speckit-clarify

Detects and resolves ambiguities in feature specifications through targeted clarification questions.

Updated Aug 28, 2026
One-click install
npx skills add https://github.com/B18Bu/Refund-Agent --skill speckit-clarify-b18bu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speckit-clarify
Source: https://github.com/B18Bu/Refund-Agent/tree/main/.agents/skills/speckit-clarify
Command: npx skills add https://github.com/B18Bu/Refund-Agent --skill speckit-clarify-b18bu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Feature specifications often contain vague requirements, missing decision points, and undefined edge cases that cause rework during planning and implementation. This Skill systematically scans a spec for underspecified areas and encodes clarified answers directly back into the spec file. ## Core Features & Use Cases - Structured Ambiguity Scan: Evaluates the spec across a taxonomy covering functional scope, data model, UX flows, non-functional requirements, integrations, edge cases, and terminology. - Interactive Questioning Loop: Asks up to 5 high-impact clarification questions one at a time, each with a recommended option or suggested answer. - Incremental Spec Updates: Records each accepted answer under a Clarifications section and applies it to the relevant spec sections, then re-validates the requirements checklist. - Use Case: Before running implementation planning on a new feature spec, run this Skill to resolve open questions about security posture, data constraints, and acceptance criteria so downstream tasks are built on unambiguous requirements. ## Quick Start Ask the assistant to clarify the current feature spec and resolve any ambiguous requirements before planning.

Frequently Asked Questions about speckit-clarify

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clarify ambiguities in a feature specification?▼

Run the clarify workflow on the active feature spec. It scans categories like functional scope, data model, and edge cases, then asks up to 5 targeted questions and writes the accepted answers directly into the spec file.

When should I run spec clarification in spec-kit?▼

Run clarification after creating the spec with the specify step and before invoking the plan step. Skipping it is allowed for exploratory spikes, but downstream rework risk increases when ambiguities remain unresolved.

How many clarification questions does the workflow ask?▼

The workflow asks a maximum of 5 questions per session, presented one at a time. Each question is either multiple-choice with a recommended option or a short answer constrained to five words or fewer.

Does spec clarification update the requirements checklist?▼

Yes. If a requirements checklist exists in the feature directory, it re-evaluates each checkbox item against the updated spec and toggles only the markers whose pass/fail state changed, reporting newly passing items and regressions.

What happens if the spec file is missing during clarification?▼

The workflow aborts and instructs you to run the specify step first. It does not create a new spec file, since clarification only operates on an existing feature specification.