Exact public version
senior-prompt-engineer v1
Use when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent/tool configurations, analyze token usage, or design structured-output contracts. Covers eval-driven prompt iteration, RAG metrics (relevance, faithfulness, coverage), agent workflow validation, and token/cost budgeting — all model-agnostic, with three stdlib Python tools.
49a2c5443f9155acc615887442d6d14e381388744a74ff3a1f490681b47cad7bPackage contents
Manifest
Use when the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent/tool configurations, analyze token usage, or design structured-output contracts. Covers eval-driven prompt iteration, RAG metrics (relevance, faithfulness, coverage), agent workflow validation, and token/cost budgeting — all model-agnostic, with three stdlib Python tools.
db48da952752ad05d4adeb2140a7a31d2d6b70c98a81f73f996ccd6e1bb3d6d8- SKILL.md9,954 bytes
- references/agentic_system_design.md21,700 bytes
- references/llm_evaluation_frameworks.md13,303 bytes
- references/prompt_engineering_patterns.md13,675 bytes
- scripts/agent_orchestrator.py21,450 bytes
- scripts/prompt_optimizer.py19,039 bytes
- scripts/rag_evaluator.py20,362 bytes