Prompt Engineer
This skill helps you craft optimized prompts for large language models, boosting response quality and unlocking better AI performance.
Install on your platform
We auto-selected Claude Code based on this skillβs supported platforms.
Run in terminal (recommended)
claude mcp add erichowens-prompt-engineer npx -- -y @trustedskills/erichowens-prompt-engineer
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"erichowens-prompt-engineer": {
"command": "npx",
"args": [
"-y",
"@trustedskills/erichowens-prompt-engineer"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The erichowens-prompt-engineer skill helps refine and optimize prompts for large language models. It allows users to iteratively improve their prompts, ensuring more accurate and relevant responses from AI agents. This includes techniques like prompt decomposition and restructuring to achieve desired outcomes.
When to use it
- Generating creative content: Use this skill when you need the AI agent to produce stories, poems, or scripts that require specific styles or tones.
- Complex problem-solving: Employ this skill when tackling intricate tasks where precise instructions are crucial for accurate results.
- Extracting data from text: Utilize it to refine prompts designed to pull specific information from lengthy documents or articles.
- Improving AI agent consistency: When you need the AI agent to consistently deliver responses in a particular format or style across multiple interactions.
Key capabilities
- Prompt decomposition
- Prompt restructuring
- Iterative prompt improvement
- Refining prompts for accuracy and relevance
Example prompts
- "Improve this prompt: 'Write a short story about a cat.'"
- "Decompose the following task into smaller, more manageable prompts: 'Create a marketing campaign for a new coffee shop.'"
- "Restructure this prompt to be more specific: 'Explain quantum physics.'"
Tips & gotchas
The skill works best when provided with an initial prompt that is already somewhat functional. Itβs designed to refine existing prompts rather than create them from scratch.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates β what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
π Community
Passed automated security scans.