prompt-lab

Replaces trial-and-error prompt engineering with structured methodology: objective definition, current prompt analysis, variant generation (instruction clarity, example strategies, output format specification), evaluation rubric design, test case creation, and failure mode identification.

| references/prompt-patterns.md | Prompt structure catalog: zero-shot, few-shot, CoT, persona, structured output | Always | | references/evaluation-metrics.md | Quality metrics (accuracy, format compliance, completeness), rubric design | Evaluation needed |

| references/failure-modes.md | Common prompt failure taxonomy, detection strategies, mitigations | Failure analysis requested | | references/output-constraints.md | Techniques for constraining LLM output format, JSON mode, schema enforcement | Format control needed |

系统的LLM提示工程：分析现有提示的故障模式，生成结构化变体（直接、少量、思维链），设计具有加权标准的评估标准，并生成用于比较提示性能的测试用例套件。触发条件：“提示工程”、“提示实验室”、“生成提示变体”、“A/B 测试提示”、“评估提示”、“优化提示”、“编写更好的提示”、“提示设计”、“提示迭代”、“少量示例”、“思路链提示”、“提示故障模式”、“改进此提示”。在专门设计、改进或评估 LLM 提示时使用此技能。不适用于评估 Claude Code 技能或 SKILL.md 文件 — 请使用技能评估器。 来源：mathews-tom/praxis-skills。