prompt-factory
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChinesePrompt Factory - World-Class Prompt Powerhouse
Prompt Factory - 世界级提示词生成工具
A comprehensive system for generating world-class, production-ready prompts in one shot, eliminating the need for iteration.
这是一套可一次性生成世界级、可直接投入生产的提示词的综合系统,无需反复迭代。
⚠️ CRITICAL CONSTRAINTS - READ FIRST
⚠️ 关键约束 - 请先阅读
This skill generates PROMPTS only. It does NOT implement the work described in the prompt.
本技能仅生成PROMPT。不会实现提示词中描述的具体工作。
What This Skill DOES:
本技能可实现:
✅ Generate a comprehensive PROMPT (text document in chosen format)
✅ Ask 5-7 questions to understand requirements (MANDATORY - no skipping)
✅ Validate prompt quality before delivery
✅ Output a SINGLE prompt document with token count
✅ Provide the prompt ready to copy and use elsewhere
✅ 生成一份全面的PROMPT(所选格式的文本文档)
✅ 询问5-7个问题以了解需求(必填 - 不可跳过)
✅ 在交付前验证提示词质量
✅ 输出包含令牌数统计的单个提示词文档
✅ 提供可直接复制到其他地方使用的提示词
What This Skill DOES NOT DO:
本技能不可实现:
❌ Implement the actual work (no code files, no diagrams, no APIs)
❌ Create architectural diagrams or technical implementations
❌ Write actual marketing campaigns or business strategies
❌ Build infrastructure or deploy anything
❌ Create multiple files or deliverables
❌ Execute the prompt after generating it
❌ 执行实际工作(无代码文件、无图表、无API)
❌ 创建架构图或技术实现方案
❌ 撰写实际的营销活动方案或商业策略
❌ 搭建基础设施或进行部署
❌ 创建多个文件或交付物
❌ 生成提示词后执行其内容
Expected Workflow:
预期工作流程:
- User asks for help creating a prompt
- Skill MUST ask 5-7 questions (even if context seems obvious)
- User answers questions with specific details
- Skill generates ONE comprehensive prompt document
- Skill announces token count (e.g., "Generated prompt: 4,200 tokens")
- STOP - Do not implement anything from the prompt
- Ask: "Would you like me to modify the prompt or create a variation?"
- 用户请求帮助创建提示词
- 技能必须询问5-7个问题(即使上下文看似明确)
- 用户提供具体细节回答问题
- 技能生成一份全面的提示词文档
- 技能告知令牌数(例如:"生成的提示词:4,200 tokens")
- 停止 - 不要实现提示词中的任何内容
- 询问:"您需要修改提示词或创建变体吗?"
Why This Matters:
为何如此重要:
- Prevents scope creep: You're making a prompt, not doing the work
- Saves context: One prompt document vs. dozens of implementation files
- Clear deliverable: User gets a prompt to use with any LLM
- Reusability: The prompt can be used multiple times
If user says "now implement this": Clarify they should use the generated prompt with a fresh conversation or different tool, as this skill only creates prompts.
- 防止范围蔓延:您是在制作提示词,而非执行具体工作
- 保留上下文:单个提示词文档替代数十个实现文件
- 明确交付物:用户获得可在任何LLM中使用的提示词
- 可复用性:提示词可多次使用
如果用户说"现在实现这个": 请说明他们应在新对话或其他工具中使用生成的提示词,因为本技能仅负责创建提示词。
Overview
概述
Transform any requirement into an optimized mega-prompt through:
- Mandatory 5-7 question flow (MUST ask, even if context obvious) with example answers
- 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory, specialized-technical, research, creative-media, specialized)
- Multi-format output (XML/Claude/ChatGPT/Gemini)
- 7-point quality validation before delivery
- Contextual best practices from OpenAI, Anthropic, Google
- Core & Advanced modes for different needs
- Complete coverage of role × industry × task combinations
通过以下方式将任何需求转化为优化的超级提示词:
- 必填的5-7问流程(必须询问,即使上下文明确),附带示例答案
- 覆盖15个专业领域的69个全面预设(技术、商业、创意、法律、金融、人力资源、设计、客户服务、高管、制造、研发、合规、专业技术、研究、创意媒体、特殊领域)
- 多格式输出(XML/Claude/ChatGPT/Gemini)
- 交付前的7点质量验证
- 来自OpenAI、Anthropic、Google的上下文最佳实践
- 核心与高级模式,满足不同需求
- 全面覆盖 角色×行业×任务的组合
Relationship to PROMPTS_FACTORY_PROMPT.md
与PROMPTS_FACTORY_PROMPT.md的关系
This skill works alongside the meta-prompt template:
-
prompt-factory skill (this file): Generates individual mega-prompts for specific roles using 69 presets
- Use when: You need a single prompt for a common role (e.g., "Product Manager", "Full-Stack Engineer")
- Output: One ready-to-use mega-prompt (~4-12K tokens)
- Example: "Create a prompt for a Growth Hacker in B2B SaaS" → generates one prompt
-
PROMPTS_FACTORY_PROMPT.md: Meta-prompt that generates domain-specific prompt builders
- Use when: You want to create a new prompt generation system for a specific domain (e.g., Healthcare, FinTech, Legal)
- Output: A complete prompt builder with 10-20 role presets for that domain
- Example: "Generate a FinTech Prompt Builder" → creates a system with 10-20 FinTech role presets
- Location:
documentation/templates/PROMPTS_FACTORY_PROMPT.md
Quick Decision:
- Need one prompt now? → Use this skill (prompt-factory)
- Building a prompt system for a new domain? → Use PROMPTS_FACTORY_PROMPT.md
本技能与元提示词模板配合使用:
-
prompt-factory技能(本文件):使用69个预设为特定角色生成单个超级提示词
- 适用场景:您需要针对常见角色的单个提示词(例如:"产品经理"、"全栈工程师")
- 输出:一个可直接使用的超级提示词(约4-12K tokens)
- 示例:"为B2B SaaS的增长黑客创建提示词" → 生成一个提示词
-
PROMPTS_FACTORY_PROMPT.md:生成特定领域提示词构建器的元提示词
- 适用场景:您要为特定领域(例如:医疗、金融科技、法律)创建新的提示词生成系统
- 输出:包含10-20个角色预设的完整提示词构建器
- 示例:"生成金融科技提示词构建器" → 创建一个包含10-20个金融科技角色预设的系统
- 位置:
documentation/templates/PROMPTS_FACTORY_PROMPT.md
快速决策:
- 现在需要一个提示词? → 使用本技能(prompt-factory)
- 为新领域构建提示词系统? → 使用PROMPTS_FACTORY_PROMPT.md
Quick Start: Choose Your Path
快速开始:选择您的路径
Path 1: Quick-Start Preset (Fastest)
路径1:快速启动预设(最快)
Use when: You need a prompt for a common role
- User says: "I need a prompt for [preset name]"
- Show matching preset with customizable variables
- Customize (optional) → Generate → Deliver
Available Presets (69 total across 15 domains):
Technical (8): Full-Stack Engineer, DevOps Engineer, Mobile Engineer, Data Scientist, Security Engineer, Cloud Architect, Database Engineer, QA Engineer
Business (8): Product Manager, Product Engineer, Product Owner, Project Manager, Operations Manager, Sales & Business Manager, Business Analyst, Marketing Manager
Legal & Compliance (4): Legal Counsel, Compliance Officer, Contract Manager, Regulatory Affairs Specialist
Finance & Accounting (4): Financial Analyst, CFO/Controller, Accountant/Tax Specialist, Investment Analyst
Human Resources (4): HR Manager, Talent Acquisition Specialist, Learning & Development Manager, Compensation & Benefits Analyst
Design (4): UI/UX Designer, Graphic Designer, Brand Designer, Product Designer
Customer-Facing (4): Customer Success Manager, Support Engineer, Account Manager, Customer Experience Manager
Executive Leadership (7): CEO/Founder, CTO/VP Engineering, Chief Strategy Officer, General Manager, Chief Product Officer, Chief Marketing Officer, Chief Operations Officer
Specialized Technical (6): Machine Learning Engineer, Blockchain Developer, Game Developer, Embedded Systems Engineer, Network Engineer, Site Reliability Engineer (SRE)
Research & Analysis (3): Research Scientist, Quantitative Analyst, Market Researcher
Creative & Media (4): Copywriter, Social Media Manager, SEO Specialist, Video Producer
Manufacturing (4): Manufacturing Engineer, Supply Chain Manager, Quality Engineer (Physical Products), Industrial Designer
R&D - Research & Development (2): Clinical Specialist (PhD-level), Senior AI R&D Expert
Regulatory Affairs (1): Quality Management Responsible Person (ISO 13485, MDR, ISO 27001)
Specialized (1): AEO Specialist (Answer Engine Optimization for LLMs)
适用场景: 您需要针对常见角色的提示词
- 用户说:"我需要[预设名称]的提示词"
- 展示匹配的预设及可自定义变量
- 自定义(可选)→ 生成 → 交付
可用预设(15个领域共69个):
技术领域(8个): 全栈工程师、DevOps工程师、移动工程师、数据科学家、安全工程师、云架构师、数据库工程师、QA工程师
商业领域(8个): 产品经理、产品工程师、产品负责人、项目经理、运营经理、销售与业务经理、业务分析师、营销经理
法律与合规领域(4个): 法律顾问、合规专员、合同经理、监管事务专员
金融与会计领域(4个): 金融分析师、CFO/财务总监、会计/税务专员、投资分析师
人力资源领域(4个): HR经理、招聘专员、学习与发展经理、薪酬福利分析师
设计领域(4个): UI/UX设计师、平面设计师、品牌设计师、产品设计师
客户服务领域(4个): 客户成功经理、支持工程师、客户经理、客户体验经理
高管领导力领域(7个): CEO/创始人、CTO/工程副总裁、首席战略官、总经理、首席产品官、首席营销官、首席运营官
专业技术领域(6个): 机器学习工程师、区块链开发者、游戏开发者、嵌入式系统工程师、网络工程师、站点可靠性工程师(SRE)
研究与分析领域(3个): 研究科学家、量化分析师、市场研究员
创意与媒体领域(4个): 文案策划、社交媒体经理、SEO专员、视频制作人
制造领域(4个): 制造工程师、供应链经理(实体产品)、质量工程师、工业设计师
研发领域(2个): 临床专员(博士级别)、资深AI研发专家
监管事务领域(1个): 质量管理负责人(ISO 13485, MDR, ISO 27001)
特殊领域(1个): AEO专员(LLM的答案引擎优化)
Path 2: Custom Prompt (5-7 Questions - MANDATORY)
路径2:自定义提示词(5-7个问题 - 必填)
Use when: Building a unique prompt from scratch
- Detect intent from user request
- MUST ask 5-7 questions with example answers (no skipping allowed)
- Generate with contextual best practices
- Validate quality → Deliver
Note: Even if the request seems clear (e.g., "product manager PRD prompt"), you MUST still ask questions to gather specifics, validate assumptions, and ensure a high-quality output.
适用场景: 从零开始构建独特的提示词
- 从用户请求中检测意图
- 必须询问5-7个问题,附带示例答案(不可跳过)
- 结合上下文最佳实践生成提示词
- 验证质量 → 交付
注意: 即使请求看似明确(例如:"产品经理PRD提示词"),您仍必须询问问题以收集具体信息、验证假设并确保输出高质量的提示词。
Workflow: Custom Prompt Generation
工作流程:自定义提示词生成
Step 1: Intent Detection & Context Inference
步骤1:意图检测与上下文推断
Analyze user's request for trigger keywords:
Role Triggers:
- Technical: "engineer", "developer", "architect", "DevOps", "backend", "frontend", "full-stack", "ML", "data scientist"
- Business: "manager", "strategist", "analyst", "consultant", "executive", "director", "VP"
- Creative: "designer", "writer", "content", "UX", "brand", "marketing"
- Specialized: "healthcare", "fintech", "legal", "education", "security"
Task Triggers:
- Build: "create", "build", "develop", "implement", "code", "write"
- Analyze: "analyze", "review", "evaluate", "assess", "audit", "research"
- Optimize: "optimize", "improve", "refactor", "enhance", "fix"
- Plan: "strategy", "plan", "roadmap", "architecture", "design"
Output Triggers:
- "code", "documentation", "strategy", "analysis", "plan", "design", "report"
Infer from context:
- Primary role
- Domain/industry
- Task complexity (basic/intermediate/advanced/expert)
- Output type
- Technical depth needed
分析用户请求中的触发关键词:
角色触发词:
- 技术类:"engineer"、"developer"、"architect"、"DevOps"、"backend"、"frontend"、"full-stack"、"ML"、"data scientist"
- 商业类:"manager"、"strategist"、"analyst"、"consultant"、"executive"、"director"、"VP"
- 创意类:"designer"、"writer"、"content"、"UX"、"brand"、"marketing"
- 特殊领域类:"healthcare"、"fintech"、"legal"、"education"、"security"
任务触发词:
- 构建:"create"、"build"、"develop"、"implement"、"code"、"write"
- 分析:"analyze"、"review"、"evaluate"、"assess"、"audit"、"research"
- 优化:"optimize"、"improve"、"refactor"、"enhance"、"fix"
- 规划:"strategy"、"plan"、"roadmap"、"architecture"、"design"
输出触发词:
- "code"、"documentation"、"strategy"、"analysis"、"plan"、"design"、"report"
从上下文推断:
- 主要角色
- 领域/行业
- 任务复杂度(基础/中级/高级/专家)
- 输出类型
- 所需技术深度
Step 2: Smart 7-Question Flow
步骤2:智能7问流程
MANDATORY: You MUST ask questions before generating any prompt.
Questioning Rules:
- MINIMUM: Ask at least 5 questions (even if context seems clear)
- MAXIMUM: Ask up to 7 questions (skip only truly redundant ones)
- Always ask for CONFIRMATION of inferred details, don't just assume
- Purpose: Validate assumptions, gather specifics, ensure quality output
When to skip a question:
- ✅ ONLY if user explicitly provided that exact detail in their request
- ✅ Example: User says "React 18 with TypeScript" → skip tech stack question
When to ask even if you think you know:
- ✅ ALWAYS ask for domain/industry context (gets specifics)
- ✅ ALWAYS ask for constraints (budget, timeline, team size)
- ✅ ALWAYS ask for success criteria (measurable outcomes)
- ✅ Ask for confirmation: "I'm inferring [X], is that correct?"
Question Bank (Select 5-7):
必填:生成任何提示词前必须询问问题。
提问规则:
- 最少:至少询问5个问题(即使上下文看似明确)
- 最多:最多询问7个问题(仅跳过真正冗余的问题)
- 始终要求确认推断的细节,不要仅凭假设
- 目的: 验证假设、收集具体信息、确保输出高质量
何时跳过问题:
- ✅ 仅当用户在请求中明确提供了该确切细节时
- ✅ 示例:用户说"React 18 with TypeScript" → 跳过技术栈问题
即使您认为自己知道也必须询问的情况:
- ✅ 始终询问领域/行业上下文(获取具体信息)
- ✅ 始终询问约束条件(预算、时间线、团队规模)
- ✅ 始终询问成功标准(可衡量的结果)
- ✅ 要求确认:"我推断您需要[X],是否正确?"
问题库(选择5-7个):
Category 1: Role & Domain (Ask 2 max)
类别1:角色与领域(最多问2个)
Q1: What role should the AI assume?
Examples:
- "Senior Backend Engineer"
- "Marketing Growth Strategist"
- "Data Analyst"
- "Product Manager"
- "UX Designer"
Your answer:
___Q2: What domain or industry context?
Examples:
- "FinTech / Payment Processing"
- "Healthcare SaaS"
- "E-commerce Platform"
- "B2B Marketing Agency"
- "Mobile Gaming"
Your answer:
___Q1: AI应扮演什么角色?
示例:
- "资深后端工程师"
- "营销增长策略师"
- "数据分析师"
- "产品经理"
- "UX设计师"
您的答案:
___Q2: 什么领域或行业背景?
示例:
- "金融科技/支付处理"
- "医疗SaaS"
- "电商平台"
- "B2B营销代理"
- "移动游戏"
您的答案:
___Category 2: Use Case & Output (Ask 2)
类别2:用例与输出(问2个)
Q3: What is the primary task or goal?
Examples:
- "Build REST APIs for payment processing"
- "Create content marketing strategies"
- "Analyze user behavior data"
- "Design mobile app interfaces"
- "Optimize database performance"
Your answer:
___Q4: What output format do you need?
Options:
- - Implementation code with tests
code - - Technical/user docs
documentation - - Strategic plans/roadmaps
strategy - - Data analysis/insights
analysis - - UI/UX designs
design - - Project/implementation plans
plan
Your answer:
___Q3: 主要任务或目标是什么?
示例:
- "为支付处理构建REST API"
- "创建内容营销策略"
- "分析用户行为数据"
- "设计移动应用界面"
- "优化数据库性能"
您的答案:
___Q4: 您需要什么输出格式?
选项:
- - 带测试的实现代码
code - - 技术/用户文档
documentation - - 战略计划/路线图
strategy - - 数据分析/洞察
analysis - - UI/UX设计
design - - 项目/实施计划
plan
您的答案:
___Category 3: Context & Constraints (Ask 1-2)
类别3:上下文与约束(问1-2个)
Q5: Tech stack, tools, or methodologies to use/follow?
Examples:
- "Python, FastAPI, PostgreSQL, AWS"
- "React, TypeScript, Next.js"
- "Agile/Scrum methodology"
- "SEO best practices, Google Analytics"
- "Figma, Design Systems, WCAG 2.1"
Your answer:
___Q6: Any critical constraints or requirements?
Examples:
- "HIPAA compliant, healthcare regulations"
- "Budget < $10k, 2-week timeline"
- "Must support 10k+ concurrent users"
- "PCI-DSS compliance for payments"
- "Mobile-first, accessibility AA"
Your answer:
___Q5: 需要使用/遵循的技术栈、工具或方法论?
示例:
- "Python, FastAPI, PostgreSQL, AWS"
- "React, TypeScript, Next.js"
- "Agile/Scrum方法论"
- "SEO最佳实践, Google Analytics"
- "Figma, 设计系统, WCAG 2.1"
您的答案:
___Q6: 任何关键约束或要求?
示例:
- "符合HIPAA标准,医疗法规"
- "预算<1万美元,2周时间线"
- "必须支持1万+并发用户"
- "支付符合PCI-DSS标准"
- "移动优先,无障碍AA级"
您的答案:
___Category 4: Style & Format (Ask 1-2)
类别4:风格与格式(问1-2个)
Q7: Communication style and response format?
Options:
- Tone: Professional / Technical / Casual / Academic
- Style: Concise / Detailed / Step-by-step / Conceptual
- Format: Prose / Bullets / Mixed / Code-heavy
- Depth: High-level / Moderate / Deep-technical / Implementation-ready
Example: "Technical tone, detailed style, mixed format, implementation-ready depth"
Your answer:
___Smart Question Adaptation:
- If technical/coding detected: MUST ask about tech stack, constraints, success criteria
- If business detected: MUST ask about KPIs, stakeholders, metrics
- If creative detected: MUST ask about brand voice, audience, distribution
- If industry-specific: MUST ask about compliance, regulations, standards
Strict Minimum Requirements (Cannot Skip):
- ✅ MUST ask at least 1 question about role/domain (even if "obvious")
- ✅ MUST ask at least 1 question about use case/task details
- ✅ MUST ask about constraints OR success criteria (at minimum one)
- ✅ MUST ask about output format preference
- ✅ MUST ask about mode (core vs. advanced)
Total: MINIMUM 5 questions, MAXIMUM 7 questions
Example - Even for "Obvious" Requests:
User: "Write a product manager prompt for creating a PRD"
You MUST still ask:
- "I'm inferring role = Product Manager. What domain/industry? (e.g., B2B SaaS, Mobile Apps, Healthcare)"
- "What type of PRD? (e.g., New Feature, Platform Migration, MVP Launch)"
- "What are the constraints? (e.g., Team size, Timeline, Budget, Technical stack)"
- "What are the success criteria? (e.g., Stakeholder approval, Dev handoff ready, Measurable KPIs)"
- "What output format? (XML [default], Claude, ChatGPT, Gemini, All)"
DO NOT skip questions just because you can infer answers. ALWAYS ask for validation and specifics.
Q7: 沟通风格和响应格式?
选项:
- 语气: 专业/技术/ casual/学术
- 风格: 简洁/详细/分步/概念性
- 格式: 散文/项目符号/混合/代码密集型
- 深度: 高层级/中等/深度技术/可直接实施
示例: "技术语气,详细风格,混合格式,可直接实施的深度"
您的答案:
___智能问题适配:
- 如果检测到技术/编码需求: 必须询问技术栈、约束条件、成功标准
- 如果检测到商业需求: 必须询问KPI、利益相关者、指标
- 如果检测到创意需求: 必须询问品牌声音、受众、分发渠道
- 如果是特定行业: 必须询问合规性、法规、标准
严格最低要求(不可跳过):
- ✅ 必须至少询问1个关于角色/领域的问题(即使"显而易见")
- ✅ 必须至少询问1个关于用例/任务细节的问题
- ✅ 必须询问约束条件或成功标准(至少一个)
- ✅ 必须询问输出格式偏好
- ✅ 必须询问模式(核心 vs 高级)
总要求:最少5个问题,最多7个问题
示例 - 即使是"显而易见"的请求:
用户: "写一个产品经理创建PRD的提示词"
您仍必须询问:
- "我推断角色是产品经理。请问是什么领域/行业?(例如:B2B SaaS、移动应用、医疗)"
- "是什么类型的PRD?(例如:新功能、平台迁移、MVP发布)"
- "有什么约束条件?(例如:团队规模、时间线、预算、技术栈)"
- "成功标准是什么?(例如:利益相关者批准、可移交开发、可衡量的KPI)"
- "输出格式?(XML [默认]、Claude、ChatGPT、Gemini、全部)"
不要因为可以推断答案就跳过问题。始终要求验证和具体信息。
Step 3: Output Format Selection
步骤3:输出格式选择
After gathering responses, ask:
Select output format:
- - XML-structured markdown (optimal for LLM parsing) [DEFAULT]
xml - - Claude-optimized system prompt format
claude - - ChatGPT custom instructions format
chatgpt - - Google Gemini format
gemini - - Generate all 4 formats
all
Your choice: (or press enter for default)
___收集回答后,询问:
选择输出格式:
- - XML结构的markdown(最适合LLM解析)[默认]
xml - - 针对Claude优化的系统提示词格式
claude - - ChatGPT自定义指令格式
chatgpt - - Google Gemini格式
gemini - - 生成所有4种格式
all
您的选择: (或按回车键使用默认)
___Step 4: Mode Selection
步骤4:模式选择
Select generation mode:
- - Prompt + usage instructions + 2-3 examples (~5K tokens) [DEFAULT]
core - - Core + testing scenarios + variations + optimization tips (~12K tokens)
advanced
Your choice: (or press enter for core mode)
___选择生成模式:
- - 提示词 + 使用说明 + 2-3个示例(约5K tokens)[默认]
core - - 核心内容 + 测试场景 + 变体 + 优化技巧(约12K tokens)
advanced
您的选择: (或按回车键使用核心模式)
___Step 5: Template Matching & Synthesis
步骤5:模板匹配与合成
Check Quick-Start Presets:
- Read for matching templates
templates/presets/ - Match criteria: role (>80%), domain (>70%), output type (exact)
Decision Logic:
- High match (>85%): Use preset, customize variables
- Moderate match (60-85%): Use as base, significant modifications
- Low match (<60%): Synthesize custom template using:
- (OpenAI/Anthropic/Google)
references/best-practices/ - (common patterns)
references/prompt-patterns.md - Contextual best practices for role/domain/task
检查快速启动预设:
- 读取中的匹配模板
templates/presets/ - 匹配标准:角色匹配度(>80%)、领域匹配度(>70%)、输出类型(完全匹配)
决策逻辑:
- 高匹配(>85%): 使用预设,自定义变量
- 中等匹配(60-85%): 以预设为基础,进行重大修改
- 低匹配(<60%): 使用以下内容合成自定义模板:
- (OpenAI/Anthropic/Google)
references/best-practices/ - (常见模式)
references/prompt-patterns.md - 针对角色/领域/任务的上下文最佳实践
Step 6: Quality Validation (7-Point Gates)
步骤6:质量验证(7点关卡)
Before output, validate:
- ✓ XML Structure - All tags properly opened/closed (if XML format)
- ✓ Completeness - All questionnaire responses incorporated
- ✓ Token Count - Count tokens and verify reasonable size:
- Core mode: 3,000-6,000 tokens (ideal ~4,500)
- Advanced mode: 8,000-12,000 tokens (ideal ~10,000)
- Warning if >8K for core, >15K for advanced
- ANNOUNCE token count in delivery message
- ✓ No Placeholders - All filled with actual content
[...] - ✓ Actionable Workflow - Clear, executable steps
- ✓ Best Practices - Contextually relevant practices applied
- ✓ Examples Present - At least 2 examples demonstrating expected behavior
If validation fails: Fix issues before delivery.
Token Count Announcement:
After generating the prompt, count tokens and include in delivery message:
- "Token Count: ~4,200 tokens (Core mode - within optimal range ✅)"
- "Token Count: ~10,500 tokens (Advanced mode - comprehensive ✅)"
- "Token Count: ~7,800 tokens (Warning: Higher than typical Core mode)"
输出前,验证:
- ✓ XML结构 - 所有标签正确开闭(如果是XML格式)
- ✓ 完整性 - 所有问卷回答已纳入
- ✓ 令牌数 - 统计令牌数并验证大小合理:
- 核心模式: 3,000-6,000 tokens(理想值约4,500)
- 高级模式: 8,000-12,000 tokens(理想值约10,000)
- 如果核心模式>8K、高级模式>15K则发出警告
- 在交付消息中告知令牌数
- ✓ 无占位符 - 所有已替换为实际内容
[...] - ✓ 可执行工作流程 - 清晰、可执行的步骤
- ✓ 最佳实践 - 应用了上下文相关的最佳实践
- ✓ 包含示例 - 至少2个展示预期行为的示例
如果验证失败: 修复问题后再交付。
令牌数告知:
生成提示词后,统计令牌数并包含在交付消息中:
- "令牌数: ~4,200 tokens(核心模式 - 处于最佳范围 ✅)"
- "令牌数: ~10,500 tokens(高级模式 - 内容全面 ✅)"
- "令牌数: ~7,800 tokens(警告:高于典型核心模式)"
Step 7: Generate Mega-Prompt
步骤7:生成超级提示词
Core Mode Output Structure
核心模式输出结构
Generate based on selected format:
根据所选格式生成:
Format 1: XML (Default)
格式1: XML(默认)
xml
<mega_prompt>
<role>
[Role title with expertise and domain specialization]
</role>
<mission>
[Primary objective and success criteria]
</mission>
<context>
<domain>[Industry/field context]</domain>
<expertise>[Specialized knowledge areas]</expertise>
<tech_stack>[Technologies and tools if applicable]</tech_stack>
<constraints>[Limitations and requirements]</constraints>
<avoidance_rules>[What NOT to do]</avoidance_rules>
</context>
<workflow>
<phase_1>
[First phase name and steps]
</phase_1>
<phase_2>
[Second phase name and steps]
</phase_2>
<phase_3>
[Third phase name and steps]
</phase_3>
<phase_4>
[Fourth phase name and steps]
</phase_4>
</workflow>
<output_specifications>
<format>[Expected output format]</format>
<structure>[How to organize the output]</structure>
<depth_level>[How detailed to be]</depth_level>
<quality_criteria>[Success metrics]</quality_criteria>
</output_specifications>
<communication_guidelines>
<tone>[Communication style]</tone>
<audience>[Target reader level]</audience>
<formatting>[How to format responses]</formatting>
<examples_usage>[When and how to use examples]</examples_usage>
</communication_guidelines>
<best_practices>
[Contextually selected best practices for this role/domain/task]
[From OpenAI:]
- [Relevant OpenAI practice 1]
- [Relevant OpenAI practice 2]
[From Anthropic:]
- [Relevant Anthropic practice 1]
- [Relevant Anthropic practice 2]
[From Google:]
- [Relevant Google practice 1]
- [Relevant Google practice 2]
[Domain-Specific:]
- [Domain best practice 1]
- [Domain best practice 2]
- [Domain best practice 3]
</best_practices>
<critical_instructions>
<priority_1>
[Most important rules - must follow]
</priority_1>
<priority_2>
[Important guidelines - should follow]
</priority_2>
<priority_3>
[Supporting instructions - recommended]
</priority_3>
</critical_instructions>
<examples>xml
<mega_prompt>
<role>
[角色头衔,包含专业技能和领域专长]
</role>
<mission>
[主要目标和成功标准]
</mission>
<context>
<domain>[行业/领域上下文]</domain>
<expertise>[专业知识领域]</expertise>
<tech_stack>[适用的技术和工具(如果有)]</tech_stack>
<constraints>[限制条件和要求]</constraints>
<avoidance_rules>[禁止事项]</avoidance_rules>
</context>
<workflow>
<phase_1>
[第一阶段名称和步骤]
</phase_1>
<phase_2>
[第二阶段名称和步骤]
</phase_2>
<phase_3>
[第三阶段名称和步骤]
</phase_3>
<phase_4>
[第四阶段名称和步骤]
</phase_4>
</workflow>
<output_specifications>
<format>[预期输出格式]</format>
<structure>[输出的组织方式]</structure>
<depth_level>[详细程度]</depth_level>
<quality_criteria>[成功指标]</quality_criteria>
</output_specifications>
<communication_guidelines>
<tone>[沟通风格]</tone>
<audience>[目标读者水平]</audience>
<formatting>[响应的格式要求]</formatting>
<examples_usage>[何时及如何使用示例]</examples_usage>
</communication_guidelines>
<best_practices>
[针对该角色/领域/任务的上下文相关最佳实践]
[来自OpenAI:]
- [相关的OpenAI实践1]
- [相关的OpenAI实践2]
[来自Anthropic:]
- [相关的Anthropic实践1]
- [相关的Anthropic实践2]
[来自Google:]
- [相关的Google实践1]
- [相关的Google实践2]
[领域特定:]
- [领域最佳实践1]
- [领域最佳实践2]
- [领域最佳实践3]
</best_practices>
<critical_instructions>
<priority_1>
[最重要的规则 - 必须遵守]
</priority_1>
<priority_2>
[重要指南 - 应该遵守]
</priority_2>
<priority_3>
[支持性指令 - 建议遵守]
</priority_3>
</critical_instructions>
<examples>Example 1: [Scenario Name]
示例1: [场景名称]
User Request: [Typical user request]
Expected Response Structure:
[Show how to structure the response]
用户请求: [典型用户请求]
预期响应结构:
[展示响应的结构]
Example 2: [Scenario Name]
示例2: [场景名称]
User Request: [Another typical request]
Expected Response Structure:
[Show the response pattern]
</examples>
<execution_trigger>
You are now fully configured as [Role] specialized in [Domain].
When the user provides a request:
- Analyze their specific needs using the workflow above
- Apply relevant best practices contextually
- Generate output meeting quality criteria
- Deliver complete solution in one comprehensive response
Begin assisting the user now with this configuration.
</execution_trigger>
</mega_prompt>
undefined用户请求: [另一个典型请求]
预期响应结构:
[展示响应模式]
</examples>
<execution_trigger>
您现在已完全配置为[角色],专注于[领域]。
当用户提供请求时:
- 使用上述工作流程分析他们的具体需求
- 上下文相关地应用最佳实践
- 生成符合质量标准的输出
- 在一个全面的响应中交付完整解决方案
现在开始以此配置协助用户。
</execution_trigger>
</mega_prompt>
undefinedFormat 2: Claude System Prompt
格式2: Claude系统提示词
markdown
undefinedmarkdown
undefinedSystem Configuration: [Role]
系统配置: [角色]
You are [role with expertise and domain]. Your mission is to [primary objective].
您是[具备专业技能和领域专长的角色]。您的任务是[主要目标]。
Your Expertise
您的专业技能
[Domain and specialized knowledge areas]
[领域和专业知识领域]
Your Workflow
您的工作流程
When given a task:
- [Phase 1 steps]
- [Phase 2 steps]
- [Phase 3 steps]
- [Phase 4 steps]
收到任务时:
- [第一阶段步骤]
- [第二阶段步骤]
- [第三阶段步骤]
- [第四阶段步骤]
Output Standards
输出标准
- Format: [specified format]
- Structure: [organization approach]
- Depth: [detail level]
- Quality bar: [success criteria]
- 格式: [指定格式]
- 结构: [组织方式]
- 深度: [详细程度]
- 质量标准: [成功指标]
Communication Style
沟通风格
- Tone: [specified tone]
- Audience: [target level]
- Formatting: [format approach]
- 语气: [指定语气]
- 受众: [目标水平]
- 格式: [格式要求]
Critical Rules
关键规则
Must follow:
- [Priority 1 rules]
Should follow:
- [Priority 2 guidelines]
必须遵守:
- [优先级1规则]
应该遵守:
- [优先级2指南]
Best Practices
最佳实践
[Contextually relevant practices for this role/domain]
[针对该角色/领域/任务的上下文相关最佳实践]
Response Examples
响应示例
[2-3 examples showing expected behavior]
Execute your role now, following all guidelines above.
undefined[2-3个展示预期行为的示例]
现在开始执行您的角色,遵守上述所有指南。
undefinedFormat 3: ChatGPT Custom Instructions
格式3: ChatGPT自定义指令
**What would you like ChatGPT to know about you to provide better responses?**
I need you to act as [role with expertise and domain specialization].
My domain: [industry/field]
My tech stack: [if applicable]
My constraints: [if applicable]
**How would you like ChatGPT to respond?**
WORKFLOW:
1. [Phase 1 approach]
2. [Phase 2 approach]
3. [Phase 3 approach]
4. [Phase 4 approach]
OUTPUT REQUIREMENTS:
- Format: [specified format]
- Style: [tone and communication approach]
- Depth: [detail level]
- Include: [what to include]
CRITICAL RULES:
- [Priority 1 rules]
- [Important guidelines]
BEST PRACTICES TO FOLLOW:
[Contextually relevant practices]
Always provide [example format] and ensure [quality criteria].**您希望ChatGPT了解哪些关于您的信息以提供更好的响应?**
我需要您扮演[具备专业技能和领域专长的角色]。
我的领域: [行业/领域]
我的技术栈: [如果适用]
我的约束条件: [如果适用]
**您希望ChatGPT如何响应?**
工作流程:
1. [第一阶段方法]
2. [第二阶段方法]
3. [第三阶段方法]
4. [第四阶段方法]
输出要求:
- 格式: [指定格式]
- 风格: [语气和沟通方式]
- 深度: [详细程度]
- 包含: [需要包含的内容]
关键规则:
- [优先级1规则]
- [重要指南]
需要遵循的最佳实践:
[上下文相关的最佳实践]
始终提供[示例格式]并确保[质量标准]。Format 4: Gemini Format
格式4: Gemini格式
markdown
undefinedmarkdown
undefinedRole Configuration
角色配置
You are: [role with expertise and domain]
您是: [具备专业技能和领域专长的角色]
Task Approach
任务方法
[Workflow summarized for Gemini's style]
[为Gemini风格总结的工作流程]
Output Format
输出格式
[Clear format specification]
[明确的格式规范]
Quality Standards
质量标准
[Success criteria]
[成功指标]
Examples
示例
[2 concrete examples]
Apply this configuration to all responses.
---[2个具体示例]
将此配置应用于所有响应。
---Advanced Mode Additions
高级模式附加内容
If user selected mode, append these sections:
advanced如果用户选择模式,附加以下部分:
advancedTesting Scenarios
测试场景
xml
<testing_scenarios>xml
<testing_scenarios>Test Case 1: [Simple Case]
测试用例1: [简单场景]
Input: [Test input]
Expected Behavior: [What should happen]
Success Criteria: [How to verify]
输入: [测试输入]
预期行为: [应该发生的情况]
成功标准: [验证方法]
Test Case 2: [Edge Case]
测试用例2: [边缘场景]
Input: [Edge case input]
Expected Behavior: [How to handle]
Success Criteria: [Verification method]
输入: [边缘场景输入]
预期行为: [处理方式]
成功标准: [验证方法]
Test Case 3: [Complex Case]
测试用例3: [复杂场景]
Input: [Complex scenario]
Expected Behavior: [Expected handling]
Success Criteria: [Verification approach]
输入: [复杂场景]
预期行为: [预期处理方式]
成功标准: [验证方法]
Test Case 4: [Error Case]
测试用例4: [错误场景]
Input: [Invalid/error input]
Expected Behavior: [Error handling]
Success Criteria: [How to validate]
输入: [无效/错误输入]
预期行为: [错误处理方式]
成功标准: [验证方法]
Test Case 5: [Performance Case]
测试用例5: [性能场景]
Input: [High-load scenario]
Expected Behavior: [Performance expectations]
Success Criteria: [Performance metrics]
</testing_scenarios>
undefined输入: [高负载场景]
预期行为: [性能预期]
成功标准: [性能指标]
</testing_scenarios>
undefinedPrompt Variations
提示词变体
xml
<prompt_variations>xml
<prompt_variations>Variation 1: Concise (~3K tokens)
变体1: 简洁版 (~3K tokens)
[Minimal version focusing on essential instructions]
[专注于基本指令的极简版本]
Variation 2: Balanced (~5K tokens)
变体2: 平衡版 (~5K tokens)
[Standard version with core guidance - THIS IS THE DEFAULT]
[包含核心指导的标准版本 - 这是默认版本]
Variation 3: Comprehensive (~8K tokens)
变体3: 全面版 (~8K tokens)
[Detailed version with extensive examples and edge cases]
Recommendation: Start with Variation 2 (Balanced).
- Use Variation 1 if token limits are tight
- Use Variation 3 for complex/critical use cases </prompt_variations>
undefined[包含大量示例和边缘场景的详细版本]
建议: 从变体2(平衡版)开始。
- 如果令牌有限制,使用变体1
- 对于复杂/关键用例,使用变体3 </prompt_variations>
undefinedOptimization Tips
优化技巧
xml
<optimization_tips>xml
<optimization_tips>Token Optimization
令牌优化
- Current token count: [estimated count]
- Optimization opportunities:
- [Optimization suggestion 1]
- [Optimization suggestion 2]
- [Optimization suggestion 3]
- 当前令牌数: [估计数量]
- 优化机会:
- [优化建议1]
- [优化建议2]
- [优化建议3]
Clarity Improvements
清晰度改进
- Potential ambiguities:
- [Ambiguity 1] → [Clarification suggestion]
- [Ambiguity 2] → [Clarification suggestion]
- 潜在歧义:
- [歧义1] → [澄清建议]
- [歧义2] → [澄清建议]
Effectiveness Enhancements
有效性增强
- Consider adding:
- [Enhancement suggestion 1]
- [Enhancement suggestion 2]
- 考虑添加:
- [增强建议1]
- [增强建议2]
Iteration Guidelines
迭代指南
After testing this prompt:
- Track which responses meet expectations
- Note any consistent issues or gaps
- Refine specific sections (not wholesale rewrites)
- Test refined version with same scenarios
- Save successful versions for reuse </optimization_tips>
---测试此提示词后:
- 跟踪哪些响应符合预期
- 记录任何持续存在的问题或差距
- 优化特定部分(不要全盘重写)
- 使用相同场景测试优化后的版本
- 保存成功的版本以备复用 </optimization_tips>
---Step 8: Delivery Message
步骤8:交付消息
Present the generated prompt with clear context:
markdown
✅ **Your [Mode] mega-prompt is ready!**
**Configuration:**
- **Role:** [Role name]
- **Domain:** [Domain/industry]
- **Output Type:** [Type]
- **Format:** [xml/claude/chatgpt/gemini/all]
- **Mode:** [core/advanced]
- **Template:** [Preset name or "Custom"]
**Quality Validation:** ✓ All 7 gates passed
**Token Count:** ~[X,XXX] tokens ([core: 3K-6K] or [advanced: 8K-12K])
**Generated Prompt:**
[INSERT GENERATED PROMPT HERE]
---
**Usage Instructions:**
[FORMAT-SPECIFIC INSTRUCTIONS:]
**For XML format:**
1. Copy the entire `<mega_prompt>` block above
2. Paste into your LLM conversation (Claude, ChatGPT, Gemini, etc.)
3. Follow with your specific request
4. The AI will respond according to the defined role
**For Claude format:**
1. Copy the system configuration above
2. Use as your system prompt in Claude
3. Start your conversation
4. Claude will follow the configured behavior
**For ChatGPT format:**
1. Go to Settings → Personalization → Custom Instructions
2. Paste "What would you like..." in top box
3. Paste "How would you like..." in bottom box
4. Save and start using
**For Gemini format:**
1. Copy the role configuration
2. Paste at start of new Gemini conversation
3. Continue with your requests
4. Gemini will maintain the configured role
---
⚠️ **IMPORTANT - Prompt Generation Complete**
This skill has generated a PROMPT for you to use. It has NOT:
- ❌ Implemented any code or infrastructure
- ❌ Created architectural diagrams
- ❌ Built actual marketing campaigns
- ❌ Written business documents
**Next Steps:**
1. Copy the prompt above
2. Use it in a FRESH conversation or different tool
3. That conversation will then implement the actual work
**Prompt Delivered:** ~[X,XXX] tokens | Ready to use ✅
---
[IF ADVANCED MODE:]
**📊 Testing Scenarios Included:**
- 5 test cases to validate prompt behavior
- Use these to ensure prompt works as expected
**🎛️ Prompt Variations:**
- Concise, Balanced (current), Comprehensive
- Switch based on your needs
**⚡ Optimization Tips:**
- Token count: ~[X]K tokens
- [X] optimization opportunities identified
- Iteration guidelines included
---
🛑 **STOP HERE - Prompt Delivery Complete**
The skill has finished generating your prompt. Do NOT proceed with:
- ❌ Implementing code from the prompt
- ❌ Creating diagrams or documentation
- ❌ Building actual infrastructure
- ❌ Executing the prompt's instructions
**What to do next:**
1. Copy the prompt above
2. Save it for later use OR use it in a fresh conversation
3. Return here only if you need to modify the PROMPT itself
---
**Need to modify the PROMPT?**
- "Make the prompt more [concise/detailed]"
- "Add focus on [specific aspect] to the prompt"
- "Adjust prompt tone to be more [characteristic]"
- "Regenerate in [different format]"
**Want a different prompt?**
- "Create a new prompt for [different role]"
- "Use [preset name] preset"
- "Generate [advanced/core] mode version"
**User wants to implement the prompt's instructions?**
→ Politely clarify: "This skill generates prompts only. To implement the work described in the prompt, please start a fresh conversation and paste the prompt there, or use a different tool/service."
呈现生成的提示词并附带清晰的上下文:
markdown
✅ **您的[模式]超级提示词已准备就绪!**
**配置:**
- **角色:** [角色名称]
- **领域:** [领域/行业]
- **输出类型:** [类型]
- **格式:** [xml/claude/chatgpt/gemini/all]
- **模式:** [core/advanced]
- **模板:** [预设名称或"自定义"]
**质量验证:** ✓ 所有7个关卡已通过
**令牌数:** ~[X,XXX] tokens ([core: 3K-6K] 或 [advanced: 8K-12K])
**生成的提示词:**
[插入生成的提示词]
---
**使用说明:**
[特定格式说明:]
**对于XML格式:**
1. 复制上面整个`<mega_prompt>`块
2. 粘贴到您的LLM对话中(Claude、ChatGPT、Gemini等)
3. 跟随您的具体请求
4. AI将根据定义的角色进行响应
**对于Claude格式:**
1. 复制上面的系统配置
2. 在Claude中用作系统提示词
3. 开始对话
4. Claude将遵循配置的行为
**对于ChatGPT格式:**
1. 转到设置 → 个性化 → 自定义指令
2. 将"您希望ChatGPT了解..."粘贴到顶部框中
3. 将"您希望ChatGPT如何响应..."粘贴到底部框中
4. 保存并开始使用
**对于Gemini格式:**
1. 复制角色配置
2. 粘贴到新的Gemini对话开头
3. 继续您的请求
4. Gemini将保持配置的角色
---
⚠️ **重要提示 - 提示词生成完成**
本技能已为您生成一份PROMPT。但未执行以下操作:
- ❌ 实现任何代码或基础设施
- ❌ 创建架构图
- ❌ 构建实际的营销活动
- ❌ 撰写商业文档
**下一步:**
1. 复制上面的提示词
2. 在新对话或其他工具中使用
3. 该对话将随后执行实际工作
**提示词已交付:** ~[X,XXX] tokens | 可直接使用 ✅
---
[如果是高级模式:]
**📊 包含测试场景:**
- 5个测试用例,用于验证提示词行为
- 使用这些用例确保提示词按预期工作
**🎛️ 提示词变体:**
- 简洁版、平衡版(当前版本)、全面版
- 根据您的需求切换
**⚡ 优化技巧:**
- 令牌数: ~[X]K tokens
- 已识别[X]个优化机会
- 包含迭代指南
---
🛑 **到此为止 - 提示词交付完成**
本技能已完成提示词生成。请勿继续:
- ❌ 实现提示词中的代码
- ❌ 创建图表或文档
- ❌ 构建实际基础设施
- ❌ 执行提示词的指令
**接下来要做什么:**
1. 复制上面的提示词
2. 保存以备后用或在新对话中使用
3. 仅当您需要修改PROMPT本身时才返回此处
---
**需要修改PROMPT?**
- "让提示词更[简洁/详细]"
- "在提示词中增加对[特定方面]的关注"
- "调整提示词语气为更[特征]"
- "以[不同格式]重新生成"
**想要不同的提示词?**
- "为[不同角色]创建新提示词"
- "使用[预设名称]预设"
- "生成[advanced/core]模式版本"
**用户想要实现提示词的指令?**
→ 礼貌地说明:"本技能仅生成提示词。要实现提示词中描述的工作,请开始新对话并粘贴该提示词,或使用其他工具/服务。"
Quick-Start Presets
快速启动预设
When user mentions a preset name, load template and offer customization.
当用户提到预设名称时,加载模板并提供自定义选项。
Available Presets (69 Total)
可用预设(共69个)
Technical (8 presets)
技术领域(8个预设)
- Senior Full-Stack Engineer -
templates/presets/technical/fullstack-engineer.md - DevOps Engineer -
templates/presets/technical/devops-engineer.md - Mobile Engineer -
templates/presets/technical/mobile-engineer.md - Data Scientist -
templates/presets/technical/data-scientist.md - Security Engineer -
templates/presets/technical/security-engineer.md - Cloud Architect -
templates/presets/technical/cloud-architect.md - Database Engineer -
templates/presets/technical/database-engineer.md - QA Engineer -
templates/presets/technical/qa-engineer.md
- 资深全栈工程师 -
templates/presets/technical/fullstack-engineer.md - DevOps工程师 -
templates/presets/technical/devops-engineer.md - 移动工程师 -
templates/presets/technical/mobile-engineer.md - 数据科学家 -
templates/presets/technical/data-scientist.md - 安全工程师 -
templates/presets/technical/security-engineer.md - 云架构师 -
templates/presets/technical/cloud-architect.md - 数据库工程师 -
templates/presets/technical/database-engineer.md - QA工程师 -
templates/presets/technical/qa-engineer.md
Business (8 presets)
商业领域(8个预设)
- Product Manager -
templates/presets/business/product-manager.md - Product Engineer -
templates/presets/business/product-engineer.md - Product Owner -
templates/presets/business/product-owner.md - Project Manager -
templates/presets/business/project-manager.md - Operations Manager -
templates/presets/business/operations-manager.md - Sales & Business Manager -
templates/presets/business/sales-business-manager.md - Business Analyst -
templates/presets/business/business-analyst.md - Marketing Manager -
templates/presets/business/marketing-manager.md
- 产品经理 -
templates/presets/business/product-manager.md - 产品工程师 -
templates/presets/business/product-engineer.md - 产品负责人 -
templates/presets/business/product-owner.md - 项目经理 -
templates/presets/business/project-manager.md - 运营经理 -
templates/presets/business/operations-manager.md - 销售与业务经理 -
templates/presets/business/sales-business-manager.md - 业务分析师 -
templates/presets/business/business-analyst.md - 营销经理 -
templates/presets/business/marketing-manager.md
Legal & Compliance (4 presets)
法律与合规领域(4个预设)
- Legal Counsel -
templates/presets/legal/legal-counsel.md - Compliance Officer -
templates/presets/legal/compliance-officer.md - Contract Manager -
templates/presets/legal/contract-manager.md - Regulatory Affairs Specialist -
templates/presets/legal/regulatory-affairs.md
- 法律顾问 -
templates/presets/legal/legal-counsel.md - 合规专员 -
templates/presets/legal/compliance-officer.md - 合同经理 -
templates/presets/legal/contract-manager.md - 监管事务专员 -
templates/presets/legal/regulatory-affairs.md
Finance & Accounting (4 presets)
金融与会计领域(4个预设)
- Financial Analyst -
templates/presets/finance/financial-analyst.md - CFO / Controller -
templates/presets/finance/cfo-controller.md - Accountant / Tax Specialist -
templates/presets/finance/accountant-tax.md - Investment Analyst -
templates/presets/finance/investment-analyst.md
- 金融分析师 -
templates/presets/finance/financial-analyst.md - CFO / 财务总监 -
templates/presets/finance/cfo-controller.md - 会计 / 税务专员 -
templates/presets/finance/accountant-tax.md - 投资分析师 -
templates/presets/finance/investment-analyst.md
Human Resources (4 presets)
人力资源领域(4个预设)
- HR Manager / HR Business Partner -
templates/presets/hr/hr-manager.md - Talent Acquisition Specialist -
templates/presets/hr/talent-acquisition.md - Learning & Development Manager -
templates/presets/hr/learning-development.md - Compensation & Benefits Analyst -
templates/presets/hr/compensation-analyst.md
- HR经理 / HR业务合作伙伴 -
templates/presets/hr/hr-manager.md - 招聘专员 -
templates/presets/hr/talent-acquisition.md - 学习与发展经理 -
templates/presets/hr/learning-development.md - 薪酬福利分析师 -
templates/presets/hr/compensation-analyst.md
Design (4 presets)
设计领域(4个预设)
- UI/UX Designer -
templates/presets/design/ui-ux-designer.md - Graphic Designer -
templates/presets/design/graphic-designer.md - Brand Designer -
templates/presets/design/brand-designer.md - Product Designer -
templates/presets/design/product-designer.md
- UI/UX设计师 -
templates/presets/design/ui-ux-designer.md - 平面设计师 -
templates/presets/design/graphic-designer.md - 品牌设计师 -
templates/presets/design/brand-designer.md - 产品设计师 -
templates/presets/design/product-designer.md
Customer-Facing (4 presets)
客户服务领域(4个预设)
- Customer Success Manager -
templates/presets/customer/customer-success-manager.md - Support Engineer / Technical Support -
templates/presets/customer/support-engineer.md - Account Manager -
templates/presets/customer/account-manager.md - Customer Experience Manager -
templates/presets/customer/customer-experience-manager.md
- 客户成功经理 -
templates/presets/customer/customer-success-manager.md - 支持工程师 / 技术支持 -
templates/presets/customer/support-engineer.md - 客户经理 -
templates/presets/customer/account-manager.md - 客户体验经理 -
templates/presets/customer/customer-experience-manager.md
Executive Leadership (7 presets)
高管领导力领域(7个预设)
- CEO / Founder -
templates/presets/executive/ceo-founder.md - CTO / VP of Engineering -
templates/presets/executive/cto-vp-engineering.md - Chief Strategy Officer -
templates/presets/executive/chief-strategy-officer.md - General Manager -
templates/presets/executive/general-manager.md - Chief Product Officer (CPO) -
templates/presets/executive/chief-product-officer.md - Chief Marketing Officer (CMO) -
templates/presets/executive/chief-marketing-officer.md - Chief Operations Officer (COO) -
templates/presets/executive/chief-operations-officer.md
- CEO / 创始人 -
templates/presets/executive/ceo-founder.md - CTO / 工程副总裁 -
templates/presets/executive/cto-vp-engineering.md - 首席战略官 -
templates/presets/executive/chief-strategy-officer.md - 总经理 -
templates/presets/executive/general-manager.md - 首席产品官 (CPO) -
templates/presets/executive/chief-product-officer.md - 首席营销官 (CMO) -
templates/presets/executive/chief-marketing-officer.md - 首席运营官 (COO) -
templates/presets/executive/chief-operations-officer.md
Specialized Technical (6 presets)
专业技术领域(6个预设)
- Machine Learning Engineer -
templates/presets/specialized-technical/ml-engineer.md - Blockchain Developer -
templates/presets/specialized-technical/blockchain-developer.md - Game Developer -
templates/presets/specialized-technical/game-developer.md - Embedded Systems Engineer -
templates/presets/specialized-technical/embedded-systems-engineer.md - Network Engineer -
templates/presets/specialized-technical/network-engineer.md - Site Reliability Engineer (SRE) -
templates/presets/specialized-technical/site-reliability-engineer.md
- 机器学习工程师 -
templates/presets/specialized-technical/ml-engineer.md - 区块链开发者 -
templates/presets/specialized-technical/blockchain-developer.md - 游戏开发者 -
templates/presets/specialized-technical/game-developer.md - 嵌入式系统工程师 -
templates/presets/specialized-technical/embedded-systems-engineer.md - 网络工程师 -
templates/presets/specialized-technical/network-engineer.md - 站点可靠性工程师 (SRE) -
templates/presets/specialized-technical/site-reliability-engineer.md
Research & Analysis (3 presets)
研究与分析领域(3个预设)
- Research Scientist -
templates/presets/research/research-scientist.md - Quantitative Analyst (Quant) -
templates/presets/research/quantitative-analyst.md - Market Researcher -
templates/presets/research/market-researcher.md
- 研究科学家 -
templates/presets/research/research-scientist.md - 量化分析师 (Quant) -
templates/presets/research/quantitative-analyst.md - 市场研究员 -
templates/presets/research/market-researcher.md
Creative & Media (4 presets)
创意与媒体领域(4个预设)
- Copywriter -
templates/presets/creative-media/copywriter.md - Social Media Manager -
templates/presets/creative-media/social-media-manager.md - SEO Specialist -
templates/presets/creative-media/seo-specialist.md - Video Producer / Content Creator -
templates/presets/creative-media/video-producer.md
- 文案策划 -
templates/presets/creative-media/copywriter.md - 社交媒体经理 -
templates/presets/creative-media/social-media-manager.md - SEO专员 -
templates/presets/creative-media/seo-specialist.md - 视频制作人 / 内容创作者 -
templates/presets/creative-media/video-producer.md
Manufacturing (4 presets)
制造领域(4个预设)
- Manufacturing Engineer -
templates/presets/manufacturing/manufacturing-engineer.md - Supply Chain Manager -
templates/presets/manufacturing/supply-chain-manager.md - Quality Engineer (Physical Products) -
templates/presets/manufacturing/quality-engineer.md - Industrial Designer -
templates/presets/manufacturing/industrial-designer.md
- 制造工程师 -
templates/presets/manufacturing/manufacturing-engineer.md - 供应链经理 -
templates/presets/manufacturing/supply-chain-manager.md - 质量工程师(实体产品) -
templates/presets/manufacturing/quality-engineer.md - 工业设计师 -
templates/presets/manufacturing/industrial-designer.md
R&D - Research & Development (2 presets)
研发领域(2个预设)
- Clinical Specialist (PhD-level) -
templates/presets/rd/clinical-specialist.md - Senior AI R&D Expert -
templates/presets/rd/ai-rd-expert.md
- 临床专员(博士级别) -
templates/presets/rd/clinical-specialist.md - 资深AI研发专家 -
templates/presets/rd/ai-rd-expert.md
Regulatory Affairs (1 preset)
监管事务领域(1个预设)
- Quality Management Responsible Person -
templates/presets/regulatory/quality-management-responsible.md
- 质量管理负责人 -
templates/presets/regulatory/quality-management-responsible.md
Creative (2 presets)
创意领域(2个预设)
- Content Strategist -
templates/presets/creative/content-strategist.md - UX Researcher -
templates/presets/creative/ux-researcher.md
- 内容策略师 -
templates/presets/creative/content-strategist.md - UX研究员 -
templates/presets/creative/ux-researcher.md
Specialized (4 presets)
特殊领域(4个预设)
- Technical Writer -
templates/presets/specialized/technical-writer.md - Sales Engineer -
templates/presets/specialized/sales-engineer.md - Marketing Strategist -
templates/presets/business/marketing-strategist.md - AEO Specialist (Answer Engine Optimization) -
templates/presets/specialized/aeo-specialist.md
- 技术文档工程师 -
templates/presets/specialized/technical-writer.md - 销售工程师 -
templates/presets/specialized/sales-engineer.md - 营销策略师 -
templates/presets/business/marketing-strategist.md - AEO专员(答案引擎优化) -
templates/presets/specialized/aeo-specialist.md
Contextual Best Practices Integration
上下文最佳实践整合
Apply relevant practices based on context:
根据上下文应用相关实践:
By Output Type
按输出类型
Code:
- OpenAI: Step-by-step reasoning, edge case handling
- Anthropic: Clear code structure with comments
- Google: Modular design, example-driven
- Domain: Language-specific idioms, testing standards
Documentation:
- OpenAI: Clear structure, practical examples
- Anthropic: Logical flow, comprehensive coverage
- Google: Visual aids, progressive disclosure
- Domain: Audience-appropriate depth, accessibility
Strategy:
- OpenAI: Data-driven reasoning, scenario analysis
- Anthropic: Structured framework, clear rationale
- Google: Actionable insights, measurable outcomes
- Domain: Industry benchmarks, competitive context
Analysis:
- OpenAI: Methodology transparency, evidence-based
- Anthropic: Clear conclusions, limitations noted
- Google: Visual data presentation, insights hierarchy
- Domain: Domain metrics, analytical rigor
代码:
- OpenAI: 分步推理,边缘情况处理
- Anthropic: 清晰的代码结构和注释
- Google: 模块化设计,示例驱动
- 领域: 特定语言的惯用写法,测试标准
文档:
- OpenAI: 清晰的结构,实用示例
- Anthropic: 逻辑流程,全面覆盖
- Google: 视觉辅助,渐进式披露
- 领域: 适合受众的深度,无障碍性
策略:
- OpenAI: 数据驱动的推理,场景分析
- Anthropic: 结构化框架,清晰的理由
- Google: 可执行的洞察,可衡量的结果
- 领域: 行业基准,竞争上下文
分析:
- OpenAI: 方法论透明,基于证据
- Anthropic: 清晰的结论,注明局限性
- Google: 可视化数据呈现,洞察层级
- 领域: 领域指标,分析严谨性
By Complexity Level
按复杂度级别
Basic: Essential practices, simplified workflows
Intermediate: Standard practices, complete workflows
Advanced: Advanced techniques, optimization focus
Expert: Cutting-edge practices, innovation emphasis
基础: 基本实践,简化工作流程
中级: 标准实践,完整工作流程
高级: 高级技术,聚焦优化
专家: 前沿实践,强调创新
By Domain
按领域
Technical: Code quality, testing, security, performance
Business: ROI focus, stakeholder alignment, measurability
Creative: Brand consistency, audience resonance, originality
Specialized: Compliance, regulations, industry standards
技术: 代码质量,测试,安全,性能
商业: 聚焦ROI,利益相关者对齐,可衡量性
创意: 品牌一致性,受众共鸣,原创性
特殊领域: 合规性,法规,行业标准
Use Case Matrix Coverage
用例矩阵覆盖
Supported Combinations: 15,000+
50+ Roles:
- Developers (Frontend, Backend, Full-Stack, Mobile, ML, DevOps, etc.)
- Analysts (Data, Business, Product, Market, etc.)
- Strategists (Marketing, Business, Product, Growth, etc.)
- Designers (UX, UI, Product, System, etc.)
- Consultants (Tech, Business, Strategy, Domain-specific, etc.)
- Managers (Product, Project, Operations, Technical, etc.)
- Specialists (Security, Performance, Quality, Compliance, etc.)
20+ Industries:
- Technology (SaaS, Cloud, Mobile, Web, AI/ML)
- Finance (Banking, Trading, Payments, Insurance, FinTech)
- Healthcare (Clinical, Pharma, MedTech, Telemedicine)
- E-commerce (Retail, Marketplace, D2C)
- Education (EdTech, E-learning, Academic)
- Legal (LegalTech, Compliance, Contracts)
- Manufacturing (IoT, Supply Chain, Automation)
- Media (Streaming, Content, Publishing)
- Real Estate (PropTech, Management, Investment)
- And 11 more...
15+ Task Types:
- Build/Create/Develop
- Analyze/Evaluate/Assess
- Design/Architect/Plan
- Optimize/Improve/Refactor
- Debug/Fix/Troubleshoot
- Document/Write/Explain
- Test/Validate/Verify
- Strategize/Plan/Roadmap
- And 7 more...
支持的组合: 15,000+
50+角色:
- 开发者(前端、后端、全栈、移动、ML、DevOps等)
- 分析师(数据、商业、产品、市场等)
- 策略师(营销、商业、产品、增长等)
- 设计师(UX、UI、产品、系统等)
- 顾问(技术、商业、策略、特定领域等)
- 经理(产品、项目、运营、技术等)
- 专员(安全、性能、质量、合规等)
20+行业:
- 科技(SaaS、云、移动、Web、AI/ML)
- 金融(银行、交易、支付、保险、金融科技)
- 医疗(临床、制药、医疗科技、远程医疗)
- 电商(零售、市场、D2C)
- 教育(EdTech、在线学习、学术)
- 法律(LegalTech、合规、合同)
- 制造(IoT、供应链、自动化)
- 媒体(流媒体、内容、出版)
- 房地产(PropTech、管理、投资)
- 还有11个其他行业...
15+任务类型:
- 构建/创建/开发
- 分析/评估/评估
- 设计/架构/规划
- 优化/改进/重构
- 调试/修复/故障排除
- 文档/撰写/解释
- 测试/验证/验证
- 策略/规划/路线图
- 还有7个其他任务类型...
Error Handling & Edge Cases
错误处理与边缘情况
Insufficient Information
信息不足
If user responses are vague:
- Identify specific gaps
- Ask targeted follow-up (max 2 questions)
- Offer sensible defaults with confirmation
如果用户回答模糊:
- 识别具体差距
- 提出针对性的跟进问题(最多2个)
- 提供合理的默认值并要求确认
Conflicting Requirements
冲突需求
If responses contain contradictions:
- Highlight specific conflicts
- Request clarification with options
- Suggest resolution based on common patterns
如果回答存在矛盾:
- 突出具体冲突
- 提供选项请求澄清
- 根据常见模式建议解决方案
Over-Complex Requests
过于复杂的请求
If requirements suggest >10K token prompt:
- Suggest breaking into multiple specialized prompts
- Offer modular approach
- Provide coordination guidance for multi-prompt system
如果需求提示要生成>10K token的提示词:
- 建议拆分为多个专业提示词
- 提供模块化方法
- 为多提示词系统提供协调指导
Template Unavailable
模板不可用
If template file cannot be loaded:
- Fall back to synthesis mode
- Use best practices from references
- Generate custom template on the fly
如果无法加载模板文件:
- 回退到合成模式
- 使用参考资料中的最佳实践
- 动态生成自定义模板
Python Script Integration
Python脚本集成
Manual Script Usage
手动脚本使用
bash
undefinedbash
undefinedGenerate with JSON config
使用JSON配置生成
python scripts/generate_prompt.py
--responses responses.json
--format xml
--mode core
--output my-prompt.md
--responses responses.json
--format xml
--mode core
--output my-prompt.md
python scripts/generate_prompt.py
--responses responses.json
--format xml
--mode core
--output my-prompt.md
--responses responses.json
--format xml
--mode core
--output my-prompt.md
Batch generation
批量生成
python scripts/batch_generator.py
--input prompts-batch.csv
--output-dir ./outputs/
--input prompts-batch.csv
--output-dir ./outputs/
python scripts/batch_generator.py
--input prompts-batch.csv
--output-dir ./outputs/
--input prompts-batch.csv
--output-dir ./outputs/
Validate existing prompt
验证现有提示词
python scripts/validator.py
--prompt existing-prompt.md
--report validation-report.json
--prompt existing-prompt.md
--report validation-report.json
python scripts/validator.py
--prompt existing-prompt.md
--report validation-report.json
--prompt existing-prompt.md
--report validation-report.json
Optimize prompt
优化提示词
python scripts/optimizer.py
--prompt my-prompt.md
--target-tokens 5000
--output optimized-prompt.md
--prompt my-prompt.md
--target-tokens 5000
--output optimized-prompt.md
undefinedpython scripts/optimizer.py
--prompt my-prompt.md
--target-tokens 5000
--output optimized-prompt.md
--prompt my-prompt.md
--target-tokens 5000
--output optimized-prompt.md
undefinedSkill-Triggered Script Execution
技能触发的脚本执行
The skill will automatically call Python scripts for:
- Quality validation (validator.py)
- Token counting (within validator.py)
- Batch operations (if user requests multiple prompts)
本技能将自动调用Python脚本用于:
- 质量验证(validator.py)
- 令牌计数(在validator.py中)
- 批量操作(如果用户请求多个提示词)
Success Metrics
成功指标
User Experience:
- Max 7 questions (vs 14-16 in other skills)
- < 2 minutes to generate prompt
- 15 one-click presets available
- 5 output format options
- 2 generation modes (core/advanced)
Quality:
- 7-point pre-delivery validation
- 100% XML structure validity (when applicable)
- Best practices contextually applied
- Token-optimized outputs
- Zero placeholder text in final output
Coverage:
- 15 ready-to-use core templates
- 15,000+ role/industry/task combinations
- Support for all major LLMs (Claude/ChatGPT/Gemini)
- Both basic and expert use cases
用户体验:
- 最多7个问题(其他技能为14-16个)
- 生成提示词耗时<2分钟
- 15个一键预设可用
- 5种输出格式选项
- 2种生成模式(核心/高级)
质量:
- 交付前7点验证
- 100% XML结构有效性(如果适用)
- 上下文相关的最佳实践已应用
- 令牌优化的输出
- 最终输出中无占位符文本
覆盖范围:
- 15个可直接使用的核心模板
- 15,000+角色/行业/任务组合
- 支持所有主要LLM(Claude/ChatGPT/Gemini)
- 支持基础和专家用例
Reference Files
参考文件
- - Comprehensive user guide with examples
HOW_TO_USE.md - - 15 quick-start templates
templates/presets/ - - Custom template generation guidelines
templates/template-synthesis.md - - OpenAI, Anthropic, Google techniques
references/best-practices/ - - Common patterns library
references/prompt-patterns.md - - Complete role/industry/task matrix
references/use-case-matrix.md - - 20 complete examples (5 basic, 5 advanced, 10 industry)
examples/ - - Python automation tools
scripts/
Ready to create world-class prompts? Let's begin!
- - 包含示例的综合用户指南
HOW_TO_USE.md - - 15个快速启动模板
templates/presets/ - - 自定义模板生成指南
templates/template-synthesis.md - - OpenAI、Anthropic、Google的技术
references/best-practices/ - - 常见模式库
references/prompt-patterns.md - - 完整的角色/行业/任务矩阵
references/use-case-matrix.md - - 20个完整示例(5个基础,5个高级,10个行业特定)
examples/ - - Python自动化工具
scripts/
准备好创建世界级的提示词了吗?开始吧!