What problem does it solve? Writing unambiguous software requirements is hard: vague prose leads to misinterpretation, scope creep, and untestable acceptance criteria. This Skill structures requirement definition using the GEARS/EARS notation, a standardized 3-file SPEC format (spec.md, plan.md, acceptance.md), and a systematic clarification process so every requirement is testable before implementation begins. ## Core Features & Use Cases - GEARS/EARS Requirement Patterns: Authors requirements using five canonical patterns (Ubiquitous, Event-driven, State-driven, Capability gate, Unwanted) with a unified compound clause and generalized subjects, including lint guidance for deprecated IF/THEN syntax. - Requirement Clarification Workflow: Applies a 5-step process (assumption analysis, Five Whys root cause analysis, scope definition, constraint extraction, success criteria and test scenario generation) to eliminate ambiguity before coding. - Plan-Run-Sync Integration: Connects SPEC documents to the MoAI-ADK workflow, including Git Worktree parallel development, SPEC lifecycle management, metadata schema validation, and TRUST 5 quality gates. - Use Case: When planning a JWT authentication feature, use this Skill to produce a SPEC with EARS requirements, quantified success criteria (e.g., P95 < 200ms), and a full test scenario table covering normal, error, edge, and security cases. ## Quick Start Ask the AI to create a SPEC document for your feature using EARS format requirements and Given-When-Then acceptance criteria.