Read, extract, merge, and modify PDF documents using Python libraries.
npx skills add https://github.com/guiledo/dotfiles --skill pdf-guiledo
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/guiledo/dotfiles/tree/main/opencode/.config/opencode/skills/pdf Command: npx skills add https://github.com/guiledo/dotfiles --skill pdf-guiledo
This Skill enables end-to-end PDF handling, including reading, extracting text and tables, merging multiple PDFs, splitting pages, rotating, watermarking, creating new PDFs, filling forms, encrypting/decrypting, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Extract all text from input.pdf and merge it with another document to create output.pdf.
High-intent search queries and answers about installing and using this skill.
To extract text from scanned PDFs, OCR processing renders pages into images using pdf2image and Pillow, enabling searchable text extraction. This makes scanned documents fully searchable and machine-readable for downstream data processing.
Yes, you can merge multiple PDFs into a single file and apply watermarks across pages. This workflow consolidates document collections while embedding branding or security marks directly into the output PDF stream.
Yes, PDF form filling and encryption are fully supported. You can populate form fields programmatically and apply encryption to secure the output document, ensuring sensitive data remains protected across multiple pages.
Extracting images from PDFs involves parsing the document stream to isolate embedded image objects. Using libraries like pypdf and pdfplumber, you can render and save embedded images for separate viewing or processing.
Yes, pypdf and pdfplumber are required to parse and modify PDF streams for splitting and rotating pages. These dependencies provide the core functionality to manipulate document structure and render page content accurately.
Text extraction fails when PDFs contain scanned images instead of embedded text streams, requiring OCR to process. Using pdf2image to render pages allows OCR to recognize text, resolving extraction failures on image-only documents.
liueggyExtract text and tables from PDFs and fill forms.
Pans0020Convert Markdown content into DOCX, PPTX, XLSX, PDF, HTML, IPYNB, MD, CSV, JSON/JSONL, XML, and extracted code files.
Leon0050Extract text and tables from PDFs using pypdf and pdf2image.
manuelbrandner85Extracts text, tables, and images from PDFs with OCR support.
