This skill should be used when a startup without a dedicated ML platform team needs recurring, latency-tolerant offline inference for a self-hosted 1B to 8B generative language model on AWS while minimizing GPU spend and recovering automatically from Spot interruption.
Install
npx skills add awslabs/startups --skill self-hosted-llm-batch-inferencenpx skills add awslabs/startups --skill self-hosted-llm-batch-inference -a claude-code -gnpx skills add awslabs/startups --skill self-hosted-llm-batch-inference -a codex -ggemini skills install https://github.com/awslabs/startups.git --path solution-architecture/plugins/aws-startups-solution-architecture/skills/self-hosted-llm-batch-inferencegh skill install awslabs/startups self-hosted-llm-batch-inferencegit clone --depth 1 https://github.com/awslabs/startups /tmp/awslabs__startups
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/awslabs__startups/solution-architecture/plugins/aws-startups-solution-architecture/skills/self-hosted-llm-batch-inference ~/.claude/skills/self-hosted-llm-batch-inference # Claude Code
cp -R /tmp/awslabs__startups/solution-architecture/plugins/aws-startups-solution-architecture/skills/self-hosted-llm-batch-inference ~/.agents/skills/self-hosted-llm-batch-inference # Codex, Cursor, Gemini CLI, Copilot, OpenCode