AI Agent Skills

Android Automation Tool Based on Vision-Language Models

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Vision utilities for web interaction agents 👀

AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design toke…

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching.…

A full attention mechanism and transformer in pure go.

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

computer vision and sports

An iOS OCR Server Using Apple’s Vision Framework

[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

An annotated implementation of the Transformer paper.

Generate draw.io diagrams from natural language — 6 presets, vision self-check + up to 5-round refinement, codebase-to-diagram, 10,000+ official shapes & 321 AI/LLM bran…

OCR & Document Extraction using vision models

Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI