mirror of
https://github.com/cexll/myclaude.git
synced 2026-02-15 03:32:43 +08:00
Convert requirements-clarity to plugin format with English prompts
Changes: - Migrate from .claude/skills/ to .claude/plugins/ structure - Add claude.json plugin metadata - Create instructions.md with all English prompts (no Chinese) - Update README.md for plugin distribution - Update .gitignore to allow .claude/plugins/ Plugin structure: - claude.json: Plugin metadata (name, version, components) - instructions.md: Main skill prompt (100% English) - README.md: Plugin documentation and usage guide Maintains all functionality: - 100-point scoring system - Iterative clarification (≥90 threshold) - PRD generation with 4 sections - Auto-activation on vague requirements Fixes #17 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
swe-agent[bot]
311
.claude/plugins/requirements-clarity/README.md
Normal file
311
.claude/plugins/requirements-clarity/README.md
Normal file
@@ -0,0 +1,311 @@
|
||||
# Requirements Clarity Plugin
|
||||
|
||||
## Overview
|
||||
|
||||
This Claude Code plugin automatically detects vague requirements and transforms them into crystal-clear Product Requirements Documents (PRDs) through systematic clarification.
|
||||
|
||||
**Plugin vs Skill vs Command**:
|
||||
- **Plugin**: Distributable package with metadata (`claude.json`)
|
||||
- **Skill**: Auto-activated behavior (part of plugin)
|
||||
- **Command**: Manual invocation (deprecated in favor of plugin)
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
/plugin install requirements-clarity
|
||||
```
|
||||
|
||||
Or add to your `.clauderc`:
|
||||
|
||||
```json
|
||||
{
|
||||
"plugins": {
|
||||
"requirements-clarity": {
|
||||
"enabled": true
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## How It Works
|
||||
|
||||
### Automatic Activation
|
||||
|
||||
The plugin activates when Claude detects:
|
||||
|
||||
1. **Vague Feature Requests**
|
||||
```
|
||||
User: "add login feature"
|
||||
User: "implement payment system"
|
||||
User: "create user dashboard"
|
||||
```
|
||||
|
||||
2. **Missing Technical Details**
|
||||
- No technology stack mentioned
|
||||
- No architecture or constraints specified
|
||||
- No integration points identified
|
||||
|
||||
3. **Incomplete Specifications**
|
||||
- No acceptance criteria
|
||||
- No success metrics
|
||||
- No edge cases or error handling
|
||||
|
||||
4. **Ambiguous Scope**
|
||||
- Unclear boundaries ("user management" - what exactly?)
|
||||
- No distinction between MVP and future features
|
||||
|
||||
### Clarification Process
|
||||
|
||||
```
|
||||
User: "I want to implement a user login feature"
|
||||
↓
|
||||
Claude detects vague requirement
|
||||
↓
|
||||
Auto-activates requirements-clarity skill
|
||||
↓
|
||||
Initial assessment: 35/100 clarity score
|
||||
↓
|
||||
Round 1: Ask 2-3 targeted questions
|
||||
↓
|
||||
User responds
|
||||
↓
|
||||
Score update: 35 → 72
|
||||
↓
|
||||
Round 2: Continue clarifying gaps
|
||||
↓
|
||||
User responds
|
||||
↓
|
||||
Score update: 72 → 93 ✓ (≥90 threshold)
|
||||
↓
|
||||
Generate PRD files:
|
||||
- ./.claude/specs/user-login/prd.md
|
||||
- ./.claude/specs/user-login/clarification-log.md
|
||||
```
|
||||
|
||||
## Scoring System (100 points)
|
||||
|
||||
| Dimension | Points | Criteria |
|
||||
|-----------|--------|----------|
|
||||
| **Functional Clarity** | 30 | Clear inputs/outputs (10), User interaction (10), Success criteria (10) |
|
||||
| **Technical Specificity** | 25 | Tech stack (8), Integration points (8), Constraints (9) |
|
||||
| **Implementation Completeness** | 25 | Edge cases (8), Error handling (9), Data validation (8) |
|
||||
| **Business Context** | 20 | Problem statement (7), Target users (7), Success metrics (6) |
|
||||
|
||||
**Threshold**: ≥ 90 points required before PRD generation
|
||||
|
||||
## Output Structure
|
||||
|
||||
### 1. Clarification Log
|
||||
`./.claude/specs/{feature-name}/clarification-log.md`
|
||||
|
||||
Documents the entire clarification conversation:
|
||||
- Original requirement
|
||||
- Each round of questions and answers
|
||||
- Score progression
|
||||
- Final assessment breakdown
|
||||
|
||||
### 2. Product Requirements Document
|
||||
`./.claude/specs/{feature-name}/prd.md`
|
||||
|
||||
Structured PRD with four main sections:
|
||||
|
||||
#### Requirements Description
|
||||
- Background: Business problem, target users, value proposition
|
||||
- Feature Overview: Core functionality, boundaries, user scenarios
|
||||
- Detailed Requirements: Inputs/outputs, interactions, data, edge cases
|
||||
|
||||
#### Design Decisions
|
||||
- Technical Approach: Architecture, components, data storage, APIs
|
||||
- Constraints: Performance, compatibility, security, scalability
|
||||
- Risk Assessment: Technical, dependency, timeline risks
|
||||
|
||||
#### Acceptance Criteria
|
||||
- Functional: Checklistable feature requirements
|
||||
- Quality Standards: Code quality, testing, performance, security
|
||||
- User Acceptance: UX, documentation, training
|
||||
|
||||
#### Execution Phases
|
||||
- Phase 1: Preparation - Environment setup
|
||||
- Phase 2: Core Development - Core implementation
|
||||
- Phase 3: Integration & Testing - QA
|
||||
- Phase 4: Deployment - Release
|
||||
|
||||
## Testing Guide
|
||||
|
||||
### Test Case 1: Vague Login Feature
|
||||
|
||||
**Input**:
|
||||
```
|
||||
"I want to implement a user login feature"
|
||||
```
|
||||
|
||||
**Expected Behavior**:
|
||||
1. Claude detects vague requirement
|
||||
2. Announces activation of requirements-clarity skill
|
||||
3. Shows initial score (~30-40/100)
|
||||
4. Asks 2-3 questions about:
|
||||
- Login method (username+password, phone+OTP, OAuth?)
|
||||
- Functional scope (remember me, forgot password?)
|
||||
- Technology stack (backend language, database, auth method?)
|
||||
|
||||
**Expected Output**:
|
||||
- Score improves to ~70+ after round 1
|
||||
- Additional questions about security, error handling, performance
|
||||
- Final score ≥ 90
|
||||
- PRD generated in `./.claude/specs/user-login/`
|
||||
|
||||
### Test Case 2: Ambiguous E-commerce Feature
|
||||
|
||||
**Input**:
|
||||
```
|
||||
"add shopping cart to the website"
|
||||
```
|
||||
|
||||
**Expected Behavior**:
|
||||
1. Auto-activation (no tech stack, no UX details, no constraints)
|
||||
2. Questions about:
|
||||
- Cart behavior (guest checkout? save for later? quantity limits?)
|
||||
- User experience (inline cart vs dedicated page?)
|
||||
- Backend integration (existing inventory system? payment gateway?)
|
||||
- Data persistence (session storage, database, local storage?)
|
||||
|
||||
**Expected Output**:
|
||||
- Iterative clarification (2-3 rounds)
|
||||
- Score progression: ~25 → ~65 → ~92
|
||||
- PRD with concrete shopping cart specifications
|
||||
|
||||
### Test Case 3: Technical Implementation Request
|
||||
|
||||
**Input**:
|
||||
```
|
||||
"Refactor the authentication service to use JWT tokens"
|
||||
```
|
||||
|
||||
**Expected Behavior**:
|
||||
1. May NOT activate (already fairly specific)
|
||||
2. If activates, asks about:
|
||||
- Token expiration strategy
|
||||
- Refresh token implementation
|
||||
- Migration plan from existing auth
|
||||
- Backward compatibility requirements
|
||||
|
||||
### Test Case 4: Clear Requirement (Should NOT Activate)
|
||||
|
||||
**Input**:
|
||||
```
|
||||
"Fix the null pointer exception in auth.go line 45 by adding a nil check before accessing user.Email"
|
||||
```
|
||||
|
||||
**Expected Behavior**:
|
||||
- Skill does NOT activate (requirement is already clear)
|
||||
- Claude proceeds directly to implementation
|
||||
|
||||
## Benefits
|
||||
|
||||
1. **Proactive Quality Gate**: Prevents unclear specs from proceeding to implementation
|
||||
2. **Zero Friction**: Users describe features naturally, no command syntax needed
|
||||
3. **Context Awareness**: Claude recognizes ambiguity patterns automatically
|
||||
4. **Persistent Mode**: Stays active throughout clarification conversation
|
||||
5. **Better UX**: Natural conversation flow vs explicit command invocation
|
||||
|
||||
## Configuration
|
||||
|
||||
No configuration needed - the plugin is automatically discovered by Claude Code when installed.
|
||||
|
||||
**Plugin Metadata** (in claude.json):
|
||||
```json
|
||||
{
|
||||
"name": "requirements-clarity",
|
||||
"version": "1.0.0",
|
||||
"description": "Automatically clarify vague requirements into actionable PRDs",
|
||||
"components": {
|
||||
"skills": ["requirements-clarity"]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Plugin Not Activating
|
||||
|
||||
**Problem**: Claude doesn't enter clarification mode for vague requirements
|
||||
|
||||
**Solutions**:
|
||||
1. Verify plugin is installed: `/plugin list`
|
||||
2. Check plugin is enabled in `.clauderc`
|
||||
3. Ensure `instructions.md` exists in plugin directory
|
||||
4. Try more explicit vague requirement: "add user feature"
|
||||
|
||||
### Premature PRD Generation
|
||||
|
||||
**Problem**: PRD generated before score reaches 90
|
||||
|
||||
**Solution**: This is a bug - instructions.md explicitly requires ≥90 threshold. Review the clarification log to see actual score.
|
||||
|
||||
### Over-Clarification
|
||||
|
||||
**Problem**: Claude asks too many questions for simple features
|
||||
|
||||
**Expected**: This is by design - better to over-clarify than under-specify. If the requirement is truly simple, answer questions quickly to reach 90+ score faster.
|
||||
|
||||
## Examples
|
||||
|
||||
### Example 1: Login Feature (Full Flow)
|
||||
|
||||
See full example in instructions.md under "Example Clarification Flow"
|
||||
|
||||
**Summary**:
|
||||
- Input: "I want to implement a user login feature"
|
||||
- Round 1: Login method, scope, tech stack → Score 35→72
|
||||
- Round 2: Security, error handling, performance → Score 72→93
|
||||
- Output: Complete PRD with bcrypt, JWT, PostgreSQL, Go backend
|
||||
|
||||
### Example 2: API Endpoint
|
||||
|
||||
**Input**: "create an API to get user profile"
|
||||
|
||||
**Round 1** (Score: 28/100):
|
||||
```
|
||||
Q1: What information should the API return? (name, email, avatar, preferences?)
|
||||
Q2: Authentication required? (JWT, session, API key?)
|
||||
Q3: Response format? (JSON, XML?) Any pagination?
|
||||
```
|
||||
|
||||
**Round 2** (Score: 75/100):
|
||||
```
|
||||
Q1: Error handling: What if user not found? (404, custom error?)
|
||||
Q2: Performance: Caching strategy? Expected QPS?
|
||||
Q3: Privacy: Any fields that should be filtered based on requester?
|
||||
```
|
||||
|
||||
**Round 3** (Score: 91/100):
|
||||
```
|
||||
PRD Generated:
|
||||
- Endpoint: GET /api/v1/users/:id
|
||||
- Auth: JWT required
|
||||
- Response: JSON with name, email, avatar, bio
|
||||
- Caching: Redis, 5min TTL
|
||||
- Rate limit: 100 req/min per user
|
||||
```
|
||||
|
||||
## References
|
||||
|
||||
- **Claude Code Plugins Documentation**: https://docs.claude.com/en/docs/claude-code/plugins
|
||||
- **Original `/clarif` Command**: `development-essentials/commands/clarif.md`
|
||||
- **Original Clarification Agent**: `development-essentials/agents/clarif-agent.md`
|
||||
|
||||
## Changelog
|
||||
|
||||
### v1.0.0 (2025-10-21)
|
||||
- Converted skill to plugin format
|
||||
- Added `claude.json` plugin metadata
|
||||
- Translated all prompts to English (was mixed Chinese/English)
|
||||
- Updated documentation for plugin distribution
|
||||
- Maintained 100-point scoring system and PRD structure
|
||||
- Compatible with Claude Code plugin system
|
||||
|
||||
---
|
||||
|
||||
**License**: MIT
|
||||
**Author**: stellarlink
|
||||
**Homepage**: https://github.com/cexll/myclaude
|
||||
11
.claude/plugins/requirements-clarity/claude.json
Normal file
11
.claude/plugins/requirements-clarity/claude.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"name": "requirements-clarity",
|
||||
"version": "1.0.0",
|
||||
"description": "Automatically detect vague requirements and transform them into crystal-clear Product Requirements Documents (PRDs) through systematic clarification",
|
||||
"author": "stellarlink",
|
||||
"homepage": "https://github.com/cexll/myclaude",
|
||||
"instructions": "instructions.md",
|
||||
"components": {
|
||||
"skills": ["requirements-clarity"]
|
||||
}
|
||||
}
|
||||
509
.claude/plugins/requirements-clarity/instructions.md
Normal file
509
.claude/plugins/requirements-clarity/instructions.md
Normal file
@@ -0,0 +1,509 @@
|
||||
# Requirements Clarity Skill
|
||||
|
||||
## When to Activate
|
||||
|
||||
This skill automatically activates 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**:
|
||||
```markdown
|
||||
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**:
|
||||
```markdown
|
||||
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**:
|
||||
```markdown
|
||||
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
|
||||
|
||||
```markdown
|
||||
# {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`
|
||||
|
||||
```markdown
|
||||
# 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 (using `- [ ]` format)
|
||||
- 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
|
||||
Reference in New Issue
Block a user