Loading...
Loading...
Found 86 Skills
Hexagonal grid mathematics, coordinate systems, pathfinding, and spatial algorithms for hex-based games. Use when implementing hex grids, calculating hex distances, finding neighbors, pathfinding on hex maps, spreading effects across hexes, or converting between coordinate systems. Triggers on requests involving hexagonal grids, hex coordinates, A* on hex maps, or hex-based game mechanics.
Guidance for implementing Adaptive Rejection Sampling (ARS) algorithms. This skill should be used when implementing rejection sampling methods, log-concave distribution samplers, or statistical sampling algorithms that require envelope construction and adaptive updates. It provides procedural approaches, performance considerations, and verification strategies specific to ARS implementations.
Implements API rate limiting using token bucket, sliding window, and Redis-based algorithms to protect against abuse. Use when securing public APIs, implementing tiered access, or preventing denial-of-service attacks.
Implements the Strategy pattern in Python backends. Run when the user mentions strategy pattern, or when you see or need a switch on type/method, multiple behaviors under the same contract, or interchangeable algorithms—apply this skill proactively without the user naming it.
Implement quiz game logic including game creation, player turn management, score calculation, answer validation, and game completion. Use when building game flows, turn-based mechanics, and scoring algorithms.
Development guide for @rytass/storages base package (儲存基底套件開發指南). Use when creating new storage adapters (新增儲存 adapter), understanding base interfaces, or extending storage functionality. Covers StorageInterface, Storage class, file converters (檔案轉換器), hash algorithms (雜湊演算法), and implementation patterns.
Design algorithms with LaTeX pseudocode and UML diagrams. Generate algorithmic environments, Mermaid class/sequence diagrams, and ensure consistency between pseudocode and implementation. Use when formalizing methods for a paper.
Use when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating the Phase 9 review loop. Provides review pass definitions (code quality, security, performance, test coverage), signal detection patterns, and iteration algorithms.
C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: - Implementing RL algorithms in C++ for performance-critical applications - Building production RL systems with libtorch - Creating replay buffers and experience storage - Optimizing RL training with GPU acceleration - Deploying RL models with ONNX Runtime
Byzantine consensus voting for multi-agent decision making. Implements voting protocols, conflict resolution, and agreement algorithms for reaching consensus among multiple agents.
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
Business logic implementation. Apply when implementing core business rules, validation logic, workflows, state machines, and domain-specific algorithms for new features.