AS

ask-user-question

A tool that allows the agent to send questions directly to the user interface.

Install

mkdir -p .claude/skills/ask-user-question && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/843" && unzip -o skill.zip -d .claude/skills/ask-user-question && rm skill.zip

Installs to .claude/skills/ask-user-question

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.
202 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Display interactive modals for user input
  • Request clarification on ambiguous tasks
  • Confirm destructive or sensitive actions
  • Collect user preferences via selectable options
  • Capture custom text input from users

How it works

The skill triggers a UI modal that allows the user to interact with the agent, bypassing the terminal which the user cannot see.

Inputs & outputs

You give it
Question text, header, and optional selection choices
You get back
User selection or custom text response

When to use ask-user-question

  • Requesting clarification on ambiguous user prompts
  • Confirming destructive actions before execution
  • Asking for user preferences during a workflow

About this skill

Ask User Question

Use this MCP tool to ask users questions and get their responses. This is the ONLY way to communicate with the user - they cannot see CLI/terminal output.

Critical Rule

The user CANNOT see your text output or CLI prompts!

If you write "Let me ask you..." and then just output text - THE USER WILL NOT SEE IT. You MUST call this tool to display a modal in the UI.

When to Use

  • Clarifying questions before starting ambiguous tasks
  • Asking user preferences (e.g., "How would you like files organized?")
  • Confirming actions before executing (especially destructive/irreversible ones)
  • Getting approval for sensitive actions (financial, messaging, deletion, etc.)
  • Any situation where you need user input to proceed

Parameters

{
  "questions": [{
    "question": "Your question to the user",
    "header": "Short label (max 12 chars)",
    "options": [
      { "label": "Option 1", "description": "What this does" },
      { "label": "Option 2", "description": "What this does" }
    ],
    "multiSelect": false
  }]
}
  • question (required): The question text to display
  • header (optional): Short category label, shown as modal title (max 12 chars)
  • options (optional): Array of selectable choices (2-4 recommended)
  • multiSelect (optional): Allow selecting multiple options (default: false)

Custom text input: To allow users to type their own response, include an option with label "Other" (case-insensitive). When selected, the UI shows a text input field.

{ "label": "Other", "description": "Type your own response" }

Important: When "Other" is selected, the response will be User responded: [their text] instead of User selected: Other. You must wait for and handle this text response - do NOT proceed as if they selected a predefined option.

Examples

Asking about organization preferences

AskUserQuestion({
  "questions": [{
    "question": "How would you like to organize your Downloads folder?",
    "header": "Organize",
    "options": [
      { "label": "By file type", "description": "Group into Documents, Images, Videos, etc." },
      { "label": "By date", "description": "Group by month/year" },
      { "label": "By project", "description": "You'll help me name project folders" }
    ]
  }]
})

Confirming a destructive action

AskUserQuestion({
  "questions": [{
    "question": "Delete these 15 duplicate files?",
    "header": "Confirm",
    "options": [
      { "label": "Delete all", "description": "Remove all 15 duplicates" },
      { "label": "Review first", "description": "Show me the list before deleting" },
      { "label": "Cancel", "description": "Don't delete anything" }
    ]
  }]
})

Simple yes/no confirmation

AskUserQuestion({
  "questions": [{
    "question": "Should I proceed with sending this email?",
    "header": "Send email",
    "options": [
      { "label": "Send", "description": "Send the email now" },
      { "label": "Cancel", "description": "Don't send" }
    ]
  }]
})

Response Format

The tool returns the user's selection:

  • User selected: By file type - Single selection
  • User selected: Option A, Option B - Multiple selections (if multiSelect: true)
  • User responded: [custom text] - If user typed a custom response
  • User declined to answer the question. - If user dismissed the modal

Wrong vs Correct

WRONG (user won't see this):

I'll help organize your files. How would you like them organized?
- By type
- By date
- By project

CORRECT (user will see a modal):

AskUserQuestion({
  "questions": [{
    "question": "How would you like your files organized?",
    "options": [
      { "label": "By type" },
      { "label": "By date" },
      { "label": "By project" }
    ]
  }]
})

When not to use it

  • When CLI output is sufficient for user communication

Limitations

  • User can dismiss the modal without answering
  • Modal title is limited to 12 characters

How it compares

It provides a direct UI-based communication channel for user feedback, whereas standard CLI output is invisible to the user.

Compared to similar skills

ask-user-question side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
ask-user-question (this skill)175moNo flagsBeginner
himalaya502moReviewIntermediate
discord-send-message79moReviewIntermediate
voicemode82moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

himalaya

openclaw

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

50191

discord-send-message

Nice-Wolf-Studio

Send messages to Discord channels via the Discord API. Use this skill when the user wants to send text messages, notifications, or formatted content to a Discord channel.

7123

voicemode

mbailey

This skill provides voice interaction capabilities for AI assistants. This skill should be used when users mention voice mode, want to have voice conversations, speak with Claude, check voice service status, or manage voice services like Whisper and Kokoro.

8104

officeemail-management

harperreed

Handle email tasks (checking inbox, drafting replies, managing threads, adding events to calendar). Use when working with emails to prevent common mistakes like broken threading or missing recipients.

896

campaign-orchestration

ernijsansons

Create and execute personalized multi-channel campaigns across email, LinkedIn, and phone based on intelligence gathering triggers. Use when planning outreach sequences, optimizing engagement strategies, or executing systematic follow-up campaigns.

690

baoyu-post-to-wechat

JimLiu

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (图文) with multiple images. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "图文/文章".

746

Search skills

Search the agent skills registry