Back to Details

prompt-creator

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<objective> Create highly effective prompts using proven techniques from Anthropic and OpenAI research. This skill covers all major prompting methodologies: clarity, structure, examples, reasoning, and advanced patterns.
Every prompt created should be clear, specific, and optimized for the target model. </objective>
<quick_start> <workflow>
  1. Clarify purpose: What should the prompt accomplish?
  2. Identify model: Claude, GPT, or other (techniques vary slightly)
  3. Select techniques: Choose from core techniques based on task complexity
  4. Structure content: Use XML tags (Claude) or markdown (GPT) for organization
  5. Add examples: Include few-shot examples for format-sensitive outputs
  6. Define success: Add clear success criteria
  7. Test and iterate: Refine based on outputs </workflow>
<core_structure> Every effective prompt has:
xml
<context>
Background information the model needs
</context>

<task>
Clear, specific instruction of what to do
</task>

<requirements>
- Specific constraints
- Output format
- Edge cases to handle
</requirements>

<examples>
Input/output pairs demonstrating expected behavior
</examples>

<success_criteria>
How to know the task was completed correctly
</success_criteria>
</core_structure> </quick_start>
<core_techniques> <technique name="be_clear_and_direct"> Priority: Always apply first
  • State exactly what you want
  • Avoid ambiguous language ("try to", "maybe", "generally")
  • Use "Always..." or "Never..." instead of "Should probably..."
  • Provide specific output format requirements
See: references/clarity-principles.md </technique>
<technique name="use_xml_tags"> **When**: Claude prompts, complex structure needed
Claude was trained with XML tags. Use them for:
  • Separating sections: 
    <context>
    , 
    <task>
    , 
    <output>
  • Wrapping data: 
    <document>
    , 
    <schema>
    , 
    <example>
  • Defining boundaries: Clear start/end of sections
See: references/xml-structure.md </technique>
<technique name="few_shot_examples"> **When**: Output format matters, pattern recognition easier than rules
Provide 2-4 input/output pairs:
xml
<examples>
<example number="1">
<input>User clicked signup button</input>
<output>track('signup_initiated', { source: 'homepage' })</output>
</example>
</examples>
See: references/few-shot-patterns.md </technique>
<technique name="chain_of_thought"> **When**: Complex reasoning, math, multi-step analysis
Add explicit reasoning instructions:
  • "Think step by step before answering"
  • "First analyze X, then consider Y, finally conclude Z"
  • Use 
    <thinking>
    tags for Claude's extended thinking
See: references/reasoning-techniques.md </technique>
<technique name="system_prompts"> **When**: Setting persistent behavior, role, constraints
System prompts set the foundation:
  • Define Claude's role and expertise
  • Set constraints and boundaries
  • Establish output format expectations
See: references/system-prompt-patterns.md </technique>
<technique name="prefilling"> **When**: Enforcing specific output format (Claude-specific)
Start Claude's response to guide format:
Assistant: {"result":
Forces JSON output without preamble. </technique>
<technique name="context_management"> **When**: Long-running tasks, multi-session work, large context usage
For Claude 4.5 with context awareness:
  • Inform about automatic context compaction
  • Add state tracking (JSON, progress.txt, git)
  • Use test-first patterns for complex implementations
  • Enable autonomous task completion across context windows
See: references/context-management.md </technique> </core_techniques>
<prompt_creation_workflow> <step_0> Gather requirements using AskUserQuestion:
  1. What is the prompt's purpose?
    • Generate content
    • Analyze/extract information
    • Transform data
    • Make decisions
    • Other
  2. What model will use this prompt?
    • Claude (use XML tags)
    • GPT (use markdown structure)
    • Other/multiple
  3. What complexity level?
    • Simple (single task, clear output)
    • Medium (multiple steps, some nuance)
    • Complex (reasoning, edge cases, validation)
  4. Output format requirements?
    • Free text
    • JSON/structured data
    • Code
    • Specific template </step_0>
<step_1> Draft the prompt using this template:
xml
<context>
[Background the model needs to understand the task]
</context>

<objective>
[Clear statement of what to accomplish]
</objective>

<instructions>
[Step-by-step process, numbered if sequential]
</instructions>

<constraints>
[Rules, limitations, things to avoid]
</constraints>

<output_format>
[Exact structure of expected output]
</output_format>

<examples>
[2-4 input/output pairs if format matters]
</examples>

<success_criteria>
[How to verify the task was done correctly]
</success_criteria>
</step_1>
<step_2> Apply relevant techniques based on complexity:
  • Simple: Clear instructions + output format
  • Medium: Add examples + constraints
  • Complex: Add reasoning steps + edge cases + validation </step_2>
<step_3> Review checklist:
  • Is the task clearly stated?
  • Are ambiguous words removed?
  • Is output format specified?
  • Are edge cases addressed?
  • Would a person with no context understand it? </step_3> </prompt_creation_workflow>
<anti_patterns> <pitfall name="vague_instructions"> ❌ "Help with the data" ✅ "Extract email addresses from the CSV, remove duplicates, output as JSON array" </pitfall>
<pitfall name="negative_prompting"> ❌ "Don't use technical jargon" ✅ "Write in plain language suitable for a non-technical audience" </pitfall> <pitfall name="no_examples"> ❌ Describing format in words only ✅ Showing 2-3 concrete input/output examples </pitfall> <pitfall name="missing_edge_cases"> ❌ "Process the file" ✅ "Process the file. If empty, return []. If malformed, return error with line number." </pitfall>
See: references/anti-patterns.md </anti_patterns>
<reference_guides> Core principles:
  • references/clarity-principles.md - Being clear and direct
  • references/xml-structure.md - Using XML tags effectively
Techniques:
  • references/few-shot-patterns.md - Example-based prompting
  • references/reasoning-techniques.md - Chain of thought, step-by-step
  • references/system-prompt-patterns.md - System prompt templates
  • references/context-management.md - Context windows, long-horizon reasoning, state tracking
Best practices by vendor:
  • references/anthropic-best-practices.md - Claude-specific techniques
  • references/openai-best-practices.md - GPT-specific techniques
Quality:
  • references/anti-patterns.md - Common mistakes to avoid
  • references/prompt-templates.md - Ready-to-use templates </reference_guides>
<success_criteria> A well-crafted prompt has:
  • Clear, unambiguous objective
  • Specific output format with example
  • Relevant context provided
  • Edge cases addressed
  • No vague language (try, maybe, generally)
  • Appropriate technique selection for task complexity
  • Success criteria defined </success_criteria>
<objective> 创建采用Anthropic和OpenAI研究验证技术的高效提示词。本技能涵盖所有主要提示词方法论：清晰性、结构化、示例、推理及高级模式。
所有生成的提示词都应清晰、具体，并针对目标模型进行优化。 </objective>
<quick_start> <workflow>
  1. 明确目标：提示词需要实现什么效果？
  2. 确定模型：Claude、GPT或其他模型（不同模型的技巧略有差异）
  3. 选择技巧：根据任务复杂度选择核心技巧
  4. 结构化内容：使用XML标签（针对Claude）或Markdown（针对GPT）进行内容组织
  5. 添加示例：对于对格式敏感的输出，添加少样本示例
  6. 定义成功标准：明确清晰的成功判定条件
  7. 测试与迭代：根据输出结果优化提示词 </workflow>
<core_structure> 每个高效提示词都包含以下结构：
xml
<context>
模型需要的背景信息
</context>

<task>
清晰、具体的任务指令
</task>

<requirements>
- 具体约束条件
- 输出格式
- 需要处理的边缘情况
</requirements>

<examples>
展示预期行为的输入/输出配对示例
</examples>

<success_criteria>
如何判断任务已正确完成
</success_criteria>
</core_structure> </quick_start>
<core_techniques> <technique name="be_clear_and_direct"> 优先级：始终首先应用
  • 明确说明你的需求
  • 避免模糊表述（如“尽量”、“也许”、“通常”）
  • 使用“必须...”或“禁止...”替代“应该可能...”
  • 提供具体的输出格式要求
参考：references/clarity-principles.md </technique>
<technique name="use_xml_tags"> **适用场景**：Claude提示词、需要复杂结构的场景
Claude是基于XML标签训练的，可将其用于：
  • 分隔内容区块：
    <context>
    、
    <task>
    、
    <output>
  • 包裹数据：
    <document>
    、
    <schema>
    、
    <example>
  • 定义边界：明确区块的开始与结束
参考：references/xml-structure.md </technique>
<technique name="few_shot_examples"> **适用场景**：输出格式重要、模式识别比规则定义更简单的场景
提供2-4组输入/输出配对示例：
xml
<examples>
<example number="1">
<input>用户点击了注册按钮</input>
<output>track('signup_initiated', { source: 'homepage' })</output>
</example>
</examples>
参考：references/few-shot-patterns.md </technique>
<technique name="chain_of_thought"> **适用场景**：复杂推理、数学计算、多步骤分析
添加明确的推理指令：
  • “在回答前逐步思考”
  • “先分析X，再考虑Y，最后得出Z结论”
  • 针对Claude使用
    <thinking>
    标签实现扩展推理
参考：references/reasoning-techniques.md </technique>
<technique name="system_prompts"> **适用场景**：设置持续行为、角色、约束条件
系统提示词是基础：
  • 定义Claude的角色与专业能力
  • 设置约束与边界
  • 明确输出格式预期
参考：references/system-prompt-patterns.md </technique>
<technique name="prefilling"> **适用场景**：强制特定输出格式（Claude专属）
通过引导Claude的响应开头来指定格式：
Assistant: {"result":
无需前缀即可强制输出JSON格式。 </technique>
<technique name="context_management"> **适用场景**：长期任务、多会话工作、大上下文使用
针对具备上下文感知能力的Claude 4.5：
  • 告知自动上下文压缩机制
  • 添加状态跟踪（JSON、progress.txt、git）
  • 针对复杂实现采用测试优先模式
  • 支持跨上下文窗口的自主任务完成
参考：references/context-management.md </technique> </core_techniques>
<prompt_creation_workflow> <step_0> 使用AskUserQuestion收集需求：
  1. 提示词的目标是什么？
    • 生成内容
    • 分析/提取信息
    • 转换数据
    • 决策制定
    • 其他
  2. 哪个模型会使用该提示词？
    • Claude（使用XML标签）
    • GPT（使用Markdown结构）
    • 其他/多个模型
  3. 任务复杂度如何？
    • 简单（单一任务、输出清晰）
    • 中等（多步骤、存在细微差别）
    • 复杂（需要推理、边缘情况、验证）
  4. 输出格式要求？
    • 自由文本
    • JSON/结构化数据
    • 代码
    • 特定模板 </step_0>
<step_1> 使用以下模板起草提示词：
xml
<context>
[模型理解任务所需的背景信息]
</context>

<objective>
[明确的任务完成目标]
</objective>

<instructions>
[分步流程，若为顺序执行则编号]
</instructions>

<constraints>
[规则、限制、需要避免的内容]
</constraints>

<output_format>
[预期输出的精确结构]
</output_format>

<examples>
[若格式重要，提供2-4组输入/输出配对示例]
</examples>

<success_criteria>
[如何验证任务已正确完成]
</success_criteria>
</step_1>
<step_2> 根据复杂度应用相关技巧：
  • 简单任务：清晰指令 + 输出格式
  • 中等任务：添加示例 + 约束条件
  • 复杂任务：添加推理步骤 + 边缘情况 + 验证机制 </step_2>
<step_3> 检查清单：
  • 任务是否明确说明？
  • 是否移除了模糊表述？
  • 是否指定了输出格式？
  • 是否处理了边缘情况？
  • 无上下文的人是否能理解该提示词？ </step_3> </prompt_creation_workflow>
<anti_patterns> <pitfall name="vague_instructions"> ❌ "帮我处理数据" ✅ "从CSV文件中提取电子邮件地址，去除重复项，以JSON数组格式输出" </pitfall>
<pitfall name="negative_prompting"> ❌ "不要使用技术术语" ✅ "使用适合非技术受众的通俗语言撰写" </pitfall> <pitfall name="no_examples"> ❌ 仅用文字描述格式 ✅ 展示2-3组具体的输入/输出示例 </pitfall> <pitfall name="missing_edge_cases"> ❌ "处理该文件" ✅ "处理该文件。若文件为空，返回[]；若格式错误，返回包含行号的错误信息。" </pitfall>
参考：references/anti-patterns.md </anti_patterns>
<reference_guides> 核心原则：
  • references/clarity-principles.md - 清晰直接原则
  • references/xml-structure.md - 有效使用XML标签
技巧：
  • references/few-shot-patterns.md - 基于示例的提示词
  • references/reasoning-techniques.md - 思维链、分步推理
  • references/system-prompt-patterns.md - 系统提示词模板
  • references/context-management.md - 上下文窗口、长期推理、状态跟踪
厂商最佳实践：
  • references/anthropic-best-practices.md - Claude专属技巧
  • references/openai-best-practices.md - GPT专属技巧
质量保障：
  • references/anti-patterns.md - 需要避免的常见错误
  • references/prompt-templates.md - 即用型模板 </reference_guides>
<success_criteria> 优质提示词具备以下特征：
  • 清晰、无歧义的目标
  • 带示例的具体输出格式
  • 提供相关上下文
  • 处理边缘情况
  • 无模糊表述（如try、maybe、generally）
  • 根据任务复杂度选择合适的技巧
  • 定义成功标准 </success_criteria>