ask-questions-if-underspecified

Generates targeted clarifying questions before implementing ambiguous requests.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/marumo333/atrox --skill ask-questions-if-underspecified-marumo333
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ask-questions-if-underspecified
Source: https://github.com/marumo333/atrox/tree/main/.claude/skills/trailofbits/plugins/ask-questions-if-underspecified/skills/ask-questions-if-underspecified
Command: npx skills add https://github.com/marumo333/atrox --skill ask-questions-if-underspecified-marumo333

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Ambiguous or underspecified requests often lead to wrong implementations, wasted effort, and rework. This Skill ensures requirements are clarified before any code is written or commands are run. ## Core Features & Use Cases - Underspecification Detection: Evaluates requests against objective, scope, constraints, environment, and safety criteria to decide if clarification is needed. - Structured Questioning: Produces 1-5 numbered, multiple-choice questions with recommended defaults and fast-path replies like defaults or 1a 2a. - Safe Pause Behavior: Blocks implementation until must-have answers arrive, while permitting clearly labeled low-risk discovery reads. - Use Case: A user asks to "update the API" without specifying version compatibility or scope. The Skill asks which endpoints are in scope and what compatibility target applies before any edits begin. ## Quick Start Ask the assistant to clarify requirements before implementing whenever a request has multiple plausible interpretations or missing constraints.

Frequently Asked Questions about ask-questions-if-underspecified

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

FAQPage Schema
How do I clarify requirements before starting implementation?▼

Identify which of the objective, scope, constraints, environment, or safety details are unclear, then ask 1-5 numbered questions with multiple-choice options. Wait for answers before editing files or running commands.

How to write clarifying questions that users answer quickly?▼

Keep questions short and numbered, offer lettered multiple-choice options, and bold a recommended default for each. Include a fast-path reply like `defaults` so users can accept all recommendations in one word.

When should I not ask clarifying questions?▼

Skip questions when the request is already clear or when a quick, low-risk discovery read of configs, existing patterns, or docs can answer the missing details. Avoid open-ended questions when a yes/no or multiple-choice would resolve ambiguity faster.

What should I do if the user says to proceed without answering?▼

State your assumptions as a short numbered list and ask for explicit confirmation. Proceed only after the user confirms or corrects those assumptions, then restate the requirements before starting work.

How many clarifying questions should be asked at once?▼

Ask 1-5 questions in the first pass, prioritizing ones that eliminate entire branches of work. Separate need-to-know from nice-to-know items to reduce friction and keep the exchange scannable.