Extract text, tables, and metadata from PDF documents.
npx skills add https://github.com/dthuy62/kollet-app --skill ck-pdf-dthuy62
Please help me install this Agent Skill. Skill: ck:pdf Source: https://github.com/dthuy62/kollet-app/tree/main/.claude/skills/document-skills/pdf Command: npx skills add https://github.com/dthuy62/kollet-app --skill ck-pdf-dthuy62
This Skill removes the manual burden of working with PDF documents by helping you extract content, generate new files, and complete form workflows programmatically.
Ask the assistant to process your PDF by extracting the content you need or filling the form fields in the document you attached.
High-intent search queries and answers about installing and using this skill.
To extract text and tables from a PDF, this Skill uses Python libraries to pull readable content and structured table data directly from the file. It transforms static PDF documents into editable text and structured outputs for reuse and analysis.
Yes, you can fill both fillable and non-fillable PDF forms. The Skill handles field discovery, annotation-based completion, and coordinate-aware placement to populate non-fillable documents using Python PDF libraries and image conversion tools.
For scanned PDF text extraction, the best approach is using OCR recovery workflows. The Skill converts PDF pages to images using pdf2image and pillow, then applies OCR to recover readable text from otherwise difficult-to-parse scanned documents.
Yes, this PDF processing approach supports merging, splitting, and watermarking. It handles everyday document operations including rotating, encrypting, and creating PDFs to automate common document manipulation workflows programmatically.
Yes, you need Python PDF libraries and image conversion tools for PDF form completion. The Skill requires pypdf, pdf2image, and pillow to handle both fillable and non-fillable documents with coordinate validation.
Interstellar-codeExtract text and tables from PDFs using Python libraries.
alibabaExtract text, tables, and metadata from PDF documents into JSON.
lxh755818-botExtract text from PDFs and scanned documents using OCR.
manuelbrandner85Extracts text, tables, and images from PDFs with OCR support.
