Use Case Specification

This walks you through creating a structured use case spec before you start any model customization work, following AWS Responsible AI Lens recommendations. 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.

skills.sh installs: 183
GitHub stars: 938
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add awslabs/agent-plugins --skill use-case-specification --agent claude-code

Installs into .claude/skills of the current project.

Files

Use Case Specification

Multi-turn conversation to gather use case details and produce a use case specification document.

Principles

One thing at a time. Each response advances exactly one decision or collects one piece of information.
Confirm before proceeding. Wait for the user to approve the spec before considering this skill complete.
Infer, don't interrogate. Use what's already known from the conversation. Only ask when you truly can't infer.
Do NOT ask about base model selection. Model selection is handled exclusively by the model-selection skill.

Workflow

Step 0: Check for Existing Spec

Before starting discovery, check if a *_use_case_spec.md file already exists in the project. If it does, present it to the user and ask whether they want to reuse it, modify it, or start fresh.