What problem does it solve? Writing clear, testable requirements is hard: teams produce ambiguous, compound, or untestable statements that cause rework later. This Skill reviews requirement statements against the EARS (Easy Approach to Requirements Syntax) notation, classifies each one into exactly one pattern, and enforces traceability back to legacy source code. ## Core Features & Use Cases - EARS pattern classification: Classifies each requirement as Ubiquitous, Event-driven, State-driven, Optional, Unwanted, or Complex, with templates for each pattern. - Quality checklist: Detects common defects such as ambiguous wording, hidden compound requirements, untestable statements, passive voice, and implementation details leaking into behavior specs. - Legacy traceability enforcement: Requires every requirement to carry a REQ-ID, acceptance criteria, and a source_legacy pointer to a Natural/Adabas legacy file or a justified [GREENFIELD] token. - Use Case: During a legacy modernization sprint, paste a draft requirement like "the system should be fast" and receive a corrected EARS statement such as "WHEN a user submits a form, the system SHALL respond within 500 ms", complete with REQ-ID, acceptance criteria, and traceability metadata. ## Quick Start Ask the assistant to review your draft requirements for EARS compliance and rewrite any that are ambiguous, compound, or missing traceability.