ask-questions-if-underspecified
Guides an AI agent to pause and ask clarifying questions when a request has ambiguous objectives, unclear scope, or missing constraints.
Setup & Installation
What This Skill Does
Guides an AI agent to pause and ask clarifying questions when a request has ambiguous objectives, unclear scope, or missing constraints. The agent asks 1-5 targeted questions before doing any work, offers multiple-choice options with defaults, and waits for answers before proceeding.
Without this skill, agents make plausible-but-wrong assumptions and produce work that must be thrown out; structured upfront questions eliminate entire branches of wasted effort.
When to use it
- Asking about target file scope before a refactor that could touch dozens of files
- Getting confirmation on compatibility requirements before upgrading a dependency
- Clarifying acceptance criteria before writing tests for an underspecified feature
- Resolving ambiguous rollback requirements before running a data migration
- Confirming which components are in-scope before a performance optimization pass
Similar Skills
mcp-builder
A development guide for building MCP (Model Context Protocol) servers that connect LLMs to external APIs and services.
skill-creator
A skill for building, testing, and refining other skills.
template
A starter scaffold for building new agent skills.
answers
Provides AI-generated answers grounded in live web search results through Brave's OpenAI-compatible chat completions endpoint.
