Skip to main content 首页 创作者 ajbcoding claude-skill-eval moai-alfred-ask-user-questions
moai-alfred-ask-user-questions Enterprise interactive survey orchestrator with AskUserQuestion tool integration, multi-select support, conditional branching, error recovery, and production-grade decision automation across all Alfred workflows; activates for requirement clarification, architectural decisions, risky operations, feature selection, and complex multi-step user interactions
跳到安装 Skills Marketplace 发现并探索由社区构建的 Agent Skills
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/AJBcoding/claude-skill-eval --skill moai-alfred-ask-user-questions命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
下载 Zip 下载中... Enterprise-grade security expertise with production-ready patterns for OWASP Top 10 2021, zero-trust architecture, threat modeling (STRIDE, PASTA), secure SDLC, DevSecOps automation, cloud security, cryptography, identity & access management, and compliance frameworks (SOC 2, ISO 27001, GDPR, CCPA).
name moai-alfred-ask-user-questions version 4.0.0 created 2025-10-22T00:00:00.000Z updated 2025-11-12T00:00:00.000Z status stable description Enterprise interactive survey orchestrator with AskUserQuestion tool integration, multi-select support, conditional branching, error recovery, and production-grade decision automation across all Alfred workflows; activates for requirement clarification, architectural decisions, risky operations, feature selection, and complex multi-step user interactions keywords ["interactive-surveys","user-clarification","decision-making","AskUserQuestion","multi-select","conditional-flow","error-recovery","workflow-automation","enterprise-ux","production-surveys"] allowed-tools ["AskUserQuestion"]
Enterprise Interactive Survey Orchestrator v4.0.0
Skill Metadata
Field Value Skill Name moai-alfred-ask-user-questions Version 4.0.0 Enterprise (2025-11-12) Core Tool AskUserQuestion (Claude Code built-in)Auto-load When Alfred detects ambiguity in requests Tier Alfred (Workflow Orchestration) Allowed tools AskUserQuestion Lines of Content 850+, with 10+ production examples Progressive Disclosure 3-level (quick-reference, patterns, advanced)
🚀 What It Does (Enterprise Context)
Purpose : Empower Alfred sub-agents to actively conduct enterprise-grade surveys for requirement clarification, architectural decisions, and complex decision automation.
Leverages Claude Code's native AskUserQuestion tool to collect explicit, structured user input that transforms vague requests into precise specifications with guaranteed UX quality across all models.
Enterprise Capabilities :
✅ Single-select & multi-select option types (independent or dependent)
✅ 1-4 questions per survey (cognitive load optimization)
✅ 2-4 options per question with trade-off analysis
✅ Automatic "Other" option for custom input validation
✅ Conditional branching based on user answers
✅ Error recovery and retry logic
✅ Integration across all Alfred commands (Plan/Run/Sync)
✅ Multi-language support (user's configured language)
✅ Accessibility-first TUI design
✅ Reduces ambiguity → single interaction vs 3-5 iterations
🎯 When to Use (Decision Framework)
✅ MANDATORY ASK when user intent is ambiguous:
Vague noun phrases : "Add dashboard", "Refactor auth", "Improve performance"
Missing concrete specification or scope
Missing scope definition : No specification of WHERE, WHO, WHAT, HOW, WHEN
Could affect 5+ files or multiple modules
Multiple valid paths : ≥2 reasonable implementation approaches
Different trade-offs (speed vs quality, simple vs comprehensive)
Trade-off decisions : Performance vs reliability, cost vs features
No single objectively best answer
Risky operations : Destructive actions (delete, migrate, reset)
Explicit informed consent required
Architectural decisions : Technology selection, API design, database choice
Long-term impact requires clarification
❌ DON'T ask when:
User explicitly specified exact requirements
Decision is automatic (no choices, pure routing)
Single obvious path exists (no alternatives)
Quick yes/no confirmation only (keep it brief)
Information already provided in conversation
🎨 Design Principles (Enterprise Standards)
Core Principle: Certainty Over Guessing Golden Rule : When in doubt, ask the user instead of assuming.
✅ User sees exactly what you'll do → no surprises
✅ Single interaction vs 3-5 rounds of back-and-forth
✅ Fast → execute with certainty
✅ Reduces "vibe coding" frustration
✅ Builds trust through transparency
Ambiguous request detected
↓
Call AskUserQuestion({questions: [...]})
↓
User selects from clear options
↓
Proceed with confirmed specifications
🏗️ Architecture: 3-Level Progressive Disclosure
Level 1: Quick Start (Minimal Invocation) const answer = await AskUserQuestion ({
questions : [
{
question : "How should we implement this?" ,
header : "Approach" ,
multiSelect : false ,
options : [
{
label : "Option 1" ,
description : "What it does and why you'd pick it."
},
{
label : "Option 2" ,
description : "Alternative with different trade-offs."
}
]
}
]
});
Multi-Select Pattern (independent features):
const answer = await AskUserQuestion ({
questions : [
{
question : "Which features should we enable?" ,
header : "Features" ,
multiSelect : true ,
options : [
{ label : "Feature A" , description : "..." },
{ label : "Feature B" , description : "..." },
{ label : "Feature C" , description : "..." }
]
}
]
});
Level 2: Enterprise Patterns Batch Questions (related decisions):
const answer = await AskUserQuestion ({
questions : [
{
question : "Which database technology?" ,
header : "Database" ,
options : [
{ label : "PostgreSQL" , description : "Relational, ACID, mature" },
{ label : "MongoDB" , description : "Document, flexible schema" }
]
},
{
question : "Cache strategy?" ,
header : "Caching" ,
options : [
{ label : "Redis" , description : "In-memory, fast" },
{ label : "Memcached" , description : "Distributed cache" }
]
}
]
});
Conditional Flow (dependent decisions):
let questions = [
{
question : "What type of deployment?" ,
header : "Deployment Type" ,
options : [
{ label : "Docker" , description : "Containerized" },
{ label : "Kubernetes" , description : "Orchestrated" },
{ label : "Serverless" , description : "Functions-as-a-Service" }
]
}
];
const initialAnswer = await AskUserQuestion ({ questions });
if (initialAnswer["Deployment Type" ] === "Kubernetes" ) {
const kubeAnswer = await AskUserQuestion ({
questions : [
{
question : "Which cluster provider?" ,
header : "K8s Provider" ,
options : [
{ label : "AWS EKS" , description : "Amazon Elastic Kubernetes" },
{ label : "GCP GKE" , description : "Google Kubernetes Engine" },
{ label : "Self-Managed" , description : "On-premises cluster" }
]
}
]
});
}
Level 3: Advanced (Error Handling & Validation) Custom Input Validation ("Other" option):
const answer = await AskUserQuestion ({
questions : [
{
question : "Which framework?" ,
header : "Framework" ,
options : [
{ label : "React" , description : "UI library" },
{ label : "Vue" , description : "Progressive framework" },
{ label : "Other" , description : "Custom framework or library" }
]
}
]
});
if (answer["Framework" ] === "Other" ||
!VALID_FRAMEWORKS .includes (answer["Framework" ])) {
const customAnswer = validateCustomInput (answer["Framework" ]);
if (!customAnswer) {
return retryWithGuidance ();
}
}
try {
const answer = await AskUserQuestion ({...});
} catch (error) {
if (error.type === "UserCancelled" ) {
return fallbackToDefault ();
} else if (error.type === "InvalidInput" ) {
return retryWithValidation ();
}
}
Risky Operation Confirmation :
const answer = await AskUserQuestion ({
questions : [
{
question : "This will DELETE 15 branches and merge to main. Continue?" ,
header : "Destructive Op" ,
options : [
{
label : "Proceed" ,
description : "Delete branches (CANNOT BE UNDONE)"
},
{
label : "Dry Run" ,
description : "Show what would be deleted"
},
{
label : "Cancel" ,
description : "Abort entire process"
}
]
}
]
});
if (answer["Destructive Op" ] === "Proceed" ) {
const final = await AskUserQuestion ({
questions : [
{
question : "Type DELETE to confirm irreversible action:" ,
header : "Final Confirmation"
}
]
});
if (final["Final Confirmation" ] === "DELETE" ) {
executeDeletion ();
}
}
📋 Key Constraints (TUI Optimization) Constraint Reason Example 1-4 questions max Avoid user fatigue Use follow-up surveys instead 2-4 options per Q Prevent choice overload Avoid 5+ options (decision paralysis) Header ≤12 chars TUI layout fit "DB Choice" not "Which Database Technology" Label 1-5 words Quick scanning "PostgreSQL" not "SQL Database by PostgreSQL" Description required Enables informed choice Always explain trade-offs Auto "Other" option Always available System adds automatically for custom input No HTML/markdown Plain text TUI Use formatting sparingly Language matching User experience Always match configured conversation_language
🔄 Integration with Alfred Sub-agents Sub-agent When to Ask Example Trigger Questions spec-builder (/alfred:1-plan)SPEC title vague, scope undefined "Add feature" without specifics "Feature type?", "Scope?", "Users affected?" tdd-implementer (/alfred:2-run)Implementation approach unclear Multiple valid implementation paths "Architecture?", "Libraries?", "Constraints?" doc-syncer (/alfred:3-sync)Sync scope unclear Full vs partial sync decision "Full sync?", "Which files?", "Auto-commit?" qa-validator Review depth unclear Quick vs comprehensive check "Review level?", "Security focus?", "Performance?"
🎓 Top 10 Usage Patterns
Pattern 1: Feature Type Clarification Trigger : "Add dashboard feature" without specificsQuestion : "Which dashboard type: Analytics, Admin, or Profile?"Outcome : Narrowed scope → faster implementation
Pattern 2: Implementation Approach Selection Trigger : Multiple valid tech choicesQuestion : "JWT tokens, session-based, or OAuth?"Outcome : Locked architecture → deterministic development
Pattern 3: Risky Operation Confirmation Trigger : Destructive action (delete, migrate, reset)Question : "This will delete X. Proceed?" with retry confirmationOutcome : Explicit consent + audit trail
Pattern 4: Multi-Feature Selection Trigger : "Which features to enable?"Question : Multi-select of independent featuresOutcome : Precise feature set → no scope creep
Pattern 5: Sequential Conditional Decisions Trigger : Dependent choices (Q2 depends on Q1)Question : First survey → follow-up based on answerOutcome : Progressive narrowing → precise specification
Pattern 6: Technology Stack Selection Trigger : "Build with what stack?"Question : Database, cache, queue, API typeOutcome : Full stack locked → team alignment
Pattern 7: Performance vs Reliability Trigger : Trade-off between conflicting goalsQuestion : "Optimize for speed, reliability, or cost?"Outcome : Explicit requirements → informed trade-offs
Pattern 8: Custom Input Handling Trigger : "Other" option selectedQuestion : "Please describe..." with validationOutcome : Unexpected inputs handled gracefully
Pattern 9: Experience Level Calibration Trigger : Unclear target audienceQuestion : "Beginner, intermediate, or advanced?"Outcome : Content adapted to expertise level
Pattern 10: Approval Workflow Trigger : Major decision needs consensusQuestion : Multi-team approval with optionsOutcome : Documented decision with stakeholder buy-in
✅ Best Practices Summary
DO's
Be specific : "Which database type?" not "What should we use?"Provide context : Include file names, scope, or impactOrder logically : General → Specific; safest option firstFlag risks : Use "NOT RECOMMENDED" or "CAUTION:" prefixesExplain trade-offs : Mention time, resources, complexity, performanceLimit options : 2-4 per question (not 5+ for decision paralysis)Validate custom input : Check "Other" responses for validityBatch related Q's : Keep related decisions together (max 4 questions)
DON'Ts
Overuse questions : Only ask when genuinely ambiguousToo many options : 5+ options cause decision paralysisVague labels : "Option A", "Use tokens", "Option 2"Skip descriptions : User needs rationale for informed choiceHide trade-offs : Always mention implications and costsAsk for obvious : Single clear path = no question neededRecursive surveys : Avoid asking the same question twiceIgnore language : Always match user's configured conversation_language
🔗 Related Skills
moai-alfred-personas (Communication styles by user level)moai-alfred-spec-authoring (SPEC clarity & structure)moai-foundation-specs (SPEC format & requirements)moai-alfred-language-detection (Conversation language handling)
📚 Quick Reference Card Scenario Action Key Points Vague request Ask for clarification 1-4 questions max Multiple approaches Let user choose Show trade-offs clearly Risky operation Get explicit consent Require final confirmation Feature selection Use multi-select Independent options only Dependent decisions Use sequential surveys Ask follow-ups based on answers Custom input Validate carefully Re-ask if invalid Accessibility Plain text UI No complex formatting
Token Budget Optimization
Average per survey : 500-800 tokensTypical workflow : 1-2 surveys per task (1,000-1,600 tokens total)Benefit : Eliminates 3-5 clarification rounds (3,000-5,000 tokens saved)ROI : Net savings of 1,400-3,500 tokens per interaction
For detailed API specifications : reference.md For real-world examples : examples.md Last Updated : 2025-11-12Status : Production Ready (Enterprise v4.0.0)
