This skill should be used when the user asks about "world design", "game world", "lore", "world map", "factions", "cultures", "environmental storytelling", "world rules", "world consistency", "geography", "history", "time systems", "day night cycle", "world scope", or needs to design the setting and context for their game.
/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/consistency-checklist.mdreferences/world-scope-worksheet.mdFrameworks for creating coherent, memorable game worlds. Focus on what players experience and interact with, not encyclopedic lore documents.
Game worlds exist to be played in, not read about. Every world element should either:
Avoid lore that exists only in text dumps. Show the world through gameplay.
Before building, determine scope based on game length and team size:
| Scope | Description | Suitable For |
|---|---|---|
| Contained | Single location with depth (a mansion, a ship, a dungeon) | Short games, game jams, solo devs |
| Regional | Multiple connected areas with distinct identities | Medium games, small teams |
| Expansive | Multiple regions, complex relationships | Longer games, larger scope |
Recommendation for indie/solo devs: Start contained. A deeply realized small world beats a shallow large one.
One sentence describing your world's unique identity:
"A world where [unique element] means [consequence for inhabitants]"
What conflict defines this world?
How does the player relate to this world?
Design geography that creates gameplay:
| Geographic Feature | Gameplay Function |
|---|---|
| Elevation changes | Verticality, vantage points, shortcuts |
| Water bodies | Barriers, navigation puzzles, resources |
| Dense areas (forests, cities) | Cover, exploration, getting lost |
| Open areas | Combat arenas, exposure, speed |
| Chokepoints | Encounters, gates, narrative beats |
Players navigate by landmarks. Every area needs:
Map how areas connect:
[Starting Area]
|
[Hub/Crossroads] --- [Optional Area]
|
[Gate/Challenge]
|
[New Region] --- [Secret Area]
For each faction:
Identity
Relationships
Player Interaction
Create gameplay through faction relationships:
Keep it simple: 2-4 factions maximum for most games.
Players should sense depth without needing to access it all.
Preferred (show):
Use sparingly (tell):
Design history in layers visible in the world:
Static time: World state doesn't change without player action
Dynamic time: World changes independent of player
If implementing day/night:
| Time | Gameplay Implications |
|---|---|
| Dawn | Transition, new opportunities |
| Day | Normal activities, visibility |
| Dusk | Transition, preparation |
| Night | Different enemies, stealth opportunities, danger |
Tip: Only add day/night if it creates meaningful gameplay differences.
For longer games, consider:
Tell stories through carefully placed objects:
Buildings and structures communicate:
Layer environmental storytelling:
For every world rule, answer: "Can the player break this?"
Track what you've communicated to players:
Kitchen sink worlds: Too many elements without cohesion Lore dumps: Exposition that stops gameplay Arbitrary restrictions: Rules that exist only to limit player Ungrounded fantasy: Magic without cost or limit Empty scale: Large worlds with nothing in them
references/world-scope-worksheet.md — Detailed world scope planning templatereferences/consistency-checklist.md — Full internal consistency checklistlevel-design — Spatial design within your worldnarrative-design — Stories told within your worldcharacter-design — Inhabitants of your worldThis 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 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 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.