replit-prompt

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Replit Prompt Generator

Replit 提示词生成器

Transform requirements into optimized prompts for Replit Agent that maximize AI understanding and minimize iterations.
将需求转化为针对Replit Agent的优化提示词,最大化AI的理解度,减少迭代次数。

When to Use

使用场景

  • User wants to build something with Replit Agent
  • User needs to convert an idea into a Replit-ready prompt
  • User wants to improve an existing Replit prompt
  • User is preparing to start a new Replit project
  • 用户希望使用Replit Agent构建内容
  • 用户需要将想法转化为可直接用于Replit的提示词
  • 用户想要优化现有的Replit提示词
  • 用户准备启动新的Replit项目

Core Principles (Replit's Official Guidelines)

核心原则(Replit官方指南)

1. Checkpoint — Structure Iteratively

1. 阶段性检查——分步结构化

Break large goals into smaller, testable steps. Use checkpoints between phases.
将大型目标拆分为更小的、可测试的小步骤,在不同阶段之间设置检查点。

2. Debug — Provide Detailed Context

2. 调试——提供详细上下文

Include exact error messages, relevant code snippets, and steps already attempted.
包含精确的错误信息、相关代码片段以及已尝试的解决步骤。

3. Discover — Ask for Suggestions

3. 探索——寻求建议

Request tool/library recommendations when unsure about approach.
当不确定实现方案时,请求工具/库的推荐。

4. Experiment — Iterate on Prompts

4. 实验——迭代优化提示词

Refine requests by adjusting wording or adding detail.
通过调整措辞或补充细节来完善请求。

5. Instruct — Use Positive Goals

5. 指令——采用正向目标表述

Frame as "do this" rather than "don't do that".
以“请执行XX”而非“不要做XX”的方式表述需求。

6. Select — Focused Context

6. 聚焦——提供相关上下文

Provide relevant context only; avoid overwhelming with unrelated information.
仅提供相关的上下文信息,避免无关内容造成信息过载。

7. Show — Concrete Examples

7. 示例——提供具体案例

Reduce ambiguity with code snippets, mockups, or reference apps.
通过代码片段、模型图或参考应用来减少歧义。

8. Simplify — Concise Language

8. 简化——使用简洁语言

Use direct, short sentences. Avoid jargon.
采用直接、简短的句子,避免行话。

9. Specify — Define Outputs

9. 明确——定义输出要求

State expected outputs, constraints, data formats, and edge cases.
说明预期的输出内容、约束条件、数据格式和边缘情况。

10. Test — Plan First

10. 测试——先规划再执行

Outline features, data structures, and user flows before prompting.
在编写提示词之前,先概述功能、数据结构和用户流程。

Prompt Structure Template

提示词结构模板

When generating prompts for Replit, use this structure:
markdown
undefined
为Replit生成提示词时,请使用以下结构:
markdown
undefined

Project Overview

项目概述

[1-2 sentences: What is being built and its core purpose]
[1-2句话:说明要构建的内容及其核心用途]

Tech Stack

技术栈

  • Frontend: [specific framework/library]
  • Backend: [specific framework/language]
  • Database: [specific database]
  • Authentication: [specific method]
  • Additional: [any other required tools/APIs]
  • 前端:[具体框架/库]
  • 后端:[具体框架/语言]
  • 数据库:[具体数据库]
  • 认证:[具体方法]
  • 其他:[任何所需的工具/API]

Core Features

核心功能

  1. [Feature 1]: [specific description with expected behavior]
  2. [Feature 2]: [specific description with expected behavior]
  3. [Feature 3]: [specific description with expected behavior]
  1. [功能1]:[包含预期行为的具体描述]
  2. [功能2]:[包含预期行为的具体描述]
  3. [功能3]:[包含预期行为的具体描述]

UI/UX Requirements

UI/UX要求

  • Design style: [modern/minimal/material/etc.]
  • Color scheme: [specific colors or "neutral professional"]
  • Layout: [sidebar/top-nav/dashboard/etc.]
  • Responsive: [yes/no, breakpoints if specific]
  • 设计风格:[现代/极简/材料设计等]
  • 配色方案:[具体颜色或“中性专业风”]
  • 布局:[侧边栏/顶部导航/仪表盘等]
  • 响应式:[是/否,如有特定要求请说明断点]

Data Model

数据模型

[Describe main entities and their relationships]
  • Entity1: field1, field2, field3
  • Entity2: field1, field2 (relates to Entity1)
[描述主要实体及其关系]
  • 实体1:字段1、字段2、字段3
  • 实体2:字段1、字段2(与实体1关联)

User Flows

用户流程

  1. [Flow 1]: Step A → Step B → Step C → Result
  2. [Flow 2]: Step A → Step B → Result
  1. [流程1]:步骤A → 步骤B → 步骤C → 结果
  2. [流程2]:步骤A → 步骤B → 结果

Constraints

约束条件

  • [Constraint 1: e.g., "Must work offline"]
  • [Constraint 2: e.g., "No external API calls except X"]
  • [约束1:例如“必须支持离线使用”]
  • [约束2:例如“除X外不允许调用外部API”]

Success Criteria

成功标准

  • [Specific testable criterion 1]
  • [Specific testable criterion 2]
  • [Specific testable criterion 3]
undefined
  • [可测试的具体标准1]
  • [可测试的具体标准2]
  • [可测试的具体标准3]
undefined

Procedure

操作流程

Step 1: Gather Requirements

步骤1:收集需求

Ask the user about:
  1. What they want to build (core functionality)
  2. Who will use it (target users)
  3. How it should work (key user flows)
  4. Why (problem being solved)
If user provides vague input, ask clarifying questions:
  • "What should happen when a user clicks X?"
  • "Should data persist between sessions?"
  • "Any specific design/framework preferences?"
向用户询问以下信息:
  1. 内容:他们想要构建什么(核心功能)
  2. 用户:目标用户是谁
  3. 方式:产品应如何运作(关键用户流程)
  4. 原因:要解决的问题是什么
如果用户提供的信息模糊,提出澄清问题:
  • “当用户点击X时应该发生什么?”
  • “会话之间数据需要持久化吗?”
  • “有没有特定的设计/框架偏好?”

Step 2: Extract Technical Details

步骤2:提取技术细节

Determine from user input or ask about:
  • Preferred tech stack (or let Replit decide)
  • Authentication requirements
  • Data storage needs
  • Third-party integrations
  • Performance requirements
从用户输入中确定或询问以下信息:
  • 偏好的技术栈(或让Replit自行决定)
  • 认证要求
  • 数据存储需求
  • 第三方集成
  • 性能要求

Step 3: Structure the Prompt

步骤3:构建提示词结构

Transform gathered information into the structured template above.
Bad prompt transformation:
❌ Bad: "Make a website for my business"
✅ Good: "Create a portfolio website for a freelance photographer with:
- Home page with hero image carousel
- Gallery page with filterable photo categories
- Contact form with email integration
- About page with bio and testimonials
- Tech: React, TailwindCSS, EmailJS for form
- Design: Clean, minimal, lots of whitespace"
将收集到的信息转化为上述结构化模板。
不良与良好的提示词转化示例:
❌ 不良:“为我的业务做个网站”
✅ 良好:“为自由摄影师创建一个作品集网站,包含:
- 带英雄图轮播的首页
- 可按类别筛选的图片画廊页面
- 集成邮箱的联系表单
- 包含个人简介和客户评价的关于页面
- 技术栈:React、TailwindCSS、EmailJS(用于表单)
- 设计风格:简洁、极简、留白充足”

Step 4: Add Specificity

步骤4:增加细节

Enhance the prompt with:
  • Concrete examples: "Like Stripe's dashboard layout"
  • Specific behaviors: "Click 'Add' opens modal, not new page"
  • Edge cases: "If cart is empty, show 'Start shopping' CTA"
  • Validation rules: "Email must be valid format, password min 8 chars"
为提示词补充以下内容:
  • 具体示例:“参考Stripe的仪表盘布局”
  • 特定行为:“点击‘添加’按钮打开模态框,而非新页面”
  • 边缘情况:“如果购物车为空,显示‘开始购物’的号召性用语”
  • 验证规则:“邮箱格式必须有效,密码最少8位”

Step 5: Present Draft

步骤5:呈现草稿

Show the optimized prompt to the user:
undefined
向用户展示优化后的提示词:
undefined

Replit Agent Prompt

Replit Agent 提示词

Optimized for: [Build Mode / Plan Mode] Estimated complexity: [Low / Medium / High]

[Generated prompt content]

Recommendations:
  1. [Tip for using this prompt effectively]
  2. [Suggested follow-up prompts after initial build]
Ready to copy to Replit?

Wait for user confirmation or modification requests.
优化模式: [构建模式 / 规划模式] 预估复杂度: [低 / 中 / 高]

[生成的提示词内容]

建议:
  1. [有效使用本提示词的技巧]
  2. [初始构建后的后续提示词建议]
是否准备好复制到Replit?

等待用户确认或修改请求。

Step 6: Provide Iteration Guidance

步骤6:提供迭代指导

After delivering the prompt, advise on:
  • Using Plan Mode first for complex features
  • Setting up checkpoints between phases
  • Follow-up prompts for refinements
交付提示词后,向用户建议:
  • 对于复杂功能,先使用规划模式
  • 在不同阶段之间设置检查点
  • 后续优化的提示词方向

Output Format

输出格式

undefined
undefined

Replit Agent Prompt

Replit Agent 提示词

Mode: Build / Plan Complexity: Low / Medium / High

[Structured prompt following template]

模式: 构建 / 规划 复杂度: 低 / 中 / 高

[遵循模板的结构化提示词]

Next Steps

后续步骤

  1. Initial Build: Copy prompt to Replit Agent
  2. After MVP: [Suggested enhancement prompt]
  3. Testing: [What to verify after build]
  1. 初始构建:将提示词复制到Replit Agent
  2. MVP完成后:[建议的增强提示词]
  3. 测试:[构建完成后需要验证的内容]

Checkpoint Strategy

阶段性检查策略

Phase 1: [Description] → Checkpoint Phase 2: [Description] → Checkpoint Phase 3: [Description] → Checkpoint
undefined
阶段1:[描述] → 检查点 阶段2:[描述] → 检查点 阶段3:[描述] → 检查点
undefined

Bad vs Good Prompt Examples

不良与良好提示词示例

IssueBad PromptGood Prompt
Vague"Fix my code""The login function in auth.js throws 'undefined user' on line 42 when email contains '+'"
No scope"Make a website""Create a 3-page portfolio: Home (hero, skills), Projects (grid with filters), Contact (form)"
Negative"Don't make it slow""Implement lazy loading for images, paginate lists to 20 items"
No detail"Add animation""Fade in hero text on page load over 0.5s, slide in cards from bottom on scroll"
Overwhelming"Build the entire backend""Implement user signup/login with JWT and a /api/profile GET endpoint"
问题不良提示词良好提示词
模糊“修复我的代码”“auth.js中的登录函数在邮箱包含'+'时,第42行抛出'undefined user'错误”
无范围“做个网站”“创建一个3页面的作品集:首页(英雄区、技能展示)、项目页(带筛选的网格布局)、联系页(表单)”
负面表述“别让它变慢”“为图片实现懒加载,列表分页显示20条内容”
缺乏细节“添加动画”“页面加载时英雄文本在0.5秒内淡入,滚动时卡片从底部滑入”
内容过载“构建整个后端”“实现基于JWT的用户注册/登录功能,以及/api/profile GET接口”

Rules

规则

  1. ALWAYS use positive framing — "Do X" not "Don't do Y"
  2. ALWAYS include tech stack — Even if "let Replit decide"
  3. ALWAYS define success criteria — Testable checkboxes
  4. ALWAYS break into phases — For anything beyond simple apps
  5. NEVER use vague terms — No "nice", "good", "fast", "modern" without specifics
  6. NEVER assume context — Replit Agent has no prior knowledge
  1. 始终使用正向表述 —— 用“执行X”而非“不要做Y”
  2. 始终包含技术栈 —— 即使是“让Replit自行决定”
  3. 始终定义成功标准 —— 可测试的复选框形式
  4. 始终拆分阶段 —— 对于简单应用之外的项目
  5. 绝不使用模糊词汇 —— 没有具体说明的情况下,避免使用“不错”“优秀”“快速”“现代”等词
  6. 绝不假设上下文 —— Replit Agent没有前置知识

Additional Resources

额外资源

See reference files for detailed patterns:
  • references/examples.md
    — Full prompt examples for common app types
  • references/tech-stacks.md
    — Recommended tech stack combinations
查看参考文件获取详细模式:
  • references/examples.md
    —— 常见应用类型的完整提示词示例
  • references/tech-stacks.md
    —— 推荐的技术栈组合