inference-server

Run `npx skills use "https://github.com/huggingface/prime-rl" --skill "huggingface/prime-rl/inference-server"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the skills in "https://github.com/huggingface/prime-rl" that are relevant to the current task. Run `npx skills add "https://github.com/huggingface/prime-rl"` and select the relevant skills, then follow their instructions.