Design, audit, and optimize prompts as task contracts with evidence, constraints, tool policy, output schemas, and evals. Use when the user asks for prompts, system instructions, prompting strategy, prompt quality, prompt optimization, RAG instructions, tool-agent instructions, or asks to avoid identity-roleplay phrasing.
Installs into .claude/skills of the current project.
Are you the author of Prompt Engineering?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/nexuslinkproductions-prompt-engineering)
---
name: prompt-engineering
description: "Design, audit, and optimize prompts as task contracts with evidence, constraints, tool policy, output schemas, and evals. Use when the user asks for prompts, system instructions, prompting strategy, prompt quality, prompt optimization, RAG instructions, tool-agent instructions, or asks to avoid identity-roleplay phrasing."
---
<!-- GENERATED:YURI-CODEX-SKILL-ADAPTER:v1 -->
# YURI skill adapter
Authoritative source: `skills/prompt-engineering/SKILL.md`
Authoritative source SHA-256: `51963b67601258075c38fe09d44bc3d469f91f2884bb8f5c68da4b17b68898f2`
Source class: `canonical`
Before acting, read the authoritative source file above completely from beginning to end. If the governed source is absent, run `node _SYSTEM/Scripts/skill-recall.mjs --show prompt-engineering` and read its complete verified output. Follow that source as the skill body; this adapter is a non-authoritative metadata-and-pointer projection.
