Skip to content
Development
Skill

/clarify-underspecified

Ask the minimum clarifying questions before implementing when scope, constraints, or success criteria are unclear. Use when a request has multiple plausible interpretations, missing acceptance criteria, or ambiguous environment constraints.

From plugin
awesome-agent-skill
26200 skills4 commands
Install
$ npx -y skills add charlieviettq/awesome-agent-skill --skill clarify-underspecified --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/clarify-underspecified

Context preview

The summary Claude sees to decide when to auto-load this skill.

Ask the minimum clarifying questions before implementing when scope, constraints, or success criteria are unclear. Use when a request has multiple plausible interpretations, missing acceptance criteria, or ambiguous environment constraints.

SKILL.md

clarify-underspecified.SKILL.md
name: clarify-underspecified
description: "Ask the minimum clarifying questions before implementing when scope, constraints, or success criteria are unclear. Use when a request has multiple plausible interpretations, missing acceptance criteria, or ambiguous environment constraints."
allowed-tools: Read, Glob, Grep

Clarify underspecified requests

When to use

  • Multiple plausible interpretations exist.
  • Objective, scope, constraints, or "done" criteria are missing.
  • Quick read-only discovery cannot resolve the ambiguity.

When not to use

  • Request is already specific enough to proceed.
  • A short repo/config read answers the open questions.

Workflow

1. Decide if the request is underspecified (objective, scope, constraints, environment, safety). 2. Ask **1-5** questions max; prefer multiple-choice with a `defaults` fast path. 3. Separate **need to know** vs **nice to know**. 4. Do not run mutating commands or commit to a detailed plan until must-have answers arrive. 5. If the user asks to proceed without answers, state assumptions explicitly and get confirmation.

Question format

1) Scope?
a) Minimal change (default)
b) Broader refactor in the same area
c) Not sure - use default

Reply: defaults (or 1a 2b)

Anti-patterns

  • Do not ask what a quick read of repo/docs already answers.
  • Do not ask open-ended questions when a yes/no or A/B choice is faster.

Output

Restate requirements in 1-3 sentences (constraints + success criteria), then start work.

Read more
Ships withawesome-agent-skill

Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

Get the whole plugin

Other skills on awesome-agent-skill.