🎓 Student | 🐍 Python | 🤖 AI & Computer Vision Learner
aidenwu0209 publishes skills that let AI agents extract text and structure from documents, including PDF table and formula extraction into Markdown or JSON, and OCR of images, screenshots and scanned PDFs with strength on CJK text. The most popular skills also cover setup of PaddleOCR-based tools across several agent platforms, with a focus on Python-driven document parsing.
Paddleocr Skills
3 skills · 35 stars · Apache-2.0
Extract tables and formulas from PDF and PdfCraft files Get Markdown or JSON from scanned PDFs with tables, LaTeX formulas and reading order.
Paddleocr Skills Setup Install and configure two PaddleOCR Agent Skills for text recognition and structured document par…
Paddleocr Text Recognition Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or…