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 hainamchung-ask-questions-if-underspecified npx -- -y @trustedskills/hainamchung-ask-questions-if-underspecified
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"hainamchung-ask-questions-if-underspecified": {
"command": "npx",
"args": [
"-y",
"@trustedskills/hainamchung-ask-questions-if-underspecified"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill allows an AI agent to proactively ask clarifying questions when a user's prompt is ambiguous or lacks sufficient detail. Instead of making assumptions, the agent will request more information to ensure accurate and relevant responses. This leads to better understanding and ultimately, improved task completion.
When to use it
- When you anticipate users might provide incomplete instructions.
- For complex tasks where multiple interpretations are possible.
- To improve the quality of AI-generated output by ensuring a clear understanding of user intent.
- In situations where avoiding incorrect assumptions is critical.
Key capabilities
- Identifies underspecified prompts.
- Generates clarifying questions.
- Requests additional information from the user.
Example prompts
- "Write a report about sales." (The agent should ask: "What time period are you interested in? What specific products or regions should be included?")
- "Summarize this article." (The agent should ask: "What is the desired length of the summary? Are there any key aspects you want me to focus on?")
- “Create an image.” (The agent should ask: “Can you describe what you’d like the image to depict?”)
Tips & gotchas
This skill works best when integrated into a conversational flow. Ensure the AI agent has the ability to present and process user responses to its clarifying questions.
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.