Skill UI

This skill covers the end-to-end development of cross-browser extensions (Chrome, Firefox). Expertise includes mastering Manifest V3, structuring complex architecture (service workers, content scripts), managing local/sync storage, building user interfaces, and implementing monetization models. Ideal for building robust, production-ready tools and navigating store publishing policies.

This guide provides minimal working examples for Deepgram speech-to-text transcription. It demonstrates how to transcribe audio from a URL or a local file using both TypeScript and Python. Users can learn basic API patterns, implement advanced features like diarization (speaker identification), and compare various model options (e.g., nova-3, nova-2). Ideal for initial integration and testing.

A comprehensive guide for selecting and optimizing embedding models for advanced vector search and retrieval-augmented generation (RAG) applications. This guide covers model comparison, chunking strategies, dimension reduction techniques, and provides runnable Python templates for both OpenAI and local Sentence Transformer implementations.

A comprehensive guide to setting up a fast, reproducible local development workflow for Groq applications. This setup includes structured project scaffolding, implementing singleton clients, defining model constants, and providing isolated unit tests with mocking, alongside live integration tests. Ideal for developers building low-latency LLM applications and ensuring rapid iteration cycles.

The official Hugging Face Hub CLI (`hf`) is a comprehensive command-line tool for managing all types of resources on the Hugging Face Hub. Use it to download, upload, synchronize, and manage models, datasets, Spaces, and cloud buckets. It facilitates secure authentication, local cache management, and complex data operations, making it essential for ML workflows.

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

A comprehensive skill designed to manage, track, and persist image assets generated by Ideogram's API. This tool addresses the critical issue of expiring image URLs by implementing a complete lifecycle pipeline. It handles metadata tracking (prompt, seed, model, style, etc.), immediate downloading, and robust storage to both local filesystems and cloud solutions like S3. Features include asset persistence, generation history logging, and image reproduction using stored seed values.

Guides researchers through nnsight’s tracing and activation APIs so you can inspect or modify PyTorch internals locally or via NDIF-powered remote runs on 70B+ foundation models without local GPUs.

This skill automates the setup and configuration of Ollama, allowing users to deploy Large Language Models (LLMs) locally. It performs system assessment (OS, GPU, RAM), selects optimal models based on hardware availability, and handles installation across macOS, Linux, and Docker. Use this when you require free, self-hosted AI alternatives, need offline inference capabilities, or wish to eliminate reliance on costly hosted API services.

PyTorch Lightning is a high-level framework built on PyTorch that significantly reduces boilerplate code in deep learning training loops. It automatically handles device management, distributed training (DDP, FSDP, DeepSpeed), mixed precision, and advanced callbacks. It allows researchers to scale models from local machines to supercomputers with minimal code changes, enabling clean, scalable, and best-practice deep learning implementations.

Vexor is a powerful command-line interface designed for advanced semantic search across local files. By utilizing vector embeddings and integrating with large language models (like Claude/Codex), it allows users to search files based on meaning and context, rather than just exact keywords. This is ideal for large codebases or document repositories where traditional keyword search methods are insufficient.

Combines ESM3 and ESM C protein language models to generate sequences, predict structures, condition functions, and extract embeddings via local or Forge API inference for protein design and engineering workflows.