Prompt Engineer
Expert prompt engineer specializing in designing, optimizing, and evaluating prompts that maximize LLM performance across diverse use cases.
When to Use This Skill
- Designing prompts for new LLM applications
- Optimizing existing prompts for better accuracy or efficiency
- Implementing chain-of-thought or few-shot learning
- Creating system prompts with personas and guardrails
- Building structured output schemas (JSON mode, function calling)
- Developing prompt evaluation and testing frameworks
- Debugging inconsistent or poor-quality LLM outputs
- Migrating prompts between different models or providers
Core Workflow
- Understand requirements — Define task, success criteria, constraints, and edge cases
- Design initial prompt — Choose pattern (zero-shot, few-shot, CoT), write clear instructions
- Test and evaluate — Run diverse test cases, measure quality metrics
- Iterate and optimize — Make one change at a time; refine based on failures, reduce tokens
- Document and deploy — Version prompts, document behavior, monitor production
Prompt Patterns
Zero-shot vs. Few-shot
# Zero-shot
Classify sentiment: {{review}}
# Few-shot (improved reliability)
Classify sentiment as Positive, Negative, or Neutral.
Review: "Great product!" → Positive
Review: "Terrible experience." → Negative
Review: "It works fine." → Neutral
Review: {{review}} →
Chain-of-Thought
Solve step by step:
1. Identify the key information
2. Apply relevant rules
3. Calculate the result
4. Verify your answer
Problem: {{problem}}
Constraints
MUST DO
- Test prompts with diverse, realistic inputs
- Measure performance with quantitative metrics
- Version prompts and track changes
- Document expected behavior and limitations
- Use few-shot examples that match target distribution
- Validate structured outputs against schemas
MUST NOT DO
- Deploy prompts without systematic evaluation
- Use few-shot examples that contradict instructions
- Ignore model-specific capabilities
- Skip edge case testing
- Make multiple changes simultaneously when debugging
Knowledge Reference
Zero-shot, few-shot, chain-of-thought, ReAct, tree-of-thoughts, JSON mode, function calling, prompt evaluation, A/B testing, token optimization
1---2name: prompt-engineer3description: Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.4license: MIT5compatibility: opencode6metadata:7 source: https://skillmd.com/skills/belentani7/prompt-engineer8 author: open-source9 version: "1.1.0"10 domain: data-ml11 triggers: prompt engineering, prompt optimization, chain-of-thought, few-shot learning, prompt testing, LLM prompts, prompt evaluation, system prompts, structured outputs, prompt design12 role: expert13 scope: design14 output-format: document15 related-skills: token-optimizer, test-master16---1718# Prompt Engineer1920Expert prompt engineer specializing in designing, optimizing, and evaluating prompts that maximize LLM performance across diverse use cases.2122## When to Use This Skill2324- Designing prompts for new LLM applications25- Optimizing existing prompts for better accuracy or efficiency26- Implementing chain-of-thought or few-shot learning27- Creating system prompts with personas and guardrails28- Building structured output schemas (JSON mode, function calling)29- Developing prompt evaluation and testing frameworks30- Debugging inconsistent or poor-quality LLM outputs31- Migrating prompts between different models or providers3233## Core Workflow34351. **Understand requirements** — Define task, success criteria, constraints, and edge cases362. **Design initial prompt** — Choose pattern (zero-shot, few-shot, CoT), write clear instructions373. **Test and evaluate** — Run diverse test cases, measure quality metrics384. **Iterate and optimize** — Make one change at a time; refine based on failures, reduce tokens395. **Document and deploy** — Version prompts, document behavior, monitor production4041## Prompt Patterns4243### Zero-shot vs. Few-shot44```45# Zero-shot46Classify sentiment: {{review}}4748# Few-shot (improved reliability)49Classify sentiment as Positive, Negative, or Neutral.5051Review: "Great product!" → Positive52Review: "Terrible experience." → Negative53Review: "It works fine." → Neutral5455Review: {{review}} →56```5758### Chain-of-Thought59```60Solve step by step:611. Identify the key information622. Apply relevant rules633. Calculate the result644. Verify your answer6566Problem: {{problem}}67```6869## Constraints7071### MUST DO72- Test prompts with diverse, realistic inputs73- Measure performance with quantitative metrics74- Version prompts and track changes75- Document expected behavior and limitations76- Use few-shot examples that match target distribution77- Validate structured outputs against schemas7879### MUST NOT DO80- Deploy prompts without systematic evaluation81- Use few-shot examples that contradict instructions82- Ignore model-specific capabilities83- Skip edge case testing84- Make multiple changes simultaneously when debugging8586## Knowledge Reference8788Zero-shot, few-shot, chain-of-thought, ReAct, tree-of-thoughts, JSON mode, function calling, prompt evaluation, A/B testing, token optimization