The Physical AI skills AI agents need.

Robium gives AI agents the expertise to architect, build, and validate Physical AI applications across simulation, data, visualization, and robotics integration. Grounded in battle-tested reference applications and continuously evolving skills.

Claude Code Cursor soon Gemini soon

/plugin marketplace add mdemirst/robium-plugin
/plugin install robium@robium

> build a mobile robot that navigates in sim

Native Cursor packaging is next.
robium's skills are plain Markdown — the
manifest is the only missing piece.

> build a mobile robot that navigates in sim

Native Gemini packaging is next.
robium's skills are plain Markdown — the
manifest is the only missing piece.

> build a mobile robot that navigates in sim

Browse skills catalog

21 skills, 11 integrations

AI agents are good at code. Robotics asks for more than code — a sprawling stack, scattered docs, and the hard-won judgment that usually lives only in an engineer's head. Robium hands your agent that judgment: hand-crafted, well-tested skills, and an architect that turns a plain-language ask into a real stack decision.

Architecture & proof

The spine of every build: pick the stack, then prove it runs.

architect v1.3.0

Entry-point skill for designing robotics applications with AI agents. Turns requirements (robot type, task, hardware, sim-vs-real, GPU/budget) into a full stack decision — middleware, simulation, data, visualization, training frameworks — plus a scaffold plan and a written architecture brief.

testing v1.2.0

Test-driven robotics development: smoke tests for launch files, sim-based regression tests, node-level unit tests, policy eval as a test, and CI patterns for robotics repos.

Simulation

Test the robot before you own the robot.

simulation v1.0.0

Choose and set up robotics simulators, and simulate sensors correctly: Gazebo vs Isaac Sim selection, sensor fidelity (rates, noise models, frames matching the real robot), determinism, and sim-to-real considerations.

gazebo v1.2.0

Modern Gazebo (gz — Harmonic/Ionic line) simulation: SDF worlds and models, sensors (lidar, camera, IMU, contact), the ros_gz bridge, spawning robots, and headless/server operation.

isaac-sim v1.0.1

NVIDIA Isaac Sim: installation and container setup, GPU/driver requirements, USD scenes, robots and sensors, the ROS 2 bridge, and headless/livestream operation for remote servers.

isaac-lab v1.0.1

NVIDIA Isaac Lab: reinforcement-learning and imitation-learning workflows on top of Isaac Sim — prebuilt environments and tasks, training runs, and exporting policies.

Data

Curated datasets and the training loop that consumes them.

data v1.1.0

Data sourcing strategy for robotics and physical-AI: choose between offline datasets (HuggingFace hub, Open X-Embodiment and similar), simulation-generated data, and teleop/real-robot collection; plan storage formats, episode structure, and dataset versioning.

lerobot v2.0.0

HuggingFace LeRobot for physical-AI manipulation: the LeRobotDataset format, loading and recording episodes, training policies (ACT, diffusion, pi0) and VLAs (SmolVLA), evaluating in simulation, and teleoperation.

huggingface v1.1.0

HuggingFace ecosystem for robotics projects: hub datasets and models for robot learning, and demo Spaces. DELEGATES: for hub mechanics (download/upload/auth/jobs), install HuggingFace's own skills — /plugin marketplace add huggingface/skills, then /plugin install hf-cli@huggingface-skills — and defer to them; this skill adds only the robotics-specific layer (which datasets and models matter for manipulation and navigation, robotics dataset conventions on the hub).

Visualization

See what the robot sees — locally, or on a remote server.

visualization v1.0.1

Choose and apply robotics visualization: selection guidance for rviz2 vs Foxglove vs Rerun, plus best practices — what to visualize at each dev stage, live vs recorded, local vs remote.

foxglove v1.2.0

Foxglove for robotics visualization: foxglove_bridge setup for live ROS 2 robots, layouts, MCAP recording and playback, and remote/web visualization of robots running on servers.

rerun v1.1.0

Rerun for data-centric robotics and ML visualization: logging APIs (Python), timelines, entity paths, and viewing policy rollouts, episode data, and sensor streams.

rviz2 v1.0.1

RViz2 visualization for ROS 2: displays, TF frame debugging, markers, saved config files, and the common 'nothing shows up' fixes (fixed frame, QoS, sim time).

Robotics integration

The middleware, the navigation stack, and reproducible environments.

ros2 v1.1.0

Core ROS 2 usage: workspaces, colcon builds, packages (ament_python/ament_cmake), nodes, topics/services/actions, QoS, launch files, parameters, TF2, rosdep, and gluing third-party packages together.

nav2 v1.1.1

Nav2 mobile-robot navigation for ROS 2: bringup, behavior trees, costmaps, planner/controller servers, localization (AMCL, slam_toolbox), waypoint following, and tuning.

integration v1.2.0

Glue robotics modules into one running system: choose module boundaries, pick inter-module communication (ROS 2 topics/services/actions, zenoh, gRPC, REST, shared memory), and write solid Dockerfiles and docker-compose for robotics workloads.

environments v1.2.0

Virtual-environment-first setup for robotics projects: decide uv/venv vs Docker, make local and remote-server runs reproduce identically, handle GPU passthrough and headless/display forwarding.

Try live demos

Built with Robium skills

Real applications, built by the skills with minimal intervention, and green on every run. They are the regression suite, the starter kits, and the proof — all at once. Take one, or build something entirely your own. All of them live in robium-applications.