Is it compatible with multiple LLM models?

The prompt patterns and evaluation frameworks are model-agnostic, though specific scripts include cost estimation for popular models like GPT-4 and Claude.

How does this skill optimize prompt token usage?

It analyzes prompts for redundancy and ambiguity, suggesting specific instruction changes that reduce token counts while maintaining or improving response clarity.

What agent patterns are supported?

It supports common agent architectures including ReAct and Plan-Execute, providing tools for visualizing and validating workflow logic.

Does it support structured outputs?

Yes, the skill provides workflows for defining JSON schemas and implementing format enforcement to ensure reliable LLM responses.

Can I use this for RAG systems?

Yes, it includes specialized tools to measure context relevance, answer faithfulness, and retrieval precision to improve RAG performance.

Senior Prompt Engineer

Name: Senior Prompt Engineer
Author: oabdelmaksoud

byoabdelmaksoud

0•

데이터 과학 및 ML

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

The Senior Prompt Engineer skill transforms Claude into a specialized consultant for Large Language Model (LLM) operations. It provides a comprehensive framework for analyzing prompt efficiency, reducing token costs, and implementing advanced patterns like Chain-of-Thought and Few-Shot learning. Beyond simple prompting, the skill offers robust tools for evaluating Retrieval-Augmented Generation (RAG) quality and orchestrating agentic system architectures, ensuring that AI workflows are reliable, cost-effective, and performance-driven for production environments.

주요 기능

01RAG evaluation metrics for measuring context relevance and answer faithfulness

02Agentic workflow visualization and validation using ReAct and Plan-Execute patterns

03Library of advanced prompt engineering patterns including few-shot and role-framing

04Automated prompt analysis for token efficiency, clarity, and cost reduction

050 GitHub stars

06Structured output design with JSON schema enforcement and format validation

사용 사례

01Improving the accuracy and groundedness of RAG systems through retrieval benchmarking

02Building reliable multi-step agent systems with validated tool-calling logic

03Reducing AI operational costs by optimizing redundant prompt contexts and token usage

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add oabdelmaksoud/superclaw senior-prompt-engineer

For use in Claude.ai and ChatGPT

주요 기능

01RAG evaluation metrics for measuring context relevance and answer faithfulness

02Agentic workflow visualization and validation using ReAct and Plan-Execute patterns

03Library of advanced prompt engineering patterns including few-shot and role-framing

04Automated prompt analysis for token efficiency, clarity, and cost reduction

050 GitHub stars

06Structured output design with JSON schema enforcement and format validation

사용 사례

01Improving the accuracy and groundedness of RAG systems through retrieval benchmarking

02Building reliable multi-step agent systems with validated tool-calling logic

03Reducing AI operational costs by optimizing redundant prompt contexts and token usage

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add oabdelmaksoud/superclaw senior-prompt-engineer

For use in Claude.ai and ChatGPT