Senior Prompt Engineer

A practical toolkit for the actual work of prompt engineering: optimizing token usage, evaluating RAG pipelines, and validating agent configurations. The prompt optimizer analyzes clarity and cost, surfaces redundancies, and suggests structural improvements. The RAG evaluator measures context relevance and answer faithfulness with specific metrics. The agent orchestrator visualizes workflows and catches configuration issues before runtime. This is less about theory and more about the repetitive debugging work that comes up when you're tuning prompts for production, tracking down why retrieval quality dropped, or figuring out if your agent is going to loop forever. Solid for anyone who spends time staring at LLM outputs wondering why they're inconsistent.

skills.sh installs: 237
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Senior Prompt Engineer

Prompt engineering patterns, LLM evaluation frameworks, and agentic system design. Provides static (deterministic) analysis tools to optimize prompts, evaluate RAG retrieval and generation quality, and validate/visualize agent workflows — plus deep reference libraries of prompt patterns, evaluation metrics, and agent architectures.