Loading...
Loading...
Found 3 Skills
Adds or modifies a Physical AI Studio policy under library/src/physicalai/policies. Use when creating a new policy family with the config/model/policy split, registering it in the get_policy factory and package exports, or keeping a policy compatible with Lightning training and export. Covers Pi0.5, Pi0, ACT, GR00T, SmolVLA, and LeRobot-wrapped policies.
Trains, validates, tests, and runs prediction for Physical AI Studio policies via the library Lightning stack. Use when running physicalai fit/validate/test/predict, calling physicalai.train.Trainer and Policy APIs from Python, writing or editing YAML configs under library/configs, wiring a model + datamodule + trainer, resuming from a checkpoint, or debugging a training run. Covers ACT, Pi0, Pi0.5, GR00T, and SmolVLA.
Drive the full lifecycle of a custom Flex Gateway policy with the Policy Development Kit (PDK) — verify prerequisites, scaffold the project, edit the gcl.yaml schema, build the WebAssembly artifact, exercise it locally with the Docker playground, then publish a dev version and cut a release to Anypoint Exchange. Use this skill whenever the user mentions PDK, Flex Gateway custom policies, `anypoint-cli-v4 pdk`, `cargo anypoint`, `make build` / `make publish` / `make release`, the `wasm32-wasip1` target, or asks to "create a custom policy", "scaffold a PDK project", "build a Flex Gateway policy", "publish a policy to Exchange", "test my policy locally", "upgrade PDK", or troubleshoots a PDK build / publish / release failure — even if they don't use the word "PDK" explicitly.