AI Agent Skills

Lightweight & fast OCR models for license plate text recognition.

Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)

A high-performance, open-source PDF data extraction tool. 一站式开源高性能数据提取工具，将复杂 PDF 文档转换为 Markdown 和 JSON 格式，使用onnx模型。

Codex / Claude Skill for editable thesis-defense PPTX from PDF or LaTeX while preserving a PowerPoint template. 从论文 PDF / LaTeX 生成可编辑答辩 PPTX，并保留指定 PPT 模板风格。

Typescript wrapper for the PDFium library, works in browser and node.js

A Document Viewer cordova/phonegap plugin for iOS, Android and Windows

Monopoly is a Python library & CLI that converts bank statement PDFs to CSV.

Pure Rust PDF library for AI/RAG: structure-aware chunking, no ML, no C deps.

This module permits to convert HTML to the PDFMake format

This code accompanies the the paper Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture (https://arxiv.org/pdf/2112.08534.pdf).

A web service for converting markdown to PDF

A tool to sign PDF files. With Linux support.

PHP library to read and extract text & images from PDFs - Fast & Low memory - Built from scratch

Generate PDF for document website 🧑‍🔧

A (companion) plugin to facilitate the extraction of text from images (OCR) and PDFs.

A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.