Design Game Encounters

From the author

Design, implement, tune, or test Three.js action-game encounters. Use for arena layout, enemy composition, spawn pacing, objectives, boss phases, reward cadence, encounter fixtures, and difficulty validation.

— the description by Meng To

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a systematic approach to encounter design for Three.js action games, focusing on player decision-making rather than simple enemy counts. It covers the entire lifecycle of an encounter, from initial composition and spatial layout to tuning difficulty and validating player experience across different devices.

What it does

Defines core encounter elements including objectives, enemy roles, and spawn pacing.
Provides guidelines for arena layout and environmental hazards.
Establishes rules for fair gameplay, such as managing camera sight lines and telegraphing attacks.
Offers a framework for testing and tuning encounters based on player decision-making.
Supports the implementation of boss phases and reward structures.

When to use it

When designing new combat encounters or boss battles in a Three.js project.
When balancing the difficulty of existing game levels.
When troubleshooting player frustration caused by unfair mechanics or poor visibility.
When setting up spawn systems and wave pacing for action sequences.

Advantages

Promotes intentional design focused on player agency and meaningful choices.
Ensures encounters remain fair by prioritizing readability and telegraphing.
Provides a structured method for iterative tuning based on observed gameplay.
Helps maintain consistency across different device form factors.

Usage examples

“Design a boss encounter for my Three.js arena with three distinct phases.”: The agent will outline a phase-based encounter structure, defining enemy behaviors, spawn timing, and environmental hazards for each stage.
“How can I balance the difficulty of my current wave-based encounter?”: The agent will suggest adjustments to enemy composition, spawn pacing, and player resource availability based on the provided design principles.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/mengto/design-game-encounters/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip design-game-encounters.zip -d .agents/skills

Documentation by Meng To

Design encounters as decisions, not actor counts.

Compose

Define objective, available space, enemy roles, spawn timing, hazards, player resources, exits, failure recovery, and reward. Add one pressure source at a time; require each archetype to create a distinct response.

Keep it fair

Protect readable paths, telegraphs, camera sight lines, and recovery windows. Cap simultaneous committed attackers and avoid offscreen damage, unavoidable chains, or encounter resets that duplicate rewards.

Validate

Create deterministic starts for low resources, each wave, boss phase, victory, and death/retry. Test desktop and mobile at the real camera distance, then adjust composition from observed decisions rather than raw completion time.

Files

ATTRIBUTION.mdAdded by AutoGineer872 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md1.0 KiB
agents/openai.yaml203 B

agents/openai.yaml

interface:
  display_name: "Design Game Encounters"
  short_description: "Design balanced Three.js combat encounters"
  default_prompt: "Use $design-game-encounters to create a balanced game encounter."

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Web 3d Asset Pipeline
OpenAIOfficial
Prepare and optimize browser-game 3D assets. Use when the user asks for GLB or glTF shipping work, including Blender cleanup and export, collision or LOD setup, compression, texture packaging, and runtime validation.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
Link-onlyGitHub stars of the source repository7.8k
3d Sky Background
Meng To· Community
Guidelines for creating camera-correct, coherent sky backgrounds and environment lighting for 3D scenes.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository7.3k
Design Action Combat
Meng To· Community
A framework for designing and testing readable, state-driven tactical combat systems for web-based games.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository7.3k
Author Game Levels
Meng To· Community
A structured workflow for designing and validating flat-plane Three.js game levels with a focus on readability and deterministic data.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository7.3k
Build Hybrid Game Assets
Meng To· Community
A structured workflow for planning, creating, and integrating hybrid 3D and 2D assets into Three.js web games.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository7.3k
Tune Enemy AI
Meng To· Community
A framework for designing, balancing, and testing legible, fair, and deterministic combat AI for action games.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository7.3k