Development

Create Dojo models for storing game state with proper key definitions, trait derivations, and ECS patterns. Use when defining game entities, components, or state structures.

Manage world migrations, handle breaking changes, and upgrade Dojo versions. Use when updating deployed worlds, migrating to new versions, or handling schema changes.

Initialize new Dojo projects with proper directory structure, configuration files, and dependencies. Use when starting a new Dojo game project or setting up the initial project structure.

Set up and configure Torii indexer for GraphQL queries, gRPC subscriptions, and SQL access. Use when indexing your deployed world for client queries or real-time updates.

Deploy Dojo worlds to local Katana, testnet, or mainnet. Configure Katana sequencer and manage deployments with sozo. Use when deploying your game or starting local development environment.

Configure Scarb.toml, dojo profiles, world settings, and dependencies. Use when setting up project configuration, managing dependencies, or configuring deployment environments.

Integrate Dojo with game clients for JavaScript, Unity, Unreal, Rust, and other platforms. Generate typed bindings and connection code. Use when connecting frontends or game engines to your Dojo world.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Verification loop evaluation framework. Provides graders, metrics, and pass@k evaluation for code quality assurance. Integrates with verification-loop for systematic quality gates.

Instinct-based learning system with confidence scoring. Automatically learns patterns from sessions and evolves them into skills. Supports import/export for team sharing.

Intelligent context window management with strategic compaction suggestions. Monitors context usage and suggests /compact at logical boundaries. Saves state before compaction to enable recovery.

Auto-extract reusable patterns from coding sessions. Activates on session end or when /learn command is invoked. Identifies successful patterns, debugging solutions, and architectural decisions worth preserving for future sessions.

服务理解与分析技能，用于快速理解和加载服务上下文，包括服务概览、业务逻辑、架构分析和运维协议。

外部知识库读取技能，用于加载项目文档、开发规范、公司要求等外部知识，在开发流程中按需调取。

经验沉淀与检索技能，在开发流程的关键节点自动检索相关经验，在任务完成后沉淀新经验。

RIPER 是 VibeCoding 的核心开发流程框架，将软件开发分解为五个有序阶段。

VibeCoding 支持多个 AI 引擎协作，通过 `.ai_state/` 文件系统实现状态共享和任务交接。

会话状态管理，保证工作流跨会话持久化

性能优化技能，识别和解决性能问题

指令生命周期管理，钩子函数，中断恢复，持续学习

Git工作流规范，分支策略和提交规范

错误学习系统，从Bug和错误中学习并记忆

问题诊断和调试技能

代码简化器，KISS原则执行者，Linus品味守护者