Loading...
Loading...
Found 8 Skills
Decouple methods that execute tasks by sending commands to a commander object.
Use this skill when implementing game programming patterns - state machines for character/AI behavior, object pooling for performance-critical spawning, event systems for decoupled game communication, or the command pattern for input handling, undo/redo, and replays. Triggers on game architecture, game loop design, entity management, finite state machines, object pools, observer/event bus, command queues, and gameplay programming patterns.
SvelteKit remote functions guidance. Use for command(), query(), form() patterns in .remote.ts files.
Expert blueprint for puzzle games including undo systems (Command pattern for state reversal), grid-based logic (Sokoban-style mechanics), non-verbal tutorials (teach through level design), win condition checking, state management, and visual feedback (instant confirmation of valid moves). Use for logic puzzles, physics puzzles, or match-3 games. Trigger keywords: puzzle_game, undo_system, command_pattern, grid_logic, non_verbal_tutorial, state_management.
Production patterns for managing complex application state in React without Redux, Zustand, or other state libraries. Includes multi-stage loading, command patterns, refs for performance, and parallel data fetching. Use when building complex UIs with interconnected states, need loading stages and progress tracking, or implementing command patterns.
Expert blueprint for digital card games (CCG/Deckbuilders) including card data structures (Resource-based), deck management (draw/discard/reshuffle), turn logic, hand layout (arcing), drag-and-drop UI, effect resolution (Command pattern), and visual polish (godot-tweening, shaders). Use for CCG, deckbuilders, or tactical card games. Trigger keywords: card_game, deck_manager, card_data, hand_layout, drag_drop_cards, effect_resolution, command_pattern, draw_pile, discard_pile.
AI SDLC approvals, sandbox, and command rule workflow. Use when an AI assistant needs to decide whether to request escalated permissions, explain sandbox failures, propose prefix_rule approvals, avoid unsafe command patterns, or document why a command was or was not rerun outside the sandbox. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution.
Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration