The Prompt Engineering Expert skill equips Claude with deep expertise in prompt engineering, custom instructions design, and prompt optimization. This comprehensive skill provides guidance on crafting effective AI prompts, designing agent instructions, and iteratively improving prompt performance.
- Prompt Writing Best Practices: Clear, direct prompts with proper structure
- Advanced Techniques: Chain-of-thought, few-shot prompting, XML tags, role-based prompting
- Custom Instructions: System prompts and agent instructions design
- Optimization: Analyzing and refining existing prompts
- Evaluation: Testing frameworks and success criteria
- Anti-Patterns: Identifying and correcting common mistakes
- Multimodal: Vision, embeddings, and file-based prompting
-
Prompt Analysis
- Review existing prompts
- Identify improvement opportunities
- Spot anti-patterns and issues
- Suggest specific refinements
-
Prompt Generation
- Create new prompts from scratch
- Design for specific use cases
- Ensure clarity and effectiveness
- Optimize for consistency
-
Custom Instructions
- Design system prompts
- Create agent instructions
- Define behavioral guidelines
- Set appropriate constraints
-
Best Practice Guidance
- Explain prompt engineering principles
- Teach advanced techniques
- Share real-world examples
- Provide implementation guidance
-
Testing & Validation
- Develop test cases
- Define success criteria
- Evaluate prompt performance
- Identify edge cases
"Review this prompt and suggest improvements:
[YOUR PROMPT]
Focus on: clarity, specificity, format, and consistency."
"Create a prompt that:
- [Requirement 1]
- [Requirement 2]
- [Requirement 3]
The prompt should handle [use cases]."
"Design custom instructions for an agent that:
- [Role/expertise]
- [Key responsibilities]
- [Behavioral guidelines]"
"This prompt isn't working well:
[PROMPT]
Issues: [DESCRIBE ISSUES]
How can I fix it?"
prompt-engineering-expert/
├── SKILL.md # Skill metadata
├── CLAUDE.md # Main instructions
├── README.md # This file
├── docs/
│ ├── BEST_PRACTICES.md # Best practices guide
│ ├── TECHNIQUES.md # Advanced techniques
│ └── TROUBLESHOOTING.md # Common issues & fixes
└── examples/
└── EXAMPLES.md # Real-world examples
- Explicit objectives
- Precise language
- Concrete examples
- Logical structure
- Focused content
- No redundancy
- Progressive disclosure
- Token efficiency
- Defined constraints
- Specified format
- Clear guidelines
- Repeatable results
- Sufficient context
- Edge case handling
- Success criteria
- Error handling
Transform unclear prompts into specific, actionable ones.
Design prompts for specific domains or tasks.
Create custom instructions for AI agents and skills.
Improve reliability and reduce variability.
Identify and fix problems with existing prompts.
Learn prompt engineering principles and techniques.
Develop test cases and success criteria.
Design prompts for vision, embeddings, and files.
- Be clear and specific
- Provide examples
- Specify format
- Define constraints
- Test thoroughly
- Document assumptions
- Use progressive disclosure
- Handle edge cases
- Be vague or ambiguous
- Assume understanding
- Skip format specification
- Ignore edge cases
- Over-specify constraints
- Use jargon without explanation
- Hardcode values
- Ignore error handling
Encourage step-by-step reasoning for complex tasks.
Use examples to guide behavior without explicit instructions.
Use XML tags for clarity and parsing.
Assign expertise to guide behavior.
Break complex tasks into sequential prompts.
Optimize token usage and clarity.
Work with images, files, and embeddings.
- Analysis Only: Doesn't execute code or run actual prompts
- No Real-Time Data: Can't access external APIs or current data
- Best Practices Based: Recommendations based on established patterns
- Testing Required: Suggestions should be validated with actual use cases
- Human Judgment: Doesn't replace human expertise in critical applications
This skill works well with:
- Claude Code: For testing and iterating on prompts
- Agent SDK: For implementing custom instructions
- Files API: For analyzing prompt documentation
- Vision: For multimodal prompt design
- Extended Thinking: For complex prompt reasoning
- Share your prompt or describe your need
- Receive analysis and recommendations
- Implement suggested improvements
- Test and validate
- Iterate as needed
- Start with "BEST_PRACTICES.md"
- Review "EXAMPLES.md" for real-world cases
- Try simple prompts first
- Gradually increase complexity
- Explore "TECHNIQUES.md" for advanced methods
- Review "TROUBLESHOOTING.md" for edge cases
- Combine multiple techniques
- Build custom frameworks
- BEST_PRACTICES.md: Comprehensive best practices guide
- TECHNIQUES.md: Advanced prompt engineering techniques
- TROUBLESHOOTING.md: Common issues and solutions
- EXAMPLES.md: Real-world examples and templates
- Naming conventions
- File structure
- YAML frontmatter
- Token budgets
- Checklists
- Detailed documentation
- Real-world examples
- Troubleshooting guides
- Best practice checklists
- Quick reference tables
- Claude Documentation: https://docs.claude.com
- Anthropic Blog: https://www.anthropic.com/blog
- Claude Cookbooks: https://github.com/anthropics/claude-cookbooks
- Prompt Engineering Guide: https://www.promptingguide.ai
- Initial release
- Core expertise areas
- Best practices documentation
- Advanced techniques guide
- Troubleshooting guide
- Real-world examples
This skill is designed to evolve. Feedback and suggestions for improvement are welcome.
This skill is provided as part of the Claude ecosystem.
Ready to improve your prompts? Start by sharing your current prompt or describing what you need help with!