Run multi-agent game theory simulations and equilibrium validations via CLI.
npx skills add https://github.com/chiangchenghsin-hash/n-nash --skill nash-cli
Please help me install this Agent Skill. Skill: nash-cli Source: https://github.com/chiangchenghsin-hash/n-nash/tree/main/nash-cli Command: npx skills add https://github.com/chiangchenghsin-hash/n-nash --skill nash-cli
NASH CLI removes friction in running, validating, sweeping, and visualizing multi-agent game theory simulations, so you can focus on interpreting equilibrium behavior instead of wiring up tooling.
Ask your AI to run uv run nash env list to confirm the available simulation environments and then execute uv run nash run --preset hawk_dove --agents 100 --rounds 200 --seed 42 -o results.json to produce JSON metrics for analysis.
High-intent search queries and answers about installing and using this skill.
Run multi-agent game theory simulations by executing a single command with preset environments, controlled seeds, and specified agent or round counts to output machine-readable JSON metrics for equilibrium analysis.
Yes, you can validate simulation results against statistical baselines and Nobel equilibrium criteria using built-in validation commands that assess equilibrium behavior across the eight Nobel-inspired models.
Sweep parameters across multi-agent game environments by running config-generated grids that systematically test variable ranges, producing statistical outputs for comparing equilibrium behavior and time-series metrics.
Visualize time-series metrics from simulation outputs by generating Matplotlib-based charts that plot behavioral data over rounds, allowing you to interpret equilibrium dynamics visually instead of parsing raw JSON.
Yes, NASH CLI supports deterministic and reproducible simulation execution by accepting user-controlled random seeds, ensuring identical preset environments yield consistent machine-readable JSON results across multiple runs.
List available Nobel-modeled simulation environments and fetch their specifications using the environment discovery command, enabling reproducible experiment setup before executing parameter sweeps or validations.
bhutanoInstall and configure a persistent Claude Code usage bar across platforms.
chiangchenghsin-hashValidate NASH simulation results against Nobel equilibrium benchmarks and generate statistical interpretations.
logeshv586-codeAnalyze spreadsheet data and create charts with openpyxl, pandas, and matplotlib.
chiangchenghsin-hashCreate configurable game-theory environment templates for Nash equilibrium simulation and validation.
