AI Agent Skills

(Java)A Method to Extract Tabular Content from PDF Files

Web Scraper used to create Kaggle European Soccer database

Creates an XML-Sitemap by crawling a given site.

CRNN with attention to do OCR,add Chinese recognition

web spider built by puppeteer, support task-queue and task-scheduling by decorators，support nedb / mongodb, support data visualization; 基于puppeteer的web爬虫框架，提供灵活的任务队列管理调度…

Benchmarking PDF libraries

🏭 PDF text extraction pipeline: self-hosted, local-first, Docker-based

Tools for automatically downloading/scraping personal financial data.

Python CLI tool and library for diffing CSV and JSON files

The official repo for “DocScanner: Robust Document Image Rectification with Progressive Learning”, IJCV, 2025.

Adds text to PDF files using the cuneiform OCR software

Online Invoice Management in Ruby On Rails.

Create unlimited invoices for free.

This is a wencai crawler.（i问财的策略回测接口的Pythonic工具包）

JARVIS - A ASSISTANT WHICH IS NEEDED FOR EVERYONE

OSINT tool to scrape names and usernames from large friend lists on Facebook, without being rate limited.