From dm-game
Engagement loop design, pacing frameworks, the experience triangle, emotion layering, and meaningful choice evaluation. Use when designing core loops, evaluating why gameplay feels flat, structuring emotional arcs, or answering 'why isn't this fun?'
npx claudepluginhub rbergman/dark-matter-marketplace --plugin dm-gameThis skill uses the workspace's default tool permissions.
**Purpose:** Tools for designing, diagnosing, and improving the player *experience* — not the feature set. Games are systems that generate experiences; this skill helps you build better generators.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Guides MCP server integration in Claude Code plugins via .mcp.json or plugin.json configs for stdio, SSE, HTTP types, enabling external services as tools.
Purpose: Tools for designing, diagnosing, and improving the player experience — not the feature set. Games are systems that generate experiences; this skill helps you build better generators.
Influences: Frameworks here draw on experience engineering theory, cognitive engagement research, and systematic game balance methodology.
Use this skill when:
Every moment of gameplay is the product of three forces:
Mechanics
(what players do)
/ \
/ \
/ \
Fiction ——— Feedback
(what it means) (what players perceive)
Diagnostic: When something feels wrong, identify which vertex is weak:
| Symptom | Weak Vertex | Fix Direction |
|---|---|---|
| "I don't know what to do" | Mechanics (unclear rules) | Simplify options, add tutorials |
| "I don't care" | Fiction (no meaning) | Connect to stakes, add narrative weight |
| "Did that work?" | Feedback (no response) | Add visual/audio/haptic confirmation |
| "It's boring" | Mechanics + Fiction gap | Close the gap — make actions feel consequential |
| "It's confusing" | All three misaligned | Strip back and realign around one clear experience |
Every game runs on loops. The tightest one is the core engagement loop:
Action → Feedback → Evaluation → Decision → Action ...
Core loop: move → shoot → evaluate → reposition (seconds)
Session loop: mission → rewards → loadout → next mission (minutes)
Meta loop: campaign → unlock → new content → campaign (hours/days)
Each loop should be satisfying on its own while feeding into the next.
The best moments layer multiple emotions simultaneously. Design for this:
Anti-pattern: Designing for "fun." Fun is an umbrella over dozens of specific emotions that require different design approaches.
For any mechanic or feature, evaluate:
Elegance = Emotional Payoff / (Player Attention Cost + Development Cost)
| Factor | Question |
|---|---|
| Emotional payoff | What does the player feel? How intensely? How often? |
| Attention cost | How much must the player learn, remember, and track? |
| Development cost | How much effort to build, tune, and maintain? |
Decision rule: If a feature scores low on elegance, either simplify it or cut it. Complexity is a budget — spend it on what matters.
A choice is meaningful when:
| Question | If "No" |
|---|---|
| Can the player understand what each option does? | Clarity problem — simplify or explain |
| Do the options lead to genuinely different outcomes? | False choice — collapse or differentiate |
| Does the outcome affect something the player cares about? | Stakes problem — raise consequences |
| Is there a dominant option? | Balance problem — see game-balance |
| Is the outcome fully predictable? | Determinism problem — add uncertainty or hidden information |
Pacing is cognitive load management across time.
Intensity
| /\ /\ /\
| / \ /\ / \/ \
| / \/ \/ \___
| /
| /
+---------------------------→ Time
Intro Rising Climax Rest
Principles:
When a mechanic works correctly but doesn't engage, run through in order:
If all seven check out and it still isn't fun: The mechanic may simply not be interesting. Consider cutting it and redirecting the complexity budget elsewhere.
Three approaches to narrative, each with different design implications:
| Mode | Control | Replayability | Design Challenge |
|---|---|---|---|
| Scripted | High (author-controlled) | Low | Don't let narrative contradict mechanics |
| Environmental | Medium (player-discovered) | Medium | Reward exploration without requiring it |
| Emergent | Low (system-generated) | High | Build systems that produce story-worthy events |
The dissonance test: If the story says one thing and the mechanics reward another, players will follow the mechanics and resent the story. Align them or cut the conflict.