Repository
microsoft/physical-ai-toolchain agent skills
- skills
- 7
- official
- 7
- GitHub stars
- 123
- Stars
- 123 (62 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Mar 2026
Install all skills
npx skills add microsoft/physical-ai-toolchainAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in microsoft/physical-ai-toolchain, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Submit, monitor, analyze, and evaluate LeRobot imitation learning training jobs on OSMO with Azure ML MLflow integration and inference evaluation - Brought to you by microsoft/physical-ai-toolchain | microsoft/ | 123 | — | ~3.8k | Automated safety check: Notes | MIT | yesterday |
| 2 | Set up a K3s cluster on an NVIDIA GPU host, connect it to Azure Arc, and configure Azure ML to use it as a Kubernetes compute target. | microsoft/ | 123 | — | ~5.7k | Automated safety check: Notes | MIT | yesterday |
| 3 | Generate, transfer, and consume environment-specific Azure, AKS, OSMO, ACR, and Azure ML deployment bundles. | microsoft/ | 123 | — | ~5.8k | Automated safety check: Pass | MIT | yesterday |
| 4 | Deploy trained robot policies to edge fleets via FluxCD GitOps, image automation, and deployment gating | microsoft/ | 123 | — | ~518 | Automated safety check: Pass | MIT | yesterday |
| 5 | Monitor robot fleet telemetry via Azure IoT Operations, drift detection, Grafana dashboards, and Fabric analytics | microsoft/ | 123 | — | ~598 | Automated safety check: Pass | MIT | yesterday |
| 6 | Deploy and manage Azure infrastructure for the Physical AI Toolchain including Terraform IaC, Kubernetes setup, GPU configuration, and network topology | microsoft/ | 123 | — | ~1.6k | Automated safety check: Pass | MIT | yesterday |
| 7 | Generate synthetic training data using NVIDIA Cosmos world foundation models for SDG pipelines | microsoft/ | 123 | — | ~469 | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill in microsoft/physical-ai-toolchain?
Osmo Lerobot Training (official) from microsoft/physical-ai-toolchain ranks first of the 7 skills in microsoft/physical-ai-toolchain listed here, with the highest score: its repository has 123 GitHub stars, its SKILL.md loads about 3.8k tokens and it has informational notes only in the automated safety check. Next come Azureml K3s Compute Target Setup and Environment Deployment.
Are the skills in microsoft/physical-ai-toolchain official?
7 of the 7 skills in microsoft/physical-ai-toolchain are official, published by the vendor's own GitHub organization: Osmo Lerobot Training, Azureml K3s Compute Target Setup, Environment Deployment, Fleet Deployment, Fleet Intelligence and 2 more.
How do I install all skills from microsoft/physical-ai-toolchain?
Run npx skills add microsoft/physical-ai-toolchain in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.