use-case-triage

Classify AI use cases against a registry and governance red lines.

9.1k|1.8k|Updated Apr 21, 2026
One-click install
npx skills add https://github.com/anthropics/claude-for-legal --skill use-case-triage-anthropics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: use-case-triage
Source: https://github.com/anthropics/claude-for-legal/tree/main/ai-governance-legal/skills/use-case-triage
Command: npx skills add https://github.com/anthropics/claude-for-legal --skill use-case-triage-anthropics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It stops the “can we just use AI for this?” hallway discussion by quickly classifying a proposed AI use case against the organization’s AI use case registry and red lines, then producing concrete conditions and routing for legal governance.

Core Features & Use Cases

  • Use-case classification: Determines whether a proposed use case is APPROVED, CONDITIONAL, or NOT APPROVED based on registry entries and red lines.
  • Governance routing: Flags required cross-plugin handoffs (for example privacy and product counsel) when personal data or product-launch implications are involved.
  • Actionable conditional output: Produces a conditions-and-next-steps table, governance tier, and approval path when a use case is CONDITIONAL.

Quick Start

Ask for triage by saying: triage this use case for AI governance: Sales team wants to score leads with AI automatically.

Frequently Asked Questions about use-case-triage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I classify AI use cases for legal governance and risk approval?

To classify AI use cases for legal governance, you triage proposed tasks against a configured use-case registry and governance red lines to produce APPROVED, CONDITIONAL, or NOT APPROVED outcomes.

What happens when an AI use case receives a conditional approval?

Conditional approval for an AI use case produces a conditions-and-next-steps table, assigns a governance tier, defines the required approval path, and flags cross-plugin handoffs for privacy or product counsel.

Can I batch triage multiple AI use cases or do I need to review them individually?

You can perform real-time triage on both single AI use cases and batches when asking whether AI can be used for described tasks, decisions, or workflows.

Does AI use case triage automatically route privacy handoffs to product counsel?

Yes, AI use case triage automatically flags required cross-plugin handoffs to privacy and product counsel when personal data or product-launch implications are detected in the proposed workflow.

What do I need to configure before running an AI use case risk classification?

Before running an AI use case risk classification, you must read the practice profile configuration to perform accurate registry lookups and execute governance red-line checks.

When should I avoid using automated AI use case triage?

You should avoid using automated AI use case triage if your organization lacks a configured use-case registry or established governance red lines, as the classification depends entirely on these configured boundaries.