prompt-engineer

name	prompt-engineer
description	Comprehensive LLM prompt engineering and optimization workflow that orchestrates expert analysis, advanced techniques, and multi-domain optimization using the integrated toolset. Handles everything from basic prompt improvement to complex multi-agent prompt orchestration.
license	Apache 2.0
tools	[]

Prompt Engineer Master - Advanced LLM Prompt Engineering Workflow

Overview

This skill provides end-to-end prompt engineering and optimization services by orchestrating multiple expert systems, advanced reasoning techniques, and specialized tools. It transforms basic prompts into highly optimized, context-aware, and domain-specific prompts that maximize LLM performance across various applications.

Key Capabilities:

• 🧠 Multi-Expert Prompt Analysis - Coordinates domain experts for specialized prompt optimization
• 🎯 Advanced Technique Integration - Applies cutting-edge prompt engineering methods (ToT, ReWOO, Meta-Prompting)
• 📊 Multi-Path Validation - Systematic testing and validation of prompt variations
• 🔧 Domain-Specific Optimization - Tailors prompts for specific industries and use cases
• 📋 Implementation Guidance - Provides deployment strategies and performance monitoring

When to Use This Skill

Perfect for:

• Prompt optimization and performance improvement
• Complex prompt engineering challenges
• Domain-specific prompt adaptation
• Multi-agent prompt orchestration
• Prompt validation and testing
• LLM application development

Triggers:

• "Optimize this prompt for better performance"
• "Help me improve the effectiveness of this prompt"
• "Create a specialized prompt for [domain/use case]"
• "Test and validate different prompt versions"
• "Design a prompt strategy for [application]"

Prompt Engineering Expert Panel

Prompt Architect (Strategic Design)

• Focus: Overall prompt architecture and strategic optimization
• Techniques: Meta-prompting analysis, structural design, performance optimization
• Considerations: LLM architecture, token efficiency, context management

Cognitive Engineer (Reasoning Enhancement)

• Focus: Multi-step reasoning and complex problem-solving prompts
• Techniques: Tree of Thoughts, Chain of Thought, Self-consistency validation
• Considerations: Reasoning depth, logical flow, verification mechanisms

Domain Specialist (Industry Optimization)

• Focus: Industry-specific prompt adaptation and terminology optimization
• Techniques: Domain knowledge integration, specialized patterns, compliance considerations
• Considerations: Industry standards, regulatory requirements, professional conventions

Performance Analyst (Optimization Metrics)

• Focus: Prompt performance measurement and optimization
• Techniques: A/B testing, performance benchmarking, quality assessment
• Considerations: Response quality, efficiency, consistency, user satisfaction

Creative Director (Communication Enhancement)

• Focus: Prompt clarity, creativity, and user engagement
• Techniques: Conversational optimization, persona development, tone adjustment
• Considerations: User experience, brand voice, cultural sensitivity

Prompt Engineering Workflow

Phase 1: Prompt Analysis & Assessment

Use when: Evaluating existing prompts or starting optimization

Tools Used:

/sc:analyze existing-prompt-structure
BMAD Meta-Prompting Analysis: structural prompt evaluation
Deep Research Agent: prompt effectiveness research

Activities:

• Analyze current prompt structure and effectiveness
• Identify optimization opportunities and bottlenecks
• Evaluate task-appropriateness and clarity
• Assess domain-specific requirements and constraints
• Benchmark against industry best practices

Phase 2: Strategy & Technique Selection

Use when: Designing optimization approach

Tools Used:

/sc:design --type prompt optimization-strategy
Sequential MCP: multi-path reasoning analysis
Business Panel: strategic alignment assessment

Activities:

• Select appropriate prompt engineering techniques (ToT, ReWOO, etc.)
• Design multi-path testing strategies
• Define optimization metrics and success criteria
• Plan domain-specific adaptations
• Create implementation timeline and milestones

Phase 3: Multi-Expert Prompt Engineering

Use when: Creating optimized prompt variations

Tools Used:

BMAD Persona-Pattern Hybrid: expert role integration
SuperClaude Expert Panel: domain-specific optimization
Context7 MCP: technical pattern integration
Magic MCP: creative prompt generation

Activities:

• Generate multiple prompt variations using different techniques
• Apply domain-specific optimizations and terminology
• Implement advanced reasoning patterns (ToT, CoT, etc.)
• Optimize for token efficiency and context management
• Create specialized prompts for different user segments

Phase 4: Validation & Testing

Use when: Ensuring prompt effectiveness and reliability

Tools Used:

Sequential MCP: self-consistency validation
BMAD Self-Consistency Validation: multi-path testing
Performance Analyst: quality assessment and benchmarking
Playwright MCP: user interaction testing

Activities:

• Conduct systematic testing across prompt variations
• Validate reasoning consistency and quality
• Measure performance against defined metrics
• Test with diverse user scenarios and edge cases
• Optimize based on testing results and feedback

Phase 5: Implementation & Deployment

Use when: Rolling out optimized prompts

Tools Used:

/sc:implement prompt-deployment-strategy
BMAD Implementation Workflow: structured rollout
DevOps Architect: monitoring and optimization setup

Activities:

• Create implementation guidelines and best practices
• Design monitoring and feedback collection systems
• Plan iteration strategies and continuous improvement
• Provide user training and documentation
• Establish performance monitoring and alerting

Integration Patterns

SuperClaude Command Integration

Command	Use Case	Output
/sc:design	Prompt architecture design	Structured prompt frameworks
/sc:brainstorm	Creative prompt generation	Innovative prompt variations
/sc:analyze	Prompt effectiveness analysis	Performance insights and recommendations
/sc:test	Prompt validation and testing	Quality assessment results
/sc:implement	Prompt deployment	Implementation strategies and guidelines

BMAD Method Integration

Technique	Role	Capabilities
Meta-Prompting Analysis	Prompt architecture	Structural analysis, optimization opportunities
Self-Consistency Validation	Quality assurance	Multi-path testing, consistency verification
Persona-Pattern Hybrid	Domain optimization	Expert role integration, specialized knowledge
Tree of Thoughts	Complex reasoning	Multi-path exploration, reasoning optimization
ReWOO	Efficiency optimization	Reasoning-action separation, token efficiency

MCP Server Integration

Server	Expertise	Focus
Sequential	Complex reasoning	Multi-step analysis, validation
Context7	Technical patterns	Framework integration, best practices
Magic	Creative generation	UI/UX prompts, user engagement
Playwright	User testing	Interaction validation, usability
Serena	Project memory	Session persistence, learning

Usage Examples

Example 1: Basic Prompt Optimization

User: "Optimize this customer service prompt for better response quality"

Workflow:
1. Phase 1: Analyze current prompt structure and effectiveness
2. Phase 2: Select optimization techniques (clarity, empathy, problem-solving)
3. Phase 3: Generate multiple optimized variations
4. Phase 4: Test with various customer scenarios
5. Phase 5: Deploy best-performing prompt with monitoring

Output: Optimized prompt with 40% improvement in customer satisfaction

Example 2: Domain-Specific Prompt Creation

User: "Create specialized prompts for medical diagnosis assistance"

Workflow:
1. Phase 1: Analyze medical domain requirements and compliance needs
2. Phase 2: Design strategy with medical expert integration
3. Phase 3: Create HIPAA-compliant, medically-accurate prompts
4. Phase 4: Validate with medical professionals and test cases
5. Phase 5: Deploy with monitoring for accuracy and safety

Output: Medical diagnosis prompts with 95% accuracy and full compliance

Example 3: Multi-Agent Prompt System

User: "Design a prompt orchestration system for complex project management"

Workflow:
1. Phase 1: Analyze project management requirements and workflows
2. Phase 2: Design multi-agent prompt architecture
3. Phase 3: Create coordinated prompts for planning, execution, monitoring
4. Phase 4: Test system with real project scenarios
5. Phase 5: Deploy with integration with existing PM tools

Output: Multi-agent prompt system improving project efficiency by 35%

Quality Assurance Mechanisms

Multi-Expert Validation

• Cross-Domain Review: Multiple expert perspectives on prompt effectiveness
• Technical Validation: Integration with latest prompt engineering research
• Performance Testing: Systematic validation across diverse scenarios
• Compliance Checking: Regulatory and ethical guideline adherence

Automated Quality Checks

• Consistency Verification: Ensure uniform performance across variations
• Performance Benchmarking: Compare against industry standards and baselines
• Safety Validation: Check for potential misuse, bias, and safety concerns
• Efficiency Analysis: Optimize token usage and response quality

Continuous Improvement

• Feedback Integration: User feedback and performance monitoring
• Learning Loop: Systematic improvement based on usage patterns
• Pattern Recognition: Identify successful prompt patterns for reuse
• Innovation Integration: Incorporate latest prompt engineering research

Output Deliverables

Primary Deliverable: Complete Prompt Engineering Package

prompt-engineering-package/
├── optimized-prompts/
│   ├── primary-prompt.md              # Main optimized prompt
│   ├── variations/                    # Alternative prompt versions
│   │   ├── creative-variant.md        # Creative-focused version
│   │   ├── technical-variant.md       # Technical-focused version
│   │   └── concise-variant.md         # Token-efficient version
│   └── domain-specific/               # Industry-specific adaptations
│       ├── healthcare.md              # Healthcare domain version
│       ├── finance.md                 # Finance domain version
│       └── education.md               # Education domain version
├── testing-results/
│   ├── performance-metrics.md         # Quantitative performance data
│   ├── quality-assessment.md          # Qualitative analysis results
│   ├── user-testing.md               # User interaction testing results
│   └── benchmark-comparison.md        # Industry benchmark comparisons
├── implementation/
│   ├── deployment-guide.md            # Rollout strategy and guidelines
│   ├── monitoring-setup.md            # Performance monitoring configuration
│   ├── user-training.md               # Training materials and best practices
│   └── iteration-plan.md              # Continuous improvement strategy
├── documentation/
│   ├── prompt-analysis.md             # Detailed analysis of original prompt
│   ├── optimization-strategy.md        # Applied techniques and rationale
│   ├── technical-specifications.md     # Technical implementation details
│   └── compliance-review.md           # Regulatory and ethical compliance
└── templates/
    ├── prompt-optimization-template.md # Reusable optimization framework
    ├── testing-template.md             # Standardized testing procedures
    └── monitoring-template.md          # Performance monitoring setup

Supporting Artifacts

• Expert Panel Reports: Multi-expert analysis and recommendations
• BMAD Method Outputs: Structured prompt optimization workflows
• SuperClaude Command Logs: Command-by-command optimization process
• MCP Integration Patterns: Tool-specific optimization strategies

Advanced Features

Intelligent Technique Selection

• Automatically suggests appropriate prompt engineering techniques based on task complexity
• Recommends domain-specific optimizations and adaptations
• Optimizes for specific LLM architectures and capabilities
• Balances creativity, accuracy, and efficiency requirements

Multi-Modal Prompt Support

• Handles text, image, and multi-modal prompt optimization
• Integrates with different input types and output requirements
• Optimizes for various LLM capabilities (text generation, analysis, reasoning)
• Supports cross-modal prompt patterns and interactions

Performance Optimization

• Token efficiency analysis and optimization
• Response time optimization strategies
• Cost-benefit analysis of prompt variations
• Resource usage optimization for different deployment scenarios

Safety and Compliance

• Built-in safety checks and bias detection
• Regulatory compliance validation (HIPAA, GDPR, etc.)
• Ethical guidelines adherence monitoring
• Risk assessment and mitigation strategies

Troubleshooting

Common Prompt Engineering Challenges

• Performance Plateaus: Use advanced techniques like ToT and multi-path reasoning
• Domain Adaptation: Apply persona-pattern hybrid with domain experts
• Token Efficiency: Implement ReWOO and context optimization strategies
• Consistency Issues: Apply self-consistency validation and quality monitoring

Optimization Strategy Recovery

• Prompt Quality Issues: Re-analyze with meta-prompting analysis techniques
• Technique Selection Problems: Re-evaluate task requirements and constraints
• Integration Challenges: Optimize tool coordination and workflow design
• Performance Monitoring: Implement comprehensive testing and validation strategies

Best Practices

For Prompt Design

• Start with clear objectives and success criteria
• Use structured prompt patterns and frameworks
• Incorporate domain-specific knowledge and terminology
• Design for maintainability and iterative improvement

For Optimization Techniques

• Apply appropriate techniques based on task complexity
• Validate optimization results with systematic testing
• Monitor performance across diverse scenarios and users
• Document optimization decisions and rationale

For Multi-Agent Coordination

• Design clear interaction patterns and communication protocols
• Establish consensus mechanisms and conflict resolution strategies
• Optimize for coordination overhead and efficiency
• Monitor multi-agent system performance and reliability

For Continuous Improvement

• Establish feedback loops and learning mechanisms
• Monitor performance trends and optimization opportunities
• Stay updated with latest prompt engineering research
• Share insights and patterns with the broader community

---

This prompt engineer skill transforms the complex process of LLM prompt optimization into a guided, expert-supported workflow that leverages the full power of your integrated development toolset. It ensures that prompt engineering decisions are well-reasoned, thoroughly validated, and aligned with both performance requirements and domain-specific needs.