This skill should be used when the user asks about "art direction", "visual style", "color palette", "aesthetic", "visual coherence", "art style guide", "visual identity", "character design style", "environment style", "UI style", or discusses establishing or reviewing visual direction. Provides art direction framework for visual 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/color-theory.mdreferences/composition.mdreferences/style-spectrums.mdEstablish and maintain visual coherence through systematic art direction.
Three levels every scene communicates through:
| Spectrum | Left ←→ Right |
|---|---|
| Fidelity | Stylized ←→ Realistic |
| Detail | Simplified ←→ Complex |
| Saturation | Desaturated ←→ Vibrant |
| Contrast | Low-key ←→ High-key |
| Form | Geometric ←→ Organic |
| Line | Hard-edge ←→ Painterly |
Document position for each. All assets should align.
Primary Palette (60/30/10 rule):
Functional Colors:
Emotional Mapping:
Normal maps add surface detail. Use consistently with visual style:
| Style | Normal Map Intensity | Recommendation |
|---|---|---|
| Stylized/Toon | 0.3-0.5 | Subtle or skip |
| PS1/N64 Retro | 0.5-0.8 | Subtle detail |
| PS2/Dreamcast | 0.8-1.2 | Standard detail |
| Realistic | 1.0-2.0 | Full detail |
When to use normal maps:
When to skip normal maps:
Material-specific intensity:
| Material | Intensity Range |
|---|---|
| Smooth plastic | 0.2-0.4 |
| Fabric/cloth | 0.5-0.8 |
| Stone/concrete | 0.8-1.2 |
| Metal (brushed) | 1.0-1.5 |
| Organic (bark, skin) | 0.6-1.0 |
Store in .studio/art-direction.md or .studio/creative-direction.md.
references/color-theory.md - Advanced palette buildingreferences/composition.md - Visual hierarchy principlesreferences/style-spectrums.md - Detailed spectrum definitionsThis 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.