
This walks you through creating a structured use case spec before you start any model customization work, following AWS Responsible AI Lens recommendations.
$ npx -y skills add awslabs/agent-plugins --skill use-case-specification --agent claude-codeInstalls into .claude/skills of the current project.
Sponsors
It asks just enough questions to capture your business problem, who'll use the model, and measurable success criteria that an LLM-as-a-Judge can evaluate. The workflow is deliberately low-friction: it infers from context instead of interrogating you, asks one thing at a time, and skips the whole process if you already have a spec file in your project. Think of it as enforced documentation that actually pays off later when you need to evaluate whether your fine-tuned model solved the problem you set out to solve. It won't ask about model selection, that's handled separately.
Select a file.