/speckit.clarify
Agent skill wrapper for the Claude command /speckit.clarify.
When the original command text references {{INPUT}}, $1, or named arguments, map them from the user's current request.
Command Instructions
Systematically resolve underspecified areas in a feature spec through structured questioning. Run before /speckit.plan.
Steps
- Locate the spec:
- If input names a feature or file path, use it. - Otherwise check .specify/specs/*/spec.md; if multiple, ask which to clarify. - Fall back to spec.md in the project root.
- Load context: Read
spec.mdand.specify/memory/constitution.mdif present. - Scan for ambiguities across nine taxonomy categories:
- Functional scope, Data model, UX flows, Non-functional attributes, Integration points, Edge cases, Constraints, Terminology, Completion signals.
- Select questions: Choose the 5 highest-impact ambiguities. Prioritize by: scope > security > UX > technical detail. Each question must materially affect architecture, data modeling, testing, UX, or compliance.
- Ask one question at a time:
- Present the question with 2-5 multiple-choice options (or note that a short phrase is acceptable). - Mark the recommended answer with reasoning. - Wait for the user's answer before asking the next question.
- Update spec incrementally: After each answer, incorporate the clarification naturally into the relevant spec section. Do not append a Q&A log — merge it into the prose.
- Final validation: Check for duplicates, contradictions, and terminology drift across the updated spec.
- Report: Coverage map across all nine ambiguity categories (resolved / deferred / clear / outstanding).
Next step: Run /speckit.plan to generate the technical implementation plan.
{{INPUT}}