Use this skill for gameplay loops: "core loop", "gameplay loop", "progression system", "game economy", "feedback loop", "reward system", "engagement loop", "pacing". **Load references when:** - Detailed loop worksheet → `references/loop-worksheet.md` - Progression curves/patterns → `references/progression-templates.md` - Economy/resource design → `references/economy-design.md`
/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/economy-design.mdreferences/loop-worksheet.mdreferences/progression-templates.mdFrameworks for designing gameplay cycles that keep players engaged. The core loop is your game's heartbeat — players don't remember features, they remember how it felt to play.
Every game loop has three phases:
[ACTION] → [FEEDBACK] → [REWARD] → repeat
The loop must be: Satisfying (feels good), Clear (know what to do), Variable (not monotonous), Progressive (mastery visible).
Games have nested loops at different time scales:
| Loop | Duration | Example |
|---|---|---|
| Micro | Seconds | Attack → Hit feedback → Damage |
| Core | Minutes | Clear room → XP → Level progress |
| Meta | Hours | Complete dungeon → New gear → Stronger |
| Session | Play session | Progress → Reason to return |
Loops connect: Micro rewards → Core loop → Meta loop → Reason to continue.
[Find challenge] → [Attempt] → [Succeed/Fail] → [Learn]
[Explore] → [Discover item] → [Add to collection] → [Unlock new areas]
[Encounter] → [Fight] → [Victory] → [Loot/XP] → [Get stronger]
[Gather resources] → [Craft/Build] → [Use creation] → [New opportunities]
| Type | Player Gains | Feels Like |
|---|---|---|
| Vertical | More power | Getting stronger |
| Horizontal | More options | Getting versatile |
| Skill | Player improves | Getting better |
| Content | Access to more | Unlocking secrets |
/ — Steady, predictable, can feel grindy╭─ — Fast start, good for onboarding─┐─┐ — Dramatic power spikes with plateaus[Sources] → Player inventory → [Sinks]
Enemies ↕ Purchases
Exploration Save/Load Consumables
Upgrades
Balance rule: Sinks must match or exceed sources, or economy inflates.
Control through: limited sources, time gating, location gating, skill gating.
Warning: Too much scarcity = frustration. Too little = meaninglessness.
Match feedback to action significance:
| Action | Feedback |
|---|---|
| Basic attack | Small sound/visual |
| Critical hit | Big sound, camera shake |
| Level up | Fanfare, UI celebration |
| Boss defeat | Extended celebration |
Checklist for each action:
Players enter flow when challenge matches skill:
Challenge
↑ FLOW ZONE (between too hard/too easy)
└────────────→ Skill
Prevent negative loops:
Structure sessions: [Hook] → [Rising action] → [Peak] → [Cool down] → [Cliffhanger]
Design natural break points: after objectives, in safe zones, after story beats, before major challenges.
Target session length: _____ minutes
game-balance — Balancing loop rewardsplayer-psychology — Understanding engagementreplayability-engineering — Loops for replayable gamesThis 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.