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
simulation-environmentUser-facing Go1 Isaac Gym environment and configuration guidance: Cfg and config_go1 setup, terrain, observations and history, reward scales, domain randomization, assets, installation and backend diagnosis, and safe static validation.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill when the user needs static/API/configuration help for the
Go1 Isaac Gym environment: choosing and validating Cfg fields, applying
config_go1, understanding terrain and observation construction, checking
reward and domain-randomization surfaces, locating assets, or diagnosing
installation and backend prerequisites.
torch.cuda.is_available() result is not
evidence that Isaac Gym or the simulator runtime works.training-and-policy, actuator fitting or
actuator-network behavior to actuator-network, and physical Go1 operation
or hardware safety to robot-deployment.The generated scope is static/API/configuration and prerequisite diagnosis pending Isaac Gym. It does not certify simulator execution, CUDA PhysX behavior, training quality, playback, checkpoints, actuator fitting, or robot hardware deployment.