# System Prompt Engineering & Few-Shot Design

> Production prompt engineering techniques for Cursor rules, LLM agents, and automated code generators with high reliability and zero hallucinations.

Canonical: https://www.agentickit.co/skills/prompt-engineering
Last updated: 2026-11-18

## Key practices
- Structure system prompts with clear XML tags: <context>, <rules>, <examples>
- Provide 2-3 high-quality few-shot examples demonstrating input/output contracts
- Instruct models to think step-by-step before producing the final code or answer
- Explicitly state negative constraints (e.g. 'Do NOT use external CSS libraries')

## Related
- [ai-engineer](https://www.agentickit.co/agents/ai-engineer)
- [tech-lead](https://www.agentickit.co/agents/tech-lead)
- [/ai-feature](https://www.agentickit.co/commands/ai-feature)
- [/define-brand-voice](https://www.agentickit.co/commands/define-brand-voice)
