# Prompt Engineering

> Design prompts that produce reliable, testable, and cost-efficient model outputs. Use when building AI workflows, reducing output variance, or improving instruction adherence.

- Skill: `nikopj01/prompt-engineering` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add nikopj01/prompt-engineering`
- Raw SKILL.md: https://api.skillmd.com/api/skills/nikopj01/prompt-engineering/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: nikopj01 (https://skillmd.com/u/nikopj01)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/nikopj01/prompt-engineering

---


# Prompt Engineering

## Workflow
1. Define task objective, constraints, and success criteria explicitly.
2. Provide structured context and unambiguous output format requirements.
3. Use few-shot examples only when behavior needs anchoring.
4. Add guardrails for refusal, uncertainty, and allowed actions.
5. Evaluate outputs with fixed test cases and iterate systematically.