Can I use this to test my RAG system's accuracy?

Yes, the RAG Evaluator tool measures metrics like Answer Faithfulness and Context Relevance, helping you identify if your model is hallucinating or retrieving irrelevant data.

What is included in the prompt engineering patterns?

It includes a reference library of established patterns such as Chain-of-Thought, Few-Shot prompting, Role Framing, and Structured Output design.

How does the Prompt Optimizer reduce costs?

It analyzes your prompts for redundant context and verbose instructions, providing suggestions to shorten the prompt while maintaining intent, effectively lowering token consumption.

Does this skill support agent visualization?

The Agent Orchestrator can parse YAML/JSON agent definitions and generate ASCII or Mermaid diagrams to visualize the execution flow and tool-calling logic.

Senior Prompt Engineer

Name: Senior Prompt Engineer
Author: oabdelmaksoud

byoabdelmaksoud

0•

Ciencia de Datos y ML

Optimizes prompts, evaluates RAG performance, and designs complex agentic workflows for high-performance LLM applications.

The Senior Prompt Engineer skill equips Claude with specialized frameworks and tools for professional-grade AI development. It provides automated utilities to analyze prompt clarity and token efficiency, metrics to evaluate RAG retrieval quality (faithfulness and relevance), and an orchestrator to visualize agentic logic like ReAct patterns. Ideal for developers building production-ready AI systems, this skill streamlines the process of refining instructions, managing few-shot examples, and ensuring reliable structured outputs through schema-driven design.

Características Principales

01Systematic few-shot example management and coverage analysis

02Agentic workflow visualization and validation using Mermaid and ASCII

030 GitHub stars

04Comprehensive RAG evaluation for context relevance and answer faithfulness

05Structured output design with JSON/XML schema enforcement and validation

06Automated prompt optimization for token efficiency and instruction clarity

Casos de Uso

01Measuring and improving the accuracy of Retrieval-Augmented Generation systems

02Architecting and debugging multi-step autonomous agent workflows

03Reducing operational costs by optimizing LLM token usage in production

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

Características Principales

01Systematic few-shot example management and coverage analysis

02Agentic workflow visualization and validation using Mermaid and ASCII

030 GitHub stars

04Comprehensive RAG evaluation for context relevance and answer faithfulness

05Structured output design with JSON/XML schema enforcement and validation

06Automated prompt optimization for token efficiency and instruction clarity

Casos de Uso

01Measuring and improving the accuracy of Retrieval-Augmented Generation systems

02Architecting and debugging multi-step autonomous agent workflows

03Reducing operational costs by optimizing LLM token usage in production

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