encounter-design
Spatial design, enemy behavior, encounter composition, and environmental flow. Use when designing combat encounters, enemy AI, level layouts, boss fights, environmental puzzles, placing enemies or items in space, designing world structure, or when encounters feel repetitive, unfair, or tactically flat. Covers the Encounter Triangle (space, adversaries, resources), combat space vocabulary, enemy archetypes, AI behavior patterns, encounter pacing, environmental guidance, world structure, and environmental storytelling.
What this skill does
# Encounter Design
**Purpose:** Tools for designing how players experience space and adversaries. An encounter is not a stat block dropped into a room — it is the intersection of spatial geometry, enemy behavior, and player resources that produces a tactical experience. This skill covers the full chain from world structure down to individual enemy placement.
**Core insight:** The same enemies in a different space feel completely different. The same space with different resources creates different strategies. Encounter design is combinatorial — small changes to any axis reshape the entire experience.
---
## When to Activate
Use this skill when:
- Designing combat encounters, arenas, or enemy placement
- Building enemy AI or defining enemy behavior patterns
- Planning level layouts, room flow, or world structure
- Designing boss fights or multi-phase encounters
- Creating environmental puzzles or hazard-based challenges
- Encounters feel repetitive, samey, or tactically flat
- Players report encounters feel unfair or unreadable
- Deciding how to guide players through space without explicit markers
- Designing the macro structure of a game world (linear, hub, open)
---
## Core Framework: The Encounter Triangle
Every encounter is shaped by three forces. The experience emerges from their intersection, not from any single axis.
```
Space
(WHERE it happens)
/ \
/ \
/ encounter \
/ experience \
/ \
Adversaries ———————— Resources
(WHO they face) (WHAT they have)
```
| Axis | What It Controls | Design Levers |
|------|-----------------|---------------|
| **Space** | Geometry, cover, elevation, sight lines, movement options | Room shape, verticality, choke points, flanking routes, hazards |
| **Adversaries** | Enemy types, behaviors, group composition, timing | Archetypes, AI complexity, wave structure, spawn placement |
| **Resources** | Health, ammo, abilities, environmental tools, information | Scarcity, placement, risk/reward of acquisition |
**The combination is the design.** Changing one axis changes the experience:
| Same Enemies, Different Space | Same Space, Different Resources |
|------------------------------|--------------------------------|
| Open arena → skill-based dodging | Full ammo → aggressive push |
| Tight corridor → claustrophobic pressure | Scarce ammo → cautious resource management |
| Elevated platforms → vertical tactics | New ability just unlocked → mastery testing |
| Multiple entrances → flanking anxiety | Environmental tools available → creative solutions |
**Diagnostic:** When an encounter feels wrong, identify which axis is underdesigned. Most "boring" encounters have interesting enemies in uninteresting space, or interesting space with no resource tension.
---
## Combat Space Composition
Space is not a container for combat — it is a participant. Every spatial element shapes player behavior.
### Space Elements
| Element | Behavior It Creates | Design Consideration |
|---------|--------------------|--------------------|
| **Cover** | Approach decisions, safety management | Must be destructible or flanakable to prevent camping |
| **Sight lines** | Long = ranged advantage; short = close-quarters tension | Mix lengths to reward weapon/ability switching |
| **Elevation** | High ground advantage, verticality adds decision layers | Ensure both high and low positions have trade-offs |
| **Choke points** | Force commitment, create risk/reward | Powerful but can feel unfair if enemies use them without counter |
| **Flanking routes** | Reward spatial awareness, punish tunnel vision | Must be readable — players need to know routes exist |
| **Environmental hazards** | Add urgency, create area denial | Should be readable before they activate; punish carelessness, not ignorance |
| **Interactables** | Creative problem-solving, environmental mastery | Explosive barrels, bridges, switches — reward observation |
### Space Vocabulary
Different room shapes produce fundamentally different encounters:
| Space Type | Geometry | Behavior It Encourages | Best For |
|-----------|----------|----------------------|----------|
| **Arena** | Open, symmetric, few obstacles | Skill-based movement, dodging, spacing | Boss fights, duels, skill tests |
| **Corridor** | Long and narrow, limited lateral movement | Funneled intensity, resource attrition | Building tension, gauntlets |
| **Hub** | Central area with multiple exits/entrances | Multi-directional awareness, choice of engagement | Exploration pivots, ambush setups |
| **Gauntlet** | Linear with sequential challenges | Sustained pressure, endurance testing | Climactic sequences, escape scenes |
| **Balcony** | Split-level with overlook positions | Ranged/melee asymmetry, vertical tactics | Mixed-range encounters |
| **Labyrinth** | Interconnected paths, limited visibility | Paranoia, ambush potential, navigation challenge | Horror, stealth, cat-and-mouse |
| **Killzone** | Inescapable area with escalating threat | Survival pressure, crowd management | Wave defense, holdout scenarios |
**Design rule:** Vary space types across a level. Three arenas in a row feel repetitive regardless of enemy variation. Alternate space vocabulary to keep encounters feeling fresh.
---
## Enemy Design as System
Enemies are behavior systems, not stat blocks. A slow enemy that blocks a doorway is more interesting than a fast enemy with more HP, because the first one changes what the player *does*.
### Enemy Archetypes
| Archetype | Role | Player Response It Forces |
|-----------|------|--------------------------|
| **Aggressor** | Closes distance, applies pressure | Reactive play, retreat decisions, priority targeting |
| **Defender** | Holds position, blocks progress | Approach planning, finding weak points, patience |
| **Supporter** | Buffs or heals other enemies | Target prioritization, "kill the healer" decisions |
| **Disruptor** | Breaks player patterns, denies abilities | Adaptation under pressure, fallback strategies |
| **Artillery** | Ranged area denial, long-range threat | Positioning awareness, closing distance under fire |
| **Swarm** | Overwhelms with individually-weak numbers | Crowd management, area-of-effect decisions |
| **Elite/Boss** | Multi-phase, tests multiple skills | Full mastery demonstration, pattern recognition |
### Composition Rules
Encounters become interesting through archetype *combinations*, not individual enemies:
- **Aggressor + Artillery** = the player is forced to close distance (artillery threat) while managing melee pressure (aggressor). Classic push-pull.
- **Defender + Supporter** = the player must find a way past the defender to reach the supporter, or the encounter becomes attrition.
- **Swarm + Disruptor** = the player's crowd-clearing tools get disrupted, forcing improvisation.
**Minimum viable encounter:** Two archetypes that create a tension the player must resolve. A single archetype is a puzzle with one answer; two archetypes create a dilemma.
### Enemy Readability
Players must identify enemy type and predict behavior from visual design alone.
- [ ] Silhouette is distinct from other enemy types at gameplay distance
- [ ] Color/material signals threat level or behavior type
- [ ] Animations telegraph attacks before they resolve
- [ ] Audio cues differentiate enemy types (especially off-screen)
- [ ] New enemy types are introduced in low-pressure situations before appearing in difficult encounters
**Design rule:** If the player dies to an enemy they couldn't read, that is a design failure, not a skill failure.
---
## Behavior Design Patterns
Enemy AI architecture determines what behaviors are possible. Choose the simplest architecture that supports the design intent.
| Architecture | Behavior Quality | Design Control | Best For |
|-------------|-----------------|----------------|----------|
| **State Machine** | Predictable, readable | HighRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.