Skill UI

This skill is designed for performing local, on-premise evaluations and benchmarking of models hosted on the Hugging Face Hub. It facilitates running specialized evaluation frameworks like `inspect-ai` and `lighteval` against local hardware. Users can select optimal inference backends, including `vllm` for high throughput, or fall back to Hugging Face Transformers or `accelerate`, ensuring comprehensive smoke testing and task selection for LLMs. It focuses purely on the local execution process, separate from remote jobs or publishing workflows.

Run Hugging Face models directly in JavaScript/TypeScript for text, vision, and speech tasks without backend servers, using Transformers.js in Node.js or modern browsers with WebGPU, quantization, and pipeline abstractions for efficient inference.

This resource is designed to document and guide the implementation of various architectural patterns and best practices when developing backend applications using the NestJS framework. It helps developers structure their code for maximum scalability and maintainability.

This comprehensive guide details how to correctly implement Firebase App Check for Flutter applications. It covers selecting platform-specific attestation providers (like Android Play Integrity and Apple DeviceCheck), configuring debug tokens, handling token refresh, and setting up enforcement mechanisms. Use this skill to significantly harden your app's security against abuse, ensuring only legitimate clients can access protected backend resources.

This skill provides a comprehensive guide to implementing high-performance, type-safe, in-memory caching in Go. It covers advanced features including nine eviction algorithms (e.g., W-TinyLFU, LRU), Time-To-Live (TTL), read-through loaders, and robust capacity sizing techniques. It is ideal for backend services requiring reliable, low-latency data access and efficient resource management.

A comprehensive set of composable handlers for building robust structured logging pipelines in Go (Go 1.21+). This library allows developers to control the entire log flow: implementing sampling for throughput control, formatting for data masking (PII), and sophisticated routing (Fanout, Router, Pipe) to multiple backend sinks like Sentry, Loki, Datadog, and others. Ideal for architecting enterprise-grade logging systems.

This skill guides the generation of a complete, production-ready Model Context Protocol (MCP) server using C# and .NET. It covers advanced architectural patterns, including Host builder setup, proper dependency injection, structured logging, and implementing robust functional tools. Ideal for developers building sophisticated AI agents or backend services that require standardized communication and tool invocation capabilities.

This utility automates the creation of a complete, production-ready Model Context Protocol (MCP) server project using Java. It generates full source code templates, including configuration, tool handling, resource definitions, and prompt logic. The generator provides robust setup for both Maven and Gradle, ensuring the resulting backend service is structured, scalable, and ready for deployment with support for reactive streams and optional Spring Boot integration.

This generator provides a comprehensive, production-ready template for building a Model Context Protocol (MCP) server using Kotlin. It sets up the full Gradle structure, integrates essential dependencies (MCP SDK, Ktor, Coroutines), and includes robust placeholders for custom tools, error handling, and testing, accelerating the development of context-aware backend services.

This tool generates a complete, production-ready project scaffold for a Model Context Protocol (MCP) server written in Ruby. It includes the necessary file structure, gem dependencies, Rake tasks, and boilerplate code for defining tools, prompts, and resources, accelerating backend development for AI applications.

This tool generates a complete, production-ready PHP Model Context Protocol (MCP) server project. It automatically scaffolds the entire structure, including tools, resources, prompts, and comprehensive tests, utilizing the official PHP SDK. It provides a standardized, robust starting point for developers building AI-integrated backend services in PHP.

Guides Python authors from commit to release with end-to-end steps for structuring src layouts, choosing setuptools/hatchling/flit/poetry backends, enforcing SOLID+type-hinting patterns, orchestrating lint/test/CI, managing PEP 440 semantics, and publishing trusted releases to PyPI.