PaddleX
PaddlePaddle
All-in-One Development Tool based on PaddlePaddle
Document ProcessingSkill source unconfirmed
6.2KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “layout-detection”
1–14 / 14
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 14
MinerU
opendatalab
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Document ProcessingSkill source unconfirmed
67.9KGitHub
Dolphin
bytedance
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Document ProcessingSkill source unconfirmed
9KGitHub
Doctr
mindee
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
Document ProcessingSkill source unconfirmed
6.1KGitHub
3.2KGitHub
VLOOK
MadMaxChow
VLOOK™ 是优雅好用的 Typora/Markdown 主题包和排版增强插件。 VLOOK™ is an elegant and practical THEME PACKAGE × TYPESETTING PLUS for Typora/Markdown
Document ProcessingSkill source unconfirmed
2.6KGitHub
PdfPig
UglyToad
Read and extract text and other content from PDFs in C# (port of PDFBox)
Document ProcessingSkill source unconfirmed
2.5KGitHub
2KGitHub
OnnxOCR
jingsongliujing
基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, wi…
Document ProcessingSkill source unconfirmed
1.8KGitHub
React Native Executorch
software-mansion
Declarative way to run AI models in React Native on device, powered by ExecuTorch.
Document ProcessingSkill source unconfirmed
1.6KGitHub
Yomitoku
kotaro-kinoshita
YomiTokuはAIを活用した日本語文書解析エンジンを提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
Document ProcessingSkill source unconfirmed
1.5KGitHub
MLKit
jenly1314
🌝 MLKit是一个强大易用的工具包。通过ML Kit您可以很轻松的实现文字识别、条码识别、图像标记、人脸检测、对象检测等功能。
Document ProcessingSkill source unconfirmed
1.2KGitHub
Chandra
datalab-to
OCR model that handles complex tables, forms, handwriting with full layout.
Document ProcessingSkill source unconfirmed
11.2KGitHub
Sile
sile-typesetter
The SILE Typesetter — Simon’s Improved Layout Engine
Document ProcessingSkill source unconfirmed
1.8KGitHub