Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
66
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The docs include explicit runtime fetches of external code: a Git workdir URL (https://github.com/user/repo.git) in references/advanced-usage.md which would be cloned as the task workdir and could contain executable code, and a pip extra index URL (https://download.pytorch.org/whl/torch_stable.html) in references/troubleshooting.md used during setup to download and install remote wheels — both are fetched at runtime and can lead to execution of remote code.
3a6c3a9
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.