Requirements Clarification Assistant

Problem It Addresses

Requirements often start as vague descriptions: business goals, user scope, functional boundaries, and technical constraints are scattered across chat messages. If engineers evaluate a solution directly from that input, they may miss key assumptions or discover priority conflicts only after rework. The req-clarifier skill turns unstructured, conversational input into a trackable working document, reducing communication gaps caused by silent assumptions.

How It Works

It progresses through capture, follow-up, merge, and output. In the first round, it organizes known information into background, goals, scope, constraints, and related fields, marking uncertain items as [to confirm]. It then asks no more than four high-priority questions, ordered from strategic intent to functional scope to execution constraints.

• Structured updates: Each round reprints the full current state, making changes easier to review.
• Domain-aware prompts: For software features, AI/LLM products, data analysis, and workflow automation, it probes platform, performance, model fallbacks, data sources, permissions, approvals, and other relevant details.
• Completeness scoring: It scores clarity of goals, success criteria, functional scope, resource constraints, and risks, then prepares a final specification once the score reaches 85 or the user confirms readiness.

Boundaries And Notes

This skill helps converge loose ideas into an executable specification, but it does not replace architecture design, compliance review, or scheduling decisions. The source emphasizes no assumptions without confirmation, so inferred details must be marked and validated. For requirements that depend on existing systems, data privacy, or security compliance, stakeholders still need to provide formal constraints. The final document reflects confirmed decisions, not unverified best practices.