This skill should be used when the user asks about "tech direction", "architecture", "code patterns", "technical vision", "code quality", "module structure", "file organization", "code splitting", "architecture decisions", "technical debt", "performance patterns", or discusses establishing or reviewing technical direction. Provides architecture framework for code coherence.
/plugin marketplace add nethercore-systems/nethercore-ai-plugins/plugin install creative-direction@nethercore-ai-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/architecture-docs.mdreferences/file-splitting.mdreferences/module-patterns.mdEstablish and maintain technical coherence through architecture decisions and quality standards.
Document significant decisions in .studio/architecture/:
.studio/architecture/
├── decisions.md # Index
├── 001-ecs-over-oop.md
└── 002-rollback-state.md
Each ADR: Context → Decision → Consequences
src/
├── core/ # Engine-level (input, render, audio)
├── game/ # Game-specific (player, enemy, world)
├── ui/ # User interface
└── shared/ # Cross-cutting (math, constants)
| Type | Soft | Hard | Action at Hard |
|---|---|---|---|
| Source code | 300 | 500 | Split into modules |
| Documentation | 500 | 1000 | Split into sections |
| Generated | 100 | 200 | External file + loader |
When approaching limits: identify subsections → extract → create interfaces → document split.
| Item | Convention |
|---|---|
| Types | PascalCase |
| Functions | snake_case |
| Constants | SCREAMING_SNAKE |
| Modules | snake_case |
Public API: Brief description, examples for non-obvious. Private: Explain "why" not "what". Errors: Result for recoverable, panic for programming errors.
Rollback: All game state deterministic, serializable, separable.
Memory:
FFI: Minimize and batch calls.
Store in .studio/architecture/ and .studio/creative-direction.md.
references/module-patterns.md - Organization patternsreferences/file-splitting.md - When/how to splitreferences/architecture-docs.md - Documentation templatesThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.