Use this skill for game storytelling: "story structure", "narrative", "quest design", "dialogue writing", "branching narrative", "environmental storytelling", "narrative pacing". **Load references when:** - Story structure templates → `references/story-structures.md` - Quest types and chains → `references/quest-patterns.md` - Dialogue techniques → `references/dialogue-guide.md` For ZX dialogue IMPLEMENTATION (text boxes, typewriter, choices): use zx-game-design:gameplay-mechanics instead.
/plugin marketplace add nethercore-systems/nethercore-ai-plugins/plugin install game-design@nethercore-ai-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/dialogue-guide.mdreferences/quest-patterns.mdreferences/story-structures.mdFrameworks for integrating story into gameplay. The best game stories feel like the player created them through their choices.
In games, the player IS the main character. Narrative design must:
Games adapt traditional structure for interactivity:
| Act | Traditional | Game Adaptation |
|---|---|---|
| 1 | Setup | Tutorial + World intro + Goal |
| 2 | Confrontation | Core loop + Escalating challenges |
| 3 | Resolution | Climax + Denouement + Reflection |
Act 2 is 60-70% of gameplay — most content lives here.
| Pattern | Structure | Best For |
|---|---|---|
| Hub & Spoke | Central hub, branching content | Open-world, RPGs |
| Episodic | Self-contained segments | Session-based play |
| Emergent | Systems create story | Roguelikes, sims |
See references/story-structures.md for Hero's Journey adaptation and beat mapping.
Every quest needs: Objective, Motivation, Challenge, Reward, Closure.
| Type | Best For |
|---|---|
| Kill/Defeat | Combat focus, clear objective |
| Fetch | Exploration, resource gathering |
| Escort | Tension, relationship building |
| Investigate | Narrative focus, mystery |
| Defend | Time pressure, tension |
| Survive | Horror, resource management |
Linear: A → B → C
Branching: A → B1 → C1 (ending 1)
↘ B2 → C2 (ending 2)
Convergent: A → B1 ↘ D (same destination)
A → B2 ↗
See references/quest-patterns.md for templates and examples.
| Purpose | Example |
|---|---|
| Information | "The key is in the tower" |
| Character | "I never trusted wizards" |
| Emotion | "Please... find my daughter" |
| Choice setup | "Help village or seek treasure?" |
| World building | "Before the war, this was a garden" |
See references/dialogue-guide.md for branching dialogue patterns.
| Level | Description | Cost |
|---|---|---|
| Flavor | Different dialogue, same outcome | Low |
| Tactical | Different paths to same goal | Medium |
| Strategic | Different goals, different endings | High |
| Systemic | Emergent from interacting systems | Very High |
Many branches early → Converge at key points → Branch again for endings.
Track player choices for: NPC reactions, content locks, endings, affinity scores.
| Method | Immersion |
|---|---|
| Environmental storytelling | High |
| Gameplay integration | High |
| NPC dialogue (on request) | Medium |
| Found documents | Medium |
| Cutscenes | Low-Medium |
| Text dumps | Low |
Tell story through the world:
For satisfying endings:
character-design — Characters in your narrativeworld-building — Setting for your storyplayer-psychology — Engagement with narrativeThis 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.