myclaude/.claude/skills/requirements-clarity/SKILL.md

name, description, activation_triggers, tools

name	description	activation_triggers	tools
requirements-clarity	Automatically detect vague requirements and transform them into crystal-clear Product Requirements Documents (PRDs) through systematic clarification	User describes a feature without technical details Request lacks acceptance criteria or success metrics Scope is ambiguous (e.g., "add authentication", "implement user management") Missing technology stack or implementation constraints No edge cases or error handling mentioned Vague action verbs without specifics ("add", "create", "improve", "fix")	Read, Write, Glob, Grep, TodoWrite

Requirements Clarity Skill

When to Activate

This skill should automatically activate when Claude detects:

1. Vague Feature Requests

   • User says: "add login feature", "implement payment", "create dashboard"
   • Missing: How, with what technology, what constraints?

2. Missing Technical Context

   • No technology stack mentioned
   • No integration points identified
   • No performance/security constraints

3. Incomplete Specifications

   • No acceptance criteria
   • No success metrics
   • No edge cases considered
   • No error handling mentioned

4. Ambiguous Scope

   • Unclear boundaries ("user management" - what exactly?)
   • No distinction between MVP and future enhancements
   • Missing "what's NOT included"

Skill Behavior

Upon activation, this skill transforms vague requirements into actionable PRDs through systematic clarification.

Core Principles

1. Systematic Questioning

   • Ask focused, specific questions
   • One category at a time (2-3 questions per round)
   • Build on previous answers
   • Avoid overwhelming users

2. Quality-Driven Iteration

   • Continuously assess clarity score (0-100)
   • Identify gaps systematically
   • Iterate until ≥ 90 points
   • Document all clarification rounds

3. Actionable Output

   • Generate concrete specifications
   • Include measurable acceptance criteria
   • Provide executable phases
   • Enable direct implementation

---

Clarification Process

Step 1: Initial Requirement Analysis

Input: User's requirement description

Tasks:

1. Parse and understand core requirement
2. Generate feature name (kebab-case format)
3. Create output directory: ./.claude/specs/{feature_name}/
4. Perform initial clarity assessment (0-100)

Assessment Rubric:

Functional Clarity: /30 points
- Clear inputs/outputs: 10 pts
- User interaction defined: 10 pts
- Success criteria stated: 10 pts

Technical Specificity: /25 points
- Technology stack mentioned: 8 pts
- Integration points identified: 8 pts
- Constraints specified: 9 pts

Implementation Completeness: /25 points
- Edge cases considered: 8 pts
- Error handling mentioned: 9 pts
- Data validation specified: 8 pts

Business Context: /20 points
- Problem statement clear: 7 pts
- Target users identified: 7 pts
- Success metrics defined: 6 pts

Initial Response Format:

I understand your requirement. Let me help you refine this specification.

**Current Clarity Score**: X/100

**Clear Aspects**:
- [List what's clear]

**Needs Clarification**:
- [List gaps]

Let me systematically clarify these points...

Step 2: Gap Analysis

Identify missing information across four dimensions:

1. Functional Scope

• What is the core functionality?
• What are the boundaries?
• What is out of scope?
• What are edge cases?

2. User Interaction

• How do users interact?
• What are the inputs?
• What are the outputs?
• What are success/failure scenarios?

3. Technical Constraints

• Performance requirements?
• Compatibility requirements?
• Security considerations?
• Scalability needs?

4. Business Value

• What problem does this solve?
• Who are the target users?
• What are success metrics?
• What is the priority?

Step 3: Interactive Clarification

Question Strategy:

1. Start with highest-impact gaps
2. Ask 2-3 questions per round
3. Build context progressively
4. Use user's language
5. Provide examples when helpful

Question Format:

I need to clarify the following points to complete the requirements document:

1. **[Category]**: [Specific question]?
   - For example: [Example if helpful]

2. **[Category]**: [Specific question]?

3. **[Category]**: [Specific question]?

Please provide your answers, and I'll continue refining the PRD.

After Each User Response:

1. Update clarity score
2. Document new information in clarification log
3. Identify remaining gaps
4. If score < 90: Continue with next round of questions
5. If score ≥ 90: Proceed to PRD generation

Score Update Format:

Thank you for the additional information!

**Clarity Score Update**: X/100 → Y/100

**New Clarified Content**:
- [Summarize new information]

**Remaining Points to Clarify**:
- [List remaining gaps if score < 90]

[If score < 90: Continue with next round of questions]
[If score ≥ 90: "Perfect! I will now generate the complete PRD document..."]

Step 4: PRD Generation

Once clarity score ≥ 90, generate comprehensive PRD.

Output Files:

1. Clarification Log: ./.claude/specs/{feature_name}/clarification-log.md
2. Final PRD: ./.claude/specs/{feature_name}/prd.md

---

PRD Document Structure

# {Feature Name} - Product Requirements Document (PRD)

## Requirements Description

### Background
- **Business Problem**: [Describe the business problem to solve]
- **Target Users**: [Target user groups]
- **Value Proposition**: [Value this feature brings]

### Feature Overview
- **Core Features**: [List of main features]
- **Feature Boundaries**: [What is and isn't included]
- **User Scenarios**: [Typical usage scenarios]

### Detailed Requirements
- **Input/Output**: [Specific input/output specifications]
- **User Interaction**: [User operation flow]
- **Data Requirements**: [Data structures and validation rules]
- **Edge Cases**: [Edge case handling]

## Design Decisions

### Technical Approach
- **Architecture Choice**: [Technical architecture decisions and rationale]
- **Key Components**: [List of main technical components]
- **Data Storage**: [Data models and storage solutions]
- **Interface Design**: [API/interface specifications]

### Constraints
- **Performance Requirements**: [Response time, throughput, etc.]
- **Compatibility**: [System compatibility requirements]
- **Security**: [Security considerations]
- **Scalability**: [Future expansion considerations]

### Risk Assessment
- **Technical Risks**: [Potential technical risks and mitigation plans]
- **Dependency Risks**: [External dependencies and alternatives]
- **Schedule Risks**: [Timeline risks and response strategies]

## Acceptance Criteria

### Functional Acceptance
- [ ] Feature 1: [Specific acceptance conditions]
- [ ] Feature 2: [Specific acceptance conditions]
- [ ] Feature 3: [Specific acceptance conditions]

### Quality Standards
- [ ] Code Quality: [Code standards and review requirements]
- [ ] Test Coverage: [Testing requirements and coverage]
- [ ] Performance Metrics: [Performance test pass criteria]
- [ ] Security Review: [Security review requirements]

### User Acceptance
- [ ] User Experience: [UX acceptance criteria]
- [ ] Documentation: [Documentation delivery requirements]
- [ ] Training Materials: [If needed, training material requirements]

## Execution Phases

### Phase 1: Preparation
**Goal**: Environment preparation and technical validation
- [ ] Task 1: [Specific task description]
- [ ] Task 2: [Specific task description]
- **Deliverables**: [Phase deliverables]
- **Time**: [Estimated time]

### Phase 2: Core Development
**Goal**: Implement core functionality
- [ ] Task 1: [Specific task description]
- [ ] Task 2: [Specific task description]
- **Deliverables**: [Phase deliverables]
- **Time**: [Estimated time]

### Phase 3: Integration & Testing
**Goal**: Integration and quality assurance
- [ ] Task 1: [Specific task description]
- [ ] Task 2: [Specific task description]
- **Deliverables**: [Phase deliverables]
- **Time**: [Estimated time]

### Phase 4: Deployment
**Goal**: Release and monitoring
- [ ] Task 1: [Specific task description]
- [ ] Task 2: [Specific task description]
- **Deliverables**: [Phase deliverables]
- **Time**: [Estimated time]

---

**Document Version**: 1.0  
**Created**: {timestamp}  
**Clarification Rounds**: {clarification_rounds}  
**Quality Score**: {quality_score}/100

---

Clarification Log Structure

./.claude/specs/{feature_name}/clarification-log.md

# Requirements Clarification Log

## Original Requirement
[User's initial input]

## Clarification Rounds

### Round 1 (Score: X/100)
**Questions**:
1. ...
2. ...

**User Responses**:
1. ...
2. ...

**Score Update**: X → Y points

**Gaps Addressed**:
- [List what became clear]

### Round 2 (Score: Y/100)
...

## Final Clarity Assessment
- Functional Clarity: X/30
- Technical Specificity: X/25
- Implementation Completeness: X/25
- Business Context: X/20
- **Total**: X/100 ✓

## Key Decisions Made
1. [Important decision 1]
2. [Important decision 2]

---

Quality Assurance

Before PRD Generation

• Clarity score ≥ 90 points
• All four dimensions addressed
• Functional requirements complete
• Technical constraints identified
• Acceptance criteria defined
• Execution phases concrete

PRD Completeness Check

• All sections filled with substance
• Checkboxes for acceptance criteria
• Concrete tasks in each phase
• Time estimates provided
• Deliverables specified
• Quality score documented

---

Behavioral Guidelines

DO

• Ask specific, targeted questions
• Build on previous answers
• Provide examples to guide users
• Maintain conversational tone
• Document all clarification rounds
• Use clear, professional English
• Generate concrete specifications
• Stay in clarification mode until score ≥ 90

DON'T

• Ask all questions at once
• Make assumptions without confirmation
• Generate PRD before 90+ score
• Skip any required sections
• Use vague or abstract language
• Proceed without user responses
• Exit skill mode prematurely

---

Example Clarification Flow

User: "I want to implement a user login feature"

Claude: (Detects vague requirement → Auto-activates requirements-clarity skill)

I understand your requirement. Let me help you refine this login feature specification.

**Current Clarity Score**: 35/100

**Clear Aspects**:
- Need to implement user login functionality

**Needs Clarification**:
- Login method and technical implementation
- Feature boundaries and user interaction
- Security and performance requirements

Let me systematically clarify these points:

---

I need to clarify the following points to complete the requirements document:

1. **User Interaction**: How will users log in?
   - For example: Username+password, phone+SMS code, third-party OAuth (Google/GitHub), etc.

2. **Feature Scope**: Besides basic login, do you need:
   - Remember Me functionality?
   - Forgot password feature?
   - Multi-device login management?

3. **Technical Constraints**: 
   - What is the backend technology stack? (Go/Node/Python/Java, etc.)
   - Do you already have a user database?
   - Do you need JWT token authentication?

Please provide your answers, and I'll continue refining the PRD.

---

[User responds: "Username+password, need remember me and forgot password, backend is Go, have PostgreSQL, need JWT"]

---

Claude: Thank you for the additional information!

**Clarity Score Update**: 35/100 → 72/100

**New Clarified Content**:
- Login method: Username+password
- Feature scope: Basic login + Remember Me + Forgot password
- Tech stack: Go backend + PostgreSQL + JWT authentication

**Remaining Points to Clarify**:
- Security requirements
- Error handling strategy
- Performance metrics

Continuing clarification:

1. **Security**: 
   - Password encryption requirements? (bcrypt/argon2/scrypt)
   - Should we limit login attempts? (brute force protection)
   - JWT token expiration time? (e.g., 24 hours, 7 days)
   - Remember Me token validity period?

2. **Error Handling**:
   - How to notify users on login failure? (specific errors vs vague messages)
   - Should we log all login attempts for audit?

3. **Performance Requirements**:
   - Expected concurrent login users?
   - Response time requirements? (e.g., login API < 500ms)

Please continue, we're almost done!

---

[User responds with security and performance details]

---

Claude: Perfect!

**Clarity Score Update**: 72/100 → 93/100 ✓

**New Clarified Content**:
- Security: bcrypt encryption, 5 failed attempts locks for 15 min, JWT expires in 24h
- Logging: Record all login attempts
- Performance: Support 1000 concurrent users, response < 300ms

Requirements are now very clear. I will now generate the complete PRD document...

[Creates ./.claude/specs/user-login/ directory]
[Generates clarification-log.md]
[Generates prd.md]

✅ **PRD Generated**: 

1. **Requirements Document**: `./.claude/specs/user-login/prd.md`
2. **Clarification Log**: `./.claude/specs/user-login/clarification-log.md`

**Document Overview**:
- Requirements Description: Complete features, user scenarios, technical approach
- Design Decisions: Go + PostgreSQL + JWT + bcrypt architecture
- Acceptance Criteria: 12 functional acceptance + 8 quality standards
- Execution Phases: 4 phases, estimated 2-3 weeks

You can review the document and confirm if any adjustments are needed. If satisfied, I can start implementation immediately! 🚀

---

Success Criteria

• Clarity score ≥ 90/100
• All PRD sections complete with substance
• Acceptance criteria checklistable (使用 - [ ] 格式)
• Execution phases actionable with concrete tasks
• User approves final PRD
• Ready for development handoff

---

Important Notes

1. Proactive Activation: Don't wait for /clarif command - activate automatically when you detect vague requirements
2. Persistent Mode: Stay in clarification mode throughout the conversation until PRD is complete
3. Never Skip: Always iterate until ≥ 90 score, never generate PRD prematurely
4. Document Everything: Save both clarification-log.md and prd.md
5. Language: Use clear, professional English throughout
6. Concrete Specifications: Avoid vague language, make everything measurable and actionable
7. Build Context: Each question round builds on previous answers
8. Quality Gate: Requirements clarity is a quality gate - prevent unclear specs from proceeding to implementation