Agent skill

game-design

Game design principles. GDD structure, balancing, player psychology, progression.

Stars 23,776
Forks 2,298

Install this agent skill to your Project

npx add-skill https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/creative-design/game-development/game-design

SKILL.md

Game Design Principles

Design thinking for engaging games.


1. Core Loop Design

The 30-Second Test

Every game needs a fun 30-second loop:
1. ACTION → Player does something
2. FEEDBACK → Game responds
3. REWARD → Player feels good
4. REPEAT

Loop Examples

Genre Core Loop
Platformer Run → Jump → Land → Collect
Shooter Aim → Shoot → Kill → Loot
Puzzle Observe → Think → Solve → Advance
RPG Explore → Fight → Level → Gear

2. Game Design Document (GDD)

Essential Sections

Section Content
Pitch One-sentence description
Core Loop 30-second gameplay
Mechanics How systems work
Progression How player advances
Art Style Visual direction
Audio Sound direction

Principles

  • Keep it living (update regularly)
  • Visuals help communicate
  • Less is more (start small)

3. Player Psychology

Motivation Types

Type Driven By
Achiever Goals, completion
Explorer Discovery, secrets
Socializer Interaction, community
Killer Competition, dominance

Reward Schedules

Schedule Effect Use
Fixed Predictable Milestone rewards
Variable Addictive Loot drops
Ratio Effort-based Grind games

4. Difficulty Balancing

Flow State

Too Hard → Frustration → Quit
Too Easy → Boredom → Quit
Just Right → Flow → Engagement

Balancing Strategies

Strategy How
Dynamic Adjust to player skill
Selection Let player choose
Accessibility Options for all

5. Progression Design

Progression Types

Type Example
Skill Player gets better
Power Character gets stronger
Content New areas unlock
Story Narrative advances

Pacing Principles

  • Early wins (hook quickly)
  • Gradually increase challenge
  • Rest beats between intensity
  • Meaningful choices

6. Anti-Patterns

❌ Don't ✅ Do
Design in isolation Playtest constantly
Polish before fun Prototype first
Force one way to play Allow player expression
Punish excessively Reward progress

Remember: Fun is discovered through iteration, not designed on paper.

Expand your agent's capabilities with these related and highly-rated skills.

davila7/claude-code-templates

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

23,776 2,298
Explore
davila7/claude-code-templates

openrlhf-training

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

23,776 2,298
Explore
davila7/claude-code-templates

gguf-quantization

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

23,776 2,298
Explore
davila7/claude-code-templates

Claude Code Guide

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

23,776 2,298
Explore
davila7/claude-code-templates

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

23,776 2,298
Explore
davila7/claude-code-templates

behavioral-modes

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

23,776 2,298
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results