【统一运行与基础诊断技能】按 discover、preflight、execute、diagnose 固定闭环执行测试任务,依据 onescience.json 的 execution_profile 三元组路由执行通道;SCnet 提交任务时必须读取根级 onescience.json.scnet 并把 region、partition/queue、work_dir 和资源参数交给 scnet-chat;配置问题自动委托 onescience-runsite 补齐后回到 runtime 继续原测试任务,环境问题自动委托 onescience-installer 安装或修复并 verify 成功后回到 runtime 继续原测试任务;当 execution_mode 为 slurm 且提交或运行反馈表明 partition、gpus_per_node、memory 等资源不可用时,探测可用 SLURM 资源并受控调整后重试。
$npx -y skills add onescience-ai/oneskills --skill onescience-runtimeInstalls into the current project.
Run `npx skills use "https://github.com/onescience-ai/oneskills" --skill "onescience-ai/oneskills/onescience-runtime"` 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/onescience-ai/oneskills" that are relevant to the current task. Run `npx skills add "https://github.com/onescience-ai/oneskills"` and select the relevant skills, then follow their instructions.