The Agent Skills Directory

[SAFE]: The skill serves as a comprehensive security and performance checklist for building ML inference servers.
[SAFE]: It proactively highlights critical security requirements, such as path traversal prevention and input sanitization for model identifiers.
[SAFE]: The documentation includes defensive coding patterns, including file size validation for uploads to prevent Denial of Service (DoS) via memory exhaustion.
[SAFE]: Standard ML serving practices are recommended, such as using torch.no_grad() for inference and ensuring proper GPU memory cleanup during model unloading.

runtime-skills