How does this skill help reduce AI costs?

It includes a Prompt Optimizer that analyzes prompts for redundant instructions and verbose examples, providing optimized versions that use fewer tokens while maintaining performance.

Can I use this for RAG system testing?

Yes, the skill features a RAG Evaluator that measures key metrics like context relevance, answer faithfulness, and retrieval precision to ensure your RAG system is grounded and accurate.

How does it handle structured data?

It provides a dedicated Structured Output Design workflow that helps you define schemas and implement format enforcement to ensure the LLM returns reliable JSON or XML every time.

Does it support agent architectures?

Absolutely. It includes an Agent Orchestrator that validates agent configurations, visualizes execution flows (like ReAct), and identifies potential issues like infinite loops or security risks.

Senior Prompt Engineer

Name: Senior Prompt Engineer
Author: piotroq

bypiotroq

0•

数据科学与机器学习

Optimizes LLM prompts, evaluates RAG performance, and designs sophisticated agentic workflows for AI applications.

The Senior Prompt Engineer skill provides a comprehensive suite of tools and patterns for developers building production-grade AI systems. It enables Claude to perform deep analysis of prompt templates for token efficiency, evaluate Retrieval-Augmented Generation (RAG) quality using industry-standard metrics, and architect complex agentic systems using patterns like ReAct. By providing structured workflows for few-shot example design and JSON schema enforcement, this skill ensures that LLM outputs remain consistent, cost-effective, and grounded in provided context.

主要功能

01RAG evaluation metrics for context relevance and faithfulness

02Agent workflow visualization and configuration validation

03Automated prompt analysis for token efficiency and clarity

04Structured output design and JSON schema enforcement

050 GitHub stars

06Few-shot example management and validation workflows

使用场景

01Designing and debugging complex multi-step autonomous agent architectures

02Improving RAG accuracy through systematic retrieval and generation testing

03Reducing LLM API costs by optimizing prompt length and redundancy

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add piotroq/adwokat-trzebnica-html-to-php-com senior-prompt-engineer

For use in Claude.ai and ChatGPT

Download Skill