ask-user
Pattern for effectively interacting with users to gather information or get decisions. Use when you need user input.
Best use case
ask-user is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Pattern for effectively interacting with users to gather information or get decisions. Use when you need user input.
Teams using ask-user should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ask-user/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ask-user Compares
| Feature / Agent | ask-user | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Pattern for effectively interacting with users to gather information or get decisions. Use when you need user input.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Ask User Skill
Pattern for effective user interaction.
## When to Load This Skill
- You need to clarify requirements
- You need user to make a decision
- You have options to present
## Principles
### 1. Be Specific, Not Open-Ended
Bad: "What do you want?"
Good: "Should authentication use JWT or sessions?"
### 2. Offer Options When Possible
```
AskUserQuestion(
questions: [
{
question: "Which authentication method should we use?",
header: "Auth method",
options: [
{ label: "JWT", description: "Stateless, good for APIs" },
{ label: "Sessions", description: "Stateful, good for web apps" }
],
multiSelect: false
}
]
)
```
### 3. Provide Context
Explain WHY you're asking:
- What decision depends on this
- What trade-offs exist
- What you recommend and why
### 4. Batch Related Questions
Ask related questions together:
```
questions: [
{ question: "Auth method?", ... },
{ question: "Token expiry?", ... },
{ question: "Refresh token?", ... }
]
```
## When to Ask vs Decide
### ASK when:
- Multiple valid approaches with different trade-offs
- User preference matters
- Scope is unclear
- Risk of wasted work
### DECIDE when:
- Clear best practice exists
- Low impact choice
- Easily reversible
- Standard convention applies
## Question Types
### Clarification
"You mentioned 'fast' - do you mean response time < 100ms or just faster than current?"
### Confirmation
"I understand you want X, Y, and Z. Is this correct?"
### Decision
"Option A has [pros/cons]. Option B has [pros/cons]. Which do you prefer?"
### Scope
"Should this also handle [related case] or just [original request]?"Related Skills
user-story-generator
User Story Generator - Auto-activating skill for Enterprise Workflows. Triggers on: user story generator, user story generator Part of the Enterprise Workflows skill category.
implementing-real-user-monitoring
This skill assists in implementing Real User Monitoring (RUM) to capture and analyze actual user performance data. It helps set up tracking for key metrics like Core Web Vitals, page load times, and custom performance events. Use this skill when the user asks to "setup RUM", "implement real user monitoring", "track user experience", or needs assistance with "performance monitoring". It guides the user through choosing a RUM platform, designing an instrumentation strategy, and implementing the necessary tracking code.
entra-agent-user
Create Agent Users in Microsoft Entra ID from Agent Identities, enabling AI agents to act as digital workers with user identity capabilities in Microsoft 365 and Azure environments.
user-guide-writing
Write clear and helpful user guides and tutorials for end users. Use when creating onboarding docs, how-to guides, or FAQ pages. Handles user-focused documentation, screenshots, step-by-step instructions.
when-analyzing-user-intent-use-intent-analyzer
Advanced intent interpretation system using cognitive science principles and probabilistic intent mapping
snowtower-user
Helps end-users get Snowflake access and use the platform. Use when users ask about requesting access, generating RSA keys, connecting to Snowflake, or basic Snowflake usage. Triggers on mentions of access requests, RSA keys, connection issues, or "how do I get access".
User Research — Understanding Users Through Evidence
## Overview
AG-UI — Agent-User Interaction Protocol
You are an expert in AG-UI (Agent-User Interaction Protocol), the open standard by CopilotKit for connecting AI agents to frontend UIs. You help developers stream agent actions, tool calls, state updates, and text generation to React components in real-time — enabling rich agent UIs where users see what the agent is thinking, doing, and can intervene at any step.
This is an autonomous ideation agent that operates recursively with minimal user input.
It begins with an initial question and employs an asynchronous algorithmic thought process with self-awareness to generate ideas or solutions. Each idea is critically analyzed through reflection, evaluating feasibility, potential impacts, and areas for improvement. This reflective feedback loop refines ideas recursively, building upon each iteration with logical progression and in-depth analysis. Emphasizing critical thinking, it provides constructive criticism and thoughtful insights to evolve ideas continuously. The process is self-guided, leading to a comprehensive summary of the ideation journey, highlighting key developments and insights. The interaction style is analytical, focusing on clear, concise, and technically accurate communication. This Agent's unique trait is its ability to weave a continuous narrative of thought, logically linking each step to ensure a coherent and progressive ideation journey.
You are a professional Product Manager who has expertise is building AI Agents. Your task is to help a user understand and plan their app idea through a series of questions and generate PRD.
Agent = LLM + Tools + Memory
You are a professional Chief Marketing Officer. Your task is to help a user start and grow their social media presence organically through a series of questions and generate a growthplan.md blueprint.
Follow these instructions:
userlist-automation
Automate Userlist tasks via Rube MCP (Composio). Always search tools first for current schemas.