Senior Prompt Engineer
Optimize prompts, design few-shot templates, evaluate RAG and LLM outputs, and sketch agent workflows with bundled Python helpers.
Overview
Senior Prompt Engineer is an agent skill most often used in Build (also Validate and Ship) that packages prompt optimization, RAG evaluation, and agent workflow design for structured LLM features.
Install
npx skills add https://github.com/alirezarezvani/claude-skills --skill senior-prompt-engineerWhat is this skill?
- Prompt optimizer CLI with --analyze for existing prompt files
- RAG evaluator pairing contexts.json and questions.json for retrieval quality
- Agent orchestrator reads agent_config.yaml and visualizes workflows
- Documented workflows for few-shot design and structured output design
- Table-of-contents coverage: optimization, RAG, orchestration, and pattern quick reference
- 3 bundled CLI tools: prompt optimizer, RAG evaluator, agent orchestrator
Adoption & trust: 819 installs on skills.sh; 17.5k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are shipping agent features but prompts drift, RAG misses context, and nobody has a repeatable way to measure or visualize multi-step LLM workflows.
Who is it for?
Indie builders building agents, RAG assistants, or structured-output APIs who already have Python and local prompt files.
Skip if: Teams that only need a single static system prompt with no evaluation, or builders who cannot run local Python tooling.
When should I use this skill?
User asks to optimize prompts, design prompt templates, evaluate LLM outputs, build agentic systems, implement RAG, create few-shot examples, analyze token usage, or design AI workflows.
What do I get? / Deliverables
You get analyzable prompts, scored retrieval runs, and a visual agent plan—so the next implementation step can lock templates and evaluation gates before coding.
- Optimized prompt analysis
- RAG evaluation run
- Agent workflow visualization from config
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because the skill’s core deliverables are agent architectures, structured outputs, and prompt assets that ship inside products. Agent-tooling is the best fit for prompt templates, RAG evaluation, and agent orchestration visualization—not one-off app UI work.
Where it fits
Tune few-shot examples so a hackathon demo returns consistent JSON before you commit to the stack.
Run prompt_optimizer.py on production prompt files and visualize agent_config.yaml before implementing orchestration code.
Re-run rag_evaluator.py on updated embeddings or chunking to catch retrieval regressions pre-release.
Refresh marketing or support assistant prompts using the same optimization workflow after user feedback.
How it compares
Use instead of ad-hoc prompt tweaking in chat when you need scripts plus evaluation workflows tied to agent_config and context files.
Common Questions / FAQ
Who is senior-prompt-engineer for?
Solo and indie developers shipping LLM-powered agents, RAG features, or workflow automations who want optimization and evaluation patterns in-repo.
When should I use senior-prompt-engineer?
During Validate when scoping demo quality; in Build when designing prompts and agent graphs; and in Ship when re-running RAG evals or token checks before release.
Is senior-prompt-engineer safe to install?
Review the Security Audits panel on this Prism page for the ingested skills.sh signal; the skill runs local Python scripts and may read prompt or context files you point at.
SKILL.md
READMESKILL.md - Senior Prompt Engineer
# Senior Prompt Engineer Prompt engineering patterns, LLM evaluation frameworks, and agentic system design. ## Table of Contents - [Quick Start](#quick-start) - [Tools Overview](#tools-overview) - [Prompt Optimizer](#1-prompt-optimizer) - [RAG Evaluator](#2-rag-evaluator) - [Agent Orchestrator](#3-agent-orchestrator) - [Prompt Engineering Workflows](#prompt-engineering-workflows) - [Prompt Optimization Workflow](#prompt-optimization-workflow) - [Few-Shot Example Design](#few-shot-example-design-workflow) - [Structured Output Design](#structured-output-design-workflow) - [Reference Documentation](#reference-documentation) - [Common Patterns Quick Reference](#common-patterns-quick-reference) --- ## Quick Start ```bash # Analyze and optimize a prompt file python scripts/prompt_optimizer.py prompts/my_prompt.txt --analyze # Evaluate RAG retrieval quality python scripts/rag_evaluator.py --contexts contexts.json --questions questions.json # Visualize agent workflow from definition python scripts/agent_orchestrator.py agent_config.yaml --visualize ``` --- ## Tools Overview ### 1. Prompt Optimizer Analyzes prompts for token efficiency, clarity, and structure. Generates optimized versions. **Input:** Prompt text file or string **Output:** Analysis report with optimization suggestions **Usage:** ```bash # Analyze a prompt file python scripts/prompt_optimizer.py prompt.txt --analyze # Output: # Token count: 847 # Estimated cost: $0.0025 (GPT-4) # Clarity score: 72/100 # Issues found: # - Ambiguous instruction at line 3 # - Missing output format specification # - Redundant context (lines 12-15 repeat lines 5-8) # Suggestions: # 1. Add explicit output format: "Respond in JSON with keys: ..." # 2. Remove redundant context to save 89 tokens # 3. Clarify "analyze" -> "list the top 3 issues with severity ratings" # Generate optimized version python scripts/prompt_optimizer.py prompt.txt --optimize --output optimized.txt # Count tokens for cost estimation python scripts/prompt_optimizer.py prompt.txt --tokens --model gpt-4 # Extract and manage few-shot examples python scripts/prompt_optimizer.py prompt.txt --extract-examples --output examples.json ``` --- ### 2. RAG Evaluator Evaluates Retrieval-Augmented Generation quality by measuring context relevance and answer faithfulness. **Input:** Retrieved contexts (JSON) and questions/answers **Output:** Evaluation metrics and quality report **Usage:** ```bash # Evaluate retrieval quality python scripts/rag_evaluator.py --contexts retrieved.json --questions eval_set.json # Output: # === RAG Evaluation Report === # Questions evaluated: 50 # # Retrieval Metrics: # Context Relevance: 0.78 (target: >0.80) # Retrieval Precision@5: 0.72 # Coverage: 0.85 # # Generation Metrics: # Answer Faithfulness: 0.91 # Groundedness: 0.88 # # Issues Found: # - 8 questions had no relevant context in top-5 # - 3 answers contained information not in context # # Recommendations: # 1. Improve chunking strategy for technical documents # 2. Add metadata filtering for date-sensitive queries # Evaluate with custom metrics python scripts/rag_evaluator.py --contexts retrieved.json --questions eval_set.json \ --metrics relevance,faithfulness,coverage # Export detailed results python scripts/rag_evaluator.py --contexts retrieved.json --questions eval_set.json \ --output report.json --verbose ``` --- ### 3. Agent Orchestrator Parses agent definitions and visualizes execution flows. Validates tool configurations. **Input:** Agent configuration (YAML/JSON) **