AI Agent Skills

📄 [Skill] Vision-in-the-loop LaTeX typesetting agent — auto-compile, render, diagnose, and fix paper layouts

Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the co…

Any source (PDF, video, web, audio, text) to interactive learning package with quizzes, flashcards and spaced repetition. One command, 12-section study guide.

How to refactor code efficiently and without pain.

A Python library to inspect and modify the internal structure of a PDF file

A CLI toolset to generate table of contents for PDF files automatically.

deepseek标配coding agent、原生支持模型路由、CodeGraph代码图谱、OCR截图识别、自动上下文压缩、最佳工作模式选择，workflow等功能，从根本上节省Token

Office document creation and editing skills for Claude Code - PPTX, DOCX, XLSX, and PDF workflows with automation support

Over 1000 flashcards to learn Rust, SQLite, Lua, C, Godot, or Wolfram Language from first principles. Written in markdown with script to convert them to Anki decks or PD…

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

Build academic conference posters as a single HTML/CSS file, rendered to print-ready PDF via headless Chromium. A coding-agent skill.

A full-stack AI helpdesk platform that uses machine learning, NLP, and OCR to automatically analyze support requests, detect similar incidents, and help teams resolve te…

Academic research skills suite for Claude Code — literature search (arXiv+PubMed+WoS), PDF extraction, figure cropping, review writing, Zotero sync, and PPT generation.

ComPDF SDK for Android — a full-featured PDF library offering comprehensive code samples and integration guides. Build robust PDF viewers and editors on Android with sup…

PDF generation with JSX. Page breaks that actually work.

Java PDF table extraction & OCR library. Extract structured tables from text-based and scanned PDFs using stream, lattice (OpenCV-style grid detection), and hybrid parsi…