RoboSkills is a low-cost, minimal set of agent workflows and tools for robotics.

Sharpa hands playing cat's cradle, reconstructed from a human video.
![]() Auto Research Improve policies and reusable skills through repeated simulation experiments. Setting: Auto-research; no direct privileged simulator state in the policy API. |
![]() Agent as Policy An LLM observes an episode and chooses actions turn by turn. Setting: Zero/one-shot demonstrations; no auto-research. |
![]() Agentic Simulation Solve simulation tasks from natural-language instructions. Setting: Privileged simulator information available. |
![]() Real2Sim Build interactive simulations from demonstrations. Setting: Physics simulation included. |
![]() Motion Generation One agent turns a text, image or video request into a motion video. Setting: Kinematic motion and rendering; no physics. |
With suitable tools, agents reach comparable performance on fewer, cheaper tokens.
We commit to keeping each workflow under 1,000 lines of code.
| Tool | Does | Reference |
|---|---|---|
| kinematics, motion planning, robot hands | Code | |
| learned grasps | Code | |
| text → masks | Paper · Code | |
| image → object mesh | Paper · Code | |
| image → depth | Paper · Code | |
| image → gravity | Paper · Code | |
| video → hand motion | Paper · Code | |
| image → hands (MANO) | Paper · Code | |
| video → human motion | Paper · Code | |
| text → G1 or human motion | Paper · Code | |
| rendering | Site · Code | |
| mesh → convex collision parts | Paper · Code | |
| physics, IK, contact feedback, rendering | Paper · Code |
Requires Python 3.10 or newer:
uv add roboskills # or: pip install roboskillsThe workflows run from a clone (git clone https://github.com/openrobokit/roboskills && cd roboskills && uv sync); each
workflow's README goes on from there.









