Extract, fill, and annotate PDF forms using Python tooling.
npx skills add https://github.com/Pans0020/opencode-skills --skill pdf-pans0020
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/Pans0020/opencode-skills/tree/main/pdf Command: npx skills add https://github.com/Pans0020/opencode-skills --skill pdf-pans0020
It removes the manual, error-prone work of extracting information from PDFs and filling their forms by providing an end-to-end toolkit for PDF parsing, transformation, and form handling.
Use Case: You receive scanned or standardized forms as PDFs and need to batch-fill them with values (e.g., names, dates, checkboxes) while validating locations and ensuring viewers render appearances correctly.
Tell the AI to fill a PDF form for the attached file "intake-form.pdf" using field values you provide, and the Skill will produce a completed PDF output.
High-intent search queries and answers about installing and using this skill.
PDF data extraction works by reading text and form field geometry with pdfplumber, converting pages to images with pdf2image for layout-aware analysis, and using pytesseract for OCR on scanned documents to capture content.
You need Python with pypdf, pdfplumber, pdf2image, pillow, pypdfium2, reportlab, and pytesseract installed. These libraries support parsing, rendering, transforming, and applying OCR to PDF documents for comprehensive form processing.
For scanned forms, use pytesseract for OCR to extract text, convert pages to images with pdf2image to understand layout geometry, and apply coordinate transforms to map extracted data to the correct positions before adding annotations.
A limitation occurs when viewers do not render appearances correctly after filling AcroForm fields. This is handled by following deterministic field handling and validation steps to ensure the PDF output displays populated values accurately.
keturkFill PDF forms and extract text and tables using Python libraries.
copilot-ldConvert PDFs, PowerPoints, and images into Schema.org annotated HTML.
marktantongcoCreate, convert, and manipulate PDF documents across generation and processing pipelines.
AllBeingsFutureExtract text, tables, images, and form data from PDFs.
