanned documents?

Yes, OCR for scanned documents is supported by converting PDF pages into images using pdf2image, then applying optical character recognition to produce searchable text from previously image-like formats.

What's the best way to merge, split, and rotate PDF pages?

The best way to merge, split, and rotate PDF pages is using deterministic Python libraries like pypdf to parse the document structure and write updated files with the desired page manipulations and appearances.

How do I extract images from a PDF and validate bounding boxes?

You can extract images from PDFs and validate bounding boxes using Python parsing libraries to detect page assets and coordinates accurately. This ensures extracted visual elements maintain their correct spatial dimensions.

Why does PDF text extraction return misaligned or missing data?

PDF text extraction may return misaligned data when documents are scanned images rather than text-based formats, requiring OCR processing to interpret the visual content accurately before extracting usable text.