speckit-clarify

To resolve ambiguity in feature specifications, run a structured clarification workflow that scans functional scope, data models, and UX flows, then records accepted answers directly into the spec. This ensures all decisions are explicit, complete, and testable before planning begins.

The best way to identify underspecified requirements is to perform a structured ambiguity scan across dimensions like non-functional quality attributes, integration dependencies, and edge cases. This process generates a prioritized queue of up to five high-impact questions to guide clarification.

To ensure spec clarifications are traceable and testable, apply accepted answers immediately to the spec under a dedicated Clarifications section with session tagging. This updates the specification after each answer to maintain explicit and complete decision records.

Yes, you can automate the clarification process across dimensions including Domain & Data Model, Interaction & UX Flow, and External Dependencies. The workflow iteratively asks up to five high-impact questions and updates the spec after each accepted answer to reduce downstream rework.

Before running a spec clarification workflow, you need a preflight prerequisites check and a loaded current feature specification. Establishing this reliable starting point allows the system to accurately scan for ambiguities and generate prioritized clarification questions.

You should use a structured clarification workflow for product requirements before planning to ensure decisions are explicit. It is applied to identify and resolve ambiguity across functional, data, UX, and non-functional dimensions, providing a post-session coverage summary to inform next steps.