nash-game-theory

To create a game theory environment for Nash equilibrium simulation, use a SKILL.md-driven template to define an environment class, configure payoff matrices, set theoretical equilibrium expectations, and wire a factory function for CLI integration.

You can validate custom payoff matrices against Nash equilibrium convergence by implementing validation metrics logic within the environment template and running convergence checks through the NASH CLI validate workflow.

Integrating a new game environment into NASH CLI workflows requires defining an environment class and a factory function in the repository structure, ensuring compatibility with run, validate, and visualization commands.

You need a custom Nash equilibrium environment when existing models fail to match your specific incentive structures, such as coordination incentives, signaling mechanisms, or custom policy games requiring formalization and benchmark testing.

Python NumPy is supported for defining payoff matrices in game theory environment design, enabling you to configure theoretical predictions and parameter ranges before implementing validation hooks in the environment class.

The research-to-implementation workflow for game theory environments guides parallel subagent research to derive payoff structures, theoretical predictions, and parameter ranges before coding the environment class and validation metrics.