Deploy and monitor model API endpoints in Domino. Covers creating prediction endpoints, version management, Grafana dashboards for latency/errors/resources, alerting, and GPU inference with NVIDIA Triton. Use when deploying models as APIs, monitoring production endpoints, or debugging endpoint issues.
安装
npx skills add dominodatalab/domino-claude-plugin --skill domino-model-endpointsnpx skills add dominodatalab/domino-claude-plugin --skill domino-model-endpoints -a claude-code -gnpx skills add dominodatalab/domino-claude-plugin --skill domino-model-endpoints -a codex -ggemini skills install https://github.com/dominodatalab/domino-claude-plugin.git --path skills/model-endpointsgh skill install dominodatalab/domino-claude-plugin domino-model-endpointsgit clone --depth 1 https://github.com/dominodatalab/domino-claude-plugin /tmp/dominodatalab__domino-claude-plugin
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/dominodatalab__domino-claude-plugin/skills/model-endpoints ~/.claude/skills/domino-model-endpoints # Claude Code
cp -R /tmp/dominodatalab__domino-claude-plugin/skills/model-endpoints ~/.agents/skills/domino-model-endpoints # Codex, Cursor, Gemini CLI, Copilot, OpenCode