Read, merge, split, rotate, and extract text and images from PDFs.
npx skills add https://github.com/xuthreekid/clawchain --skill pdf-tools-xuthreekid
Please help me install this Agent Skill. Skill: pdf-tools Source: https://github.com/xuthreekid/clawchain/tree/main/backend/data/skills/pdf-tools Command: npx skills add https://github.com/xuthreekid/clawchain --skill pdf-tools-xuthreekid
PDFs are ubiquitous but difficult to search, extract data from, or repurpose across documents. This skill enables robust reading, merging, splitting, rotation, image extraction, metadata handling, and simple generation of new PDFs.
Convert "document.pdf" to a searchable text layer and save results to "document.txt" in the working directory.
High-intent search queries and answers about installing and using this skill.
Extracting text and images from a PDF involves reading the document pages using Python-based tooling like PyPDF2 to retrieve embedded media, outputting searchable text layers and image files for archival conversion.
Merging multiple PDFs or splitting them by page range is achieved by applying document-processing scripts that read, modify, and generate PDFs, resulting in consolidated documents or targeted extracted sections.
Reading and editing PDF metadata to standardize documents requires applying Python-based tooling that accesses internal document properties, allowing you to update attributes and generate standardized PDF files.
Yes, you can use Python to rotate PDF pages for proper orientation by applying document-processing tools that modify page properties, resulting in correctly aligned PDF documents ready for viewing or archival.
Yes, this approach supports simple generation of PDFs from text or Markdown by applying Python-based tooling to read, modify, and generate PDFs, producing new documents from raw text content.
Batch processing legacy PDFs into a searchable archive requires applying document-processing workflows that extract text, images, and structured metadata, converting unstructured PDFs into searchable text layers.
ExuberantWitnessCompile LaTeX source files into PDF documents using latexmk.
sixscripts-aiConfigure vector retrieval pipelines with embedding models and HNSW indexes.
first-flukeConvert PDF documents into structured Markdown with text, tables, and images.
nadicodeaiExtract and convert PDF, scanned document, and image text to plain text or Markdown using OCR and pymupdf/marker-pdf.
