executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
wrappers-and-utilitiesUse PettingZoo conversion wrappers, utility wrappers, AgentSelector, reward/observation helpers, and wrapper troubleshooting guidance.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill when an agent needs to convert between PettingZoo AEC and Parallel APIs, compose utility wrappers, diagnose wrapper errors, use AgentSelector, compute random-policy reward baselines, save image observations, or capture text rendering.
aec_to_parallel, parallel_to_aec, turn_based_aec_to_parallel, wrapper ordering, AEC-vs-Parallel limitations, base wrappers, or multi-episode wrappers.AgentSelector, average_total_reward, save_observation, CaptureStdoutWrapper, capture_stdout, or EnvLogger guidance.parallel_to_aec and valid aec_to_parallel conversion semantics work in the installed PettingZoo package.step(None) control flow, use ../use-environments/SKILL.md.raw_env() factories, _was_dead_step, _clear_rewards, or custom AgentSelector turn logic, use ../custom-environments/SKILL.md.api_test, parallel_api_test, seed tests, render tests, or native wrapper test selection, use ../testing-and-validation/SKILL.md.Treat PettingZoo's utility wrappers as mostly AEC-oriented. If a user starts from a Parallel environment, convert to AEC when needed, apply AEC wrappers there, then convert back only when the environment satisfies the parallel-conversion assumptions.