Tooluck logoTooluck
SKILL.md

use-case-specification

Agent skill fromawslabs/agent-plugins

Creates a reusable use case specification file that defines the business problem, stakeholders, and measurable success criteria for model customization, as recommended by the AWS Responsible AI Lens. Use as the default first step in any model customization plan. Skip only if the user explicitly declines or already has a use case specification to reuse. Captures problem statement, primary users, and LLM-as-a-Judge success tenets.

How to install use-case-specification

install use-case-specification
# install the agent-plugins pack with the skills CLI
npx skills add awslabs/agent-plugins

# or add only this skill to Claude Code: copy the folder

plugins/sagemaker-ai/skills/use-case-specification/

# into

~/.claude/skills/use-case-specification/ (all projects)

.claude/skills/use-case-specification/ (one project)

plugins/sagemaker-ai/skills/use-case-specification/SKILL.md

Apache-2.0Full file
1# Use Case Specification
2
3Multi-turn conversation to gather use case details and produce a use case specification document.
4
5## Principles
6
71. **One thing at a time.** Each response advances exactly one decision or collects one piece of information.
82. **Confirm before proceeding.** Wait for the user to approve the spec before considering this skill complete.
93. **Infer, don't interrogate.** Use what's already known from the conversation. Only ask when you truly can't infer.
104. **Do NOT ask about base model selection.** Model selection is handled exclusively by the model-selection skill.
11
12## Workflow
13
14### Step 0: Check for Existing Spec
15
16Before 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.
17
18### Phase 1: Discovery (1–3 turns)
19
20Review what is already known from the conversation so far, then identify what is still missing. You need these three things:
21
22- **What** is the problem the user is trying to solve with model customization
23- **Who** will use the finetuned model and in what context
24- **Which** success criteria can be used to evaluate how well the custom model performs compared to the base model on a test set. Success criteria must be measurable by an LLM-as-a-Judge (e.g., response accuracy, tone adherence) — not things like latency or throughput.
25
26**Guidelines**:
27
28- Infer as much as possible from what the user has already said
29…

Excerpt shown under the repository's Apache-2.0 license.

More skills in agent-plugins

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates