Use when the user asks why a reported NVFLARE job failure signal occurred: the job failed, stalled, timed out, lost clients, ended with EXECUTION_EXCEPTION, or produced suspicious errors. Diagnose in simulation, POC, or production by collecting bounded evidence and mapping failure patterns to recovery actions.
Install
npx skills add NVIDIA/skills --skill nvflare-diagnose-jobnpx skills add NVIDIA/skills --skill nvflare-diagnose-job -a claude-code -gnpx skills add NVIDIA/skills --skill nvflare-diagnose-job -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/nvflare-diagnose-jobgh skill install NVIDIA/skills nvflare-diagnose-jobgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/nvflare-diagnose-job ~/.claude/skills/nvflare-diagnose-job # Claude Code
cp -R /tmp/NVIDIA__skills/skills/nvflare-diagnose-job ~/.agents/skills/nvflare-diagnose-job # Codex, Cursor, Gemini CLI, Copilot, OpenCode