dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or…
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.
$ npx -y skills add MemTensor/MemOS --skill ask-user-question --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ask-user-questionContext preview
The summary Claude sees to decide when to auto-load this skill.
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.
name: ask-user-question description: 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.
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.
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.
{
"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
}]
}**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.
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" }
]
}]
})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" }
]
}]
})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" }
]
}]
})The tool returns the user's selection:
**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" }
]
}]
})Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Repo: MemTensor/MemOS
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or…
Enforces explicit user permission before any file deletion. Activates when you're about to use rm, unlink, fs.rm, or any operation that removes files from…