Abstract Strategy

This is a comprehensive framework for designing abstract strategy games like Chess, Go, or Hex. It walks you through brainstorming techniques (like mechanism extraction from physics or chemistry), design principles (maximizing the depth-to-complexity ratio), and concrete evaluation criteria (first player should win 45-55%, rules fit on one page). The toolkit covers board topology, piece systems, victory conditions, and balance considerations like the pie rule. Use it when you're designing a board game from scratch or need to evaluate whether your prototype has genuine strategic depth or just accidental complexity. The testing protocol and anti-patterns section are especially practical for catching common failures like analysis paralysis or dominant strategies.

skills.sh installs: 404
GitHub stars: 182
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jwynia/agent-skills --skill abstract-strategy --agent claude-code

Installs into .claude/skills of the current project.

Files

Abstract Strategy Game Design

Purpose

Design abstract strategy games—games with perfect information, no randomness, and strategic depth. Provides frameworks for ideation, design, and evaluation.

Core Definition

Abstract strategy games require:

Perfect Information: All game state visible to all players
No Randomness: Outcomes determined solely by player decisions
Minimal Theme: Mechanics over narrative
Player Agency: Success depends on strategic thinking

Quick Reference: Game Types

Type	Core Mechanic	Examples
Connection	Form paths/networks	Hex, TwixT
Territory	Control areas	Go, Othello
Capture	Eliminate pieces	Chess, Checkers
Pattern	Create arrangements	Gomoku, Pentago
Racing	Reach goal first	Chinese Checkers