Skill UI

This guide provides comprehensive documentation and code examples for integrating OpenEvidence webhooks. Learn how to subscribe to real-time events (e.g., query completion, evidence updates, new citations) to keep clinical decision support systems fresh. Use these webhooks to trigger downstream audit workflows and ensure immediate data synchronization.

Flash Attention optimizer delivers 2-4x speedup and 10-20x memory savings for transformer attention, ideal when training or running long-context models that hit GPU memory or latency limits; supports PyTorch native scaled_dot_product_attention, the flash-attn library, H100 FP8 precision, and sliding-window attention.

This guide provides comprehensive principles for modern game development, covering engine selection (Unity, Unreal, Godot), platform integration (Steam features, console compliance), input abstraction, and performance optimization techniques. It helps developers make informed decisions when building cross-platform games for PC and console environments.

Provides Playwright-powered browser automation that detects dev servers, writes tests to /tmp, launches a visible Chromium, and exercises login flows, responsive layouts, form submissions, link checks, or any browser task to validate web functionality.

Guides SaaS teams through value-based pricing, tier design, research techniques (Van Westendorp, MaxDiff) and pricing-page best practices to capture customer willingness to pay and support monetization decisions.

Showcases modern Python practices, covering strict 3.12 type hints, dataclasses vs Pydantic decisions, asyncio/httpx patterns, src-layout projects, pyproject tool configs, virtual env workflows, and pytest guidance for reliable codebases.

A concise collection of idiomatic Python best practices—from readability and explicit configuration to type hints, error handling, and context managers—aimed at building robust, maintainable applications.

Guides adding PyTorch FSDP2’s fully_shard integration to training loops, covering correct distributed init, bottom-up sharding, mixed precision/offload policies, DTensor-aware optimizers, and distributed checkpointing so oversized models or DeviceMesh sharding goals work reliably.

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.

A practical decision framework for determining whether to use regular expressions or Large Language Models (LLMs) when parsing structured text (e.g., forms, quizzes, invoices). It recommends starting with deterministic, low-cost regex for 95-98% of structured data, and only invoking expensive LLM calls for identifying and validating ambiguous edge cases, optimizing both cost and accuracy.

This guide provides comprehensive best practices for creating high-quality videos using Remotion within a React environment. It covers advanced techniques for dynamic content generation, including integrating 3D models (Three.js), managing diverse assets like audio, video, and fonts, implementing complex animations, data visualization, and generating precise captions. Use this skill when developing professional, robust video generation workflows in React.

Ruzzy is a coverage-guided Ruby fuzzer leveraging libFuzzer to exercise both pure Ruby code and native C extensions; follow the provided installer, harness patterns, and sanitizer-aware runs to validate Ruby apps or gems for memory safety issues.