Ask Questions If Underspecified
This skill prompts for clarification when input is vague or lacks detail, ensuring more accurate and relevant responses.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add ask-questions-if-underspecified npx -- -y @trustedskills/ask-questions-if-underspecified
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"ask-questions-if-underspecified": {
"command": "npx",
"args": [
"-y",
"@trustedskills/ask-questions-if-underspecified"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill enables an AI agent to recognize when a user's request is vague or lacks sufficient detail and prompts the user for clarification. It ensures that the agent can provide accurate, relevant responses by asking targeted questions to fill in missing information.
When to use it
- A user provides a request with ambiguous parameters, such as "Fix this bug."
- The task requires specific input that isn't clearly defined, like "Generate a report."
- You want to avoid making assumptions about the user's intent or requirements.
- The AI agent needs additional context to perform its function effectively.
Key capabilities
- Detects underspecified requests in natural language
- Prompts users for missing details
- Improves accuracy of responses by gathering necessary information
Example prompts
- "How can I help you today?"
- "Could you clarify what you mean by 'fix this bug'?"
- "What kind of report are you looking for?"
Tips & gotchas
- This skill works best when paired with a clear set of follow-up questions tailored to the domain.
- Avoid over-prompting, as it may frustrate users if too many clarifications are required.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.