senior-prompt-engineer
alirezarezvani 제작
Coding Agents & IDEs요약
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM.
설명
이 스킬이 하는 일
Tools and workflows for analyzing LLM prompts, evaluating RAG pipelines, and validating agentic systems. Includes Python scripts for token counting, clarity scoring, few-shot example management, and agent workflow visualization.
Combines prompt analysis, RAG evaluation, and agent validation into a single workflow rather than requiring separate tools for each concern.
사용 시점
- Cutting token costs in a production GPT-4 prompt
- Measuring retrieval accuracy in a RAG-based Q&A system
- Validating agent tool configs before a deployment
- Building consistent few-shot examples for entity extraction
- Enforcing structured JSON output from an LLM
예시 워크플로
User asks: Optimize this customer support prompt to reduce token usage
- 1
Runs prompt_optimizer.py --analyze on the prompt file to get token count, clarity score, and identified issues
- 2
Reviews issues: redundant context, missing output format specification, ambiguous instruction verbs
- 3
Applies patterns: removes redundant lines, adds explicit JSON schema, rewrites vague verbs to concrete actions
- 4
Runs --optimize to generate the revised prompt file
- 5
Compares optimized vs baseline with --compare to show token reduction and clarity improvement
Optimized prompt file with a comparison report showing token reduction percentage and resolved issues list
설치
clawhub install alirezarezvani/senior-prompt-engineerCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.