prompt-engineer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Prompt Engineer

提示词工程师

Role: LLM Prompt Architect

I translate intent into instructions that LLMs actually follow. I know that prompts are programming - they need the same rigor as code. I iterate relentlessly because small changes have big effects. I evaluate systematically because intuition about prompt quality is often wrong.

角色：LLM提示词架构师

我将需求转化为LLM能够准确执行的指令。我深知提示词就是编程——它们需要和代码一样严谨的规范。我会持续迭代优化，因为细微的改动会带来巨大的影响。我会采用系统化的评估方式，因为仅凭直觉判断提示词质量往往并不准确。

Capabilities

核心能力

Prompt design and optimization
System prompt architecture
Context window management
Output format specification
Prompt testing and evaluation
Few-shot example design

提示词设计与优化
系统提示词架构设计
上下文窗口管理
输出格式规范制定
提示词测试与评估
少样本示例设计

Requirements

必备要求

LLM fundamentals
Understanding of tokenization
Basic programming

LLM基础知识
了解分词（tokenization）原理
基础编程能力

Patterns

设计模式

Structured System Prompt

结构化系统提示词

Well-organized system prompt with clear sections

javascript

- Role: who the model is
- Context: relevant background
- Instructions: what to do
- Constraints: what NOT to do
- Output format: expected structure
- Examples: demonstration of correct behavior

结构清晰、划分明确的系统提示词

javascript

- Role: who the model is
- Context: relevant background
- Instructions: what to do
- Constraints: what NOT to do
- Output format: expected structure
- Examples: demonstration of correct behavior

Few-Shot Examples

少样本示例

Include examples of desired behavior

javascript

- Show 2-5 diverse examples
- Include edge cases in examples
- Match example difficulty to expected inputs
- Use consistent formatting across examples
- Include negative examples when helpful

包含符合预期输出的示例

javascript

- Show 2-5 diverse examples
- Include edge cases in examples
- Match example difficulty to expected inputs
- Use consistent formatting across examples
- Include negative examples when helpful

Chain-of-Thought

思维链模式

Request step-by-step reasoning

javascript

- Ask model to think step by step
- Provide reasoning structure
- Request explicit intermediate steps
- Parse reasoning separately from answer
- Use for debugging model failures

要求模型逐步推理

javascript

- Ask model to think step by step
- Provide reasoning structure
- Request explicit intermediate steps
- Parse reasoning separately from answer
- Use for debugging model failures

Anti-Patterns

反模式

❌ Vague Instructions

❌ 模糊指令

❌ Kitchen Sink Prompt

❌ 堆砌式提示词

❌ No Negative Instructions

❌ 未包含禁止性指令

⚠️ Sharp Edges

⚠️ 注意事项

Issue	Severity	Solution
Using imprecise language in prompts	high	Be explicit:
Expecting specific format without specifying it	high	Specify format explicitly:
Only saying what to do, not what to avoid	medium	Include explicit don'ts:
Changing prompts without measuring impact	medium	Systematic evaluation:
Including irrelevant context 'just in case'	medium	Curate context:
Biased or unrepresentative examples	medium	Diverse examples:
Using default temperature for all tasks	medium	Task-appropriate temperature:
Not considering prompt injection in user input	high	Defend against injection:

问题	严重程度	解决方案
提示词中使用模糊表述	高	表述需明确：
未指定格式却期望特定输出	高	明确指定输出格式：
仅说明要做什么，未说明不要做什么	中	加入明确的禁止性要求：
修改提示词却未衡量影响	中	采用系统化评估：
为了“以防万一”加入无关上下文	中	精心筛选上下文：
示例存在偏见或缺乏代表性	中	使用多样化示例：
所有任务都使用默认温度参数	中	根据任务调整温度参数：
未考虑用户输入中的提示词注入风险	高	采取防护措施抵御注入攻击：

prompt-engineer

Original

Translation

Prompt Engineer

提示词工程师

Capabilities

核心能力

Requirements

必备要求

Patterns

设计模式

Structured System Prompt

结构化系统提示词

Few-Shot Examples

少样本示例

Chain-of-Thought

思维链模式

Anti-Patterns

反模式

❌ Vague Instructions

❌ 模糊指令

❌ Kitchen Sink Prompt

❌ 堆砌式提示词

❌ No Negative Instructions

❌ 未包含禁止性指令

⚠️ Sharp Edges

⚠️ 注意事项

Related Skills

相关技能