Skill UI

This skill runs an automated evolution process designed to systematically optimize the seven core policy surfaces of an AI agent harness (e.g., planner, contextBuilder, reviewer). By mutating these policies and scoring the variants in a sandbox, it identifies crucial performance improvements without requiring expensive foundation model retraining. It is ideal for empirical configuration tuning and establishing optimized baselines.

This tool executes a GEPA learning cycle, automating the evolution and optimization of policy prompts against a scored task corpus. Instead of relying on manual prompt iteration, it measures performance improvements, identifying the best working 'harness genome.' It is ideal for measuring sustainable improvements in task performance and supports a free, cost-estimating dry-run mode before committing to actual model calls.

A comprehensive guide to best practices for data access and persistence in Spring Boot using JPA and Hibernate. Covers critical topics such as entity modeling, relationship management (preventing N+1), transaction handling, query optimization, indexing strategies, and connection pooling.

This tool provides a structured way to run predefined, periodic background workers (e.g., security audits, performance optimization, memory consolidation). It utilizes native scheduling mechanisms to automatically dispatch and re-schedule tasks within a session, ensuring continuous system maintenance and optimal performance monitoring.

This optimizer guides the acceleration of complex, multi-stage processes, such as CI/CD pipelines, large-scale refactoring, or data validation. It instructs users to decompose large tasks into independent execution lanes, build a dependency graph, batch read/check operations, and manage writes with strict isolation to maximize speed without sacrificing correctness. Ideal for optimizing development workflows and testing cycles.

A comprehensive guide covering advanced patterns, common pitfalls, and optimization techniques for using Prisma ORM in TypeScript backend applications. Learn best practices for schema design, handling transactions, optimizing queries (include vs select), and managing connection pools in production environments.

A comprehensive guide detailing advanced performance optimization patterns for React 18/19 and Next.js. Adapted from Vercel Engineering's best practices, this skill organizes 70+ critical rules across eight categories—including eliminating waterfalls, optimizing bundle size, improving server-side rendering, and managing client-side re-renders. Use this when developing, reviewing, or refactoring high-performance React applications.

This skill is designed for complex, iterative decision-making processes requiring deep computation, such as stochastic optimization, high-dimensional search, or repeated model rollouts. It mandates the creation of a structured 'Ledger' to rigorously record every trial, prior winner, fresh information, and decision mark. It ensures that conclusions are based on durable evidence, managing risk through explicit promotion gates and preventing premature certainty.

A comprehensive guide to building high-performance, scalable UIs using the latest SwiftUI best practices. Covers advanced state management with @Observable, type-safe navigation using NavigationStack, view composition techniques, and crucial performance optimization tips for iOS and macOS development.

This tool automates the process of optimizing investment portfolio allocations using a mean-variance engine. It integrates neural prediction models and risk constraints to determine optimal asset weights. Users can set specific risk targets, assess comprehensive risk metrics (variance, correlation), and generate actionable, step-by-step rebalancing plans for professional portfolio management.

This skill performs mean-variance portfolio optimization by solving the linear system Σ · x = μ using the Conjugate Gradient (CG) method. It is significantly faster (40-60x) and numerically robust compared to legacy methods like the Neumann series. It takes a covariance matrix (Σ) and expected return vector (μ) to determine optimal asset weights, providing full provenance tracking for auditability.

A comprehensive guide covering best practices for the Vite build tool. Learn how to configure advanced features such as environment variables, plugins, HMR, dependency pre-bundling, and optimizing the final production build for modern web applications.