Browsing:

affaan-m

Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.

llama-farm

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

huggingface

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

vllm-project

Community maintained hardware plugin for vLLM on Ascend

aicodingstack

AI Coding Stack - Your AI Coding Ecosystem Hub.

attasec

CLI tool for Continuous Threat Modeling

nv-action

vllm-ascend-model-adapter is a skill that enables adaptation of Hugging Face or local models to run on vllm-ascend, supporting both existing and new model architectures.

SyedaNabila559

A full-stack web app using Next.js and Tailwind CSS for the frontend, Python backend, and Neon PostgreSQL for the database. It also features an AI chatbot for real-time user interaction, ensuring scalability and high performance.

JimScope

sqlmodel-expert is an advanced SQLModel skill that provides comprehensive patterns and migrations for production databases using Python and Alembic.

William-XiaodongAn

cardiac-model-generate is a skill that generates Html simulation files from cardiac models based on provided names and parameters.

jehna

vibe-model is a skill for creating and modifying parametric 3D models using OpenSCAD, compiling to STL via openscad-wasm for VibeCad Studio

JimScope

SaaS for sending SMS