AI Agent Skills

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

Speaker is a Codex skill project for academic presentations: read real.pptx, combine text extraction, PPTX structure parsing, page-by-page rendering, OCR, and visual rev…

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…