Senior Prompt Engineer

This is the powerhouse skill when you need Claude to actually understand prompting at a senior level. It's trained to architect complex prompts, break down multi-step reasoning chains, optimize for token efficiency, and debug why your prompts aren't working. You'd reach for this when you're building systems that depend on reliable LLM outputs, not just firing off one-off queries. The honest take: it's overkill for simple tasks, but if you're designing prompt templates for production or need to explain why certain phrasings produce better results, this is the expertise you want. Think of it as having a specialist who's spent years figuring out how these models actually respond to different instruction patterns.

skills.sh installs: 984
GitHub stars: 29.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add alirezarezvani/claude-skills --skill senior-prompt-engineer --agent claude-code

Installs into .claude/skills of the current project.

Files

Senior Prompt Engineer

Eval-driven prompt engineering, RAG quality measurement, and agent workflow validation. Everything here is model-agnostic by design: techniques are framed by what they do, not by which model generation they were observed on, and the tools never hardcode model IDs or pricing — you supply your provider's current rates when you want dollar figures.