Extract layout-aware text and tables from PDFs with OCR.
npx skills add https://github.com/ruuxi/stella --skill pdf-ruuxi
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/ruuxi/stella/tree/main/runtime/home-seed/skills/pdf Command: npx skills add https://github.com/ruuxi/stella --skill pdf-ruuxi
Working with PDFs often leads to frustrating, unreliable results: extracted text misses layout context, scanned documents are completely unreadable with standard tools, and generated PDFs have broken fonts, clipped content, or misaligned elements. This Skill eliminates those issues by providing vetted tools and clear workflows for every common PDF task.
Use this Skill to extract all text and table data from your attached scanned invoice PDF and export the results to a CSV file.
High-intent search queries and answers about installing and using this skill.
To extract text from a scanned PDF without losing layout, this Skill applies OCR with reading order detection to convert image-based documents into readable content while preserving multi-column structures and coordinate context.
The best way to extract table data from PDF invoices is using layout-aware text extraction to pull structured data while preserving coordinate context, which can then be compiled into a structured spreadsheet or CSV for accounting workflows.
To generate a PDF from structured content without broken fonts or clipped elements, this Skill creates files and performs mandatory visual layout verification before final delivery to ensure layout fidelity.
Standard PDF text extraction fails on multi-column scanned documents because it lacks reading order detection and layout-aware coordinate context, issues this Skill resolves by applying advanced OCR specifically for complex structures.
Yes, you can split, merge, and rotate existing PDF pages without disrupting the original layout, as the workflow includes visual layout verification to ensure structural fidelity before final delivery.
lyq-linExtract text from PDFs and create or merge PDF documents.
robwestzConvert heavyweight PDFs, Office documents, and spreadsheets into markdown or CSV artifacts.
Ryno-Crypto-Mining-ServicesExtract text, tables, and images from PDFs using Python libraries.
MarbleSodasExtract searchable text from PDFs and scanned documents via web or local parsing.
