PAI-210 · Education

Agentic Physical AI: The Open Skill Layer

Build the open, cross-vendor skill layer that turns any policy into a robot skill: it installs, checks the body's declared capabilities against what the skill needs, and holds every action inside a runtime envelope on-device. You implement capability negotiation, the runtime envelope, policy-agnostic skills, LeRobot composition, and a safe MCP tool — then author and ship your own. The runtime clamp is the floor, not the guarantee — a box constraint bolted around the policy; the guarantee that matters is a certificate on the action's own energy, baked in (see Energy First Architecture).

Intermediate–Advanced·6 lessons · self-paced·6 lessons
▶ Start the course ← All courses
Module 1

The contract

Why robots need a skill layer: negotiate capabilities and bound the runtime.

  1. IntermediateWill this run on my robot?Answer a skill's compatibility against a robot's capabilities — before anything moves.→
  2. IntermediateThe safety envelope lives in the runtimeBound ANY policy — even a hijacked one — with a runtime that clamps every command.→
Module 2

Policy-agnostic skills

One contract, any policy — and composing the LeRobot ecosystem.

  1. IntermediateOne contract, any policySwap an analytic policy for a learned one without touching the contract, envelope, or wire.→
  2. IntermediateCompose LeRobot — one adapter, any checkpointDrive different LeRobot architectures through one `.select_action` adapter, with action chunking.→
Module 3

The protocol and the standard

Expose a robot to an LLM safely, then author and ship a skill.

  1. AdvancedMCP for robots, done rightExpose a robot to a language model over a tool that enforces the safety envelope in the protocol.→
  2. AdvancedCapstone — author and ship a skillWrite a skill contract, validate it, gate it, and run it inside its own safety envelope.→