631 AI Prompts for Coding

The best Coding prompts across 14 subcategories. Tested on ChatGPT, Claude, Gemini and every major model.

Browse the prompts

## Role

You are a meticulous cybersecurity consultant specializing in website security audits and vulnerability assessments.

## Task

Create a comprehensive security audit checklist for {{website-url}} that identifies potential vulnerabilities, proposes mitigation strategies, and provides recommendations to enhance the site's trustworthiness and resilience against cyber threats.

## Audit Framework

Generate a structured checklist covering these areas:

**1. Information Gathering**
- Collect domain and hosting details
- Identify technologies used (CMS, frameworks, libraries)
- Map website architecture and functionality

**2. Vulnerability Scanning**
- Perform automated vulnerability scans using recommended tools
- Analyze and prioritize vulnerabilities by severity
- Manually verify high-risk findings to eliminate false positives

**3. Access Control and Authentication**
- Test for weak

Website Security Audit Checklist Generator

Generates a comprehensive security audit checklist for any website, identifying vulnerabilities and mitigation strategies across ten critical security areas. Runs on ChatGPT, Claude, Gemini, and Grok.

213
## Role

You are a full-stack Google Workspace integration specialist building production-ready Google Drive add-ons.

## Task

Create a comprehensive, step-by-step implementation guide for a Google Drive add-on based on the specification below.

## Context

{{add-on-specification}}

## Requirements

- Native Google Drive integration with minimal user friction
- Enterprise-grade architecture with robust error handling
- Modern, accessible UI with responsive design
- Complete OAuth security configuration
- Production-ready deployment strategy

## Output

Structure your implementation guide with these sections, providing complete code examples and specific implementation details for each:

### Architecture Planning and File Structure
- Project organization and module design
- Dependency management and versioning

### Backend Development with Apps Script
- Core business logic implementation

Google Drive Add-On Development Prompt

Generates a complete, step-by-step implementation guide for building production-ready Google Drive add-ons with Apps Script. Runs on ChatGPT, Claude, Gemini, and Grok to produce enterprise-grade code, architecture plans, and deployment strategies.

205

Standing Instruction for Unattended Agent Runs

Generate standing instructions for autonomous agents to properly manage turn behavior when operating unattended. Ideal for integrating into system prompts for AI-based task automation.

196

Vocabulary Learning App Builder

Generates a complete, production-ready vocabulary learning web application with spaced repetition, state management, and modern UI/UX. Outputs full-stack React TypeScript code that runs on ChatGPT, Claude, or Cursor.

193

UI/UX Design Guidelines Generator for Digital Products

Generates a comprehensive, structured design guideline document covering color, typography, layout, navigation, accessibility, and interaction patterns. Runs on ChatGPT, Claude, and Gemini to produce ready-to-implement standards for design teams.

190
## Role

You are an expert web-based 3D racing game developer with AAA studio background (Polyphony Digital, Turn 10) who specializes in building high-performance browser games using Three.js. You understand racing physics deeply (tire slip angles, weight transfer, handling models), have shipped multiple Three.js racing prototypes, and know which optimizations matter for 60fps in WebGL.

## Context

The user is building a complete 3D racing game from scratch using Three.js and JavaScript. Unlike traditional game engines that provide physics, multiplayer, and optimization systems out of the box, they must architect everything custom while staying within browser constraints. The challenge is balancing visual fidelity with frame rate, creating engaging AI, and building modular systems (physics, rendering, input, multiplayer state management) that won't collapse under technical debt.

## Tas

Build 3D Racing Games With Three.js and JavaScript

Generates a complete Three.js development roadmap for building browser-based 3D racing games with vehicle physics, AI opponents, split-screen multiplayer, and 60fps optimization. Runs on ChatGPT, Claude, Gemini, and Grok.

185
## Role
You are a full-stack developer specializing in gamified productivity applications.

## Task
Create a complete gamified task management system that transforms tasks into RPG-style experiences using behavioral psychology principles.

## Context
{{project-requirements}}

## Output
Deliver production-ready code with:

● **Project Architecture** – File structure, dependencies, and setup instructions
● **Core Game Mechanics** – XP systems, level calculations, streak tracking, and achievement triggers
● **React Components** – Quest dashboard, progress tracker, and celebration animations
● **Psychology Integration** – Reward systems and behavioral reinforcement patterns
● **UI Design** – Responsive layouts, animations, and accessibility features
● **Production Deployment** – Performance optimization, offline functionality, and deployment guidelines

Provide:

● Complete file implementati

Gamified Task Management App Builder

Generates production-ready code for a gamified task management web application that turns tasks into RPG-style quests with XP systems, level progression, and achievement tracking. Runs on ChatGPT, Claude, and Cursor.

184

Fix Code Errors With Systematic Debugging

Guides developers through structured, hypothesis-driven debugging using the scientific method to identify root causes and implement fixes. Runs on ChatGPT, Claude, Gemini, and Grok.

182

Configure iPhone App Project Settings

Generates a step-by-step Xcode configuration checklist for setting up a clean iPhone-only iOS project with deployment, orientation, security, and App Store compliance defaults. Runs on ChatGPT, Claude, Gemini, and Grok.

182
## Role

You are a design systems architect who builds Tailwind CSS-based style guides that bridge the gap between design intent and developer implementation. Your documentation is specific, actionable, and maintained without constant designer oversight.

## Task

Generate a comprehensive style guide with concrete values, Tailwind CSS utility classes, and implementation patterns. Each section must include specific measurements, class names, and usage guidelines—no abstract descriptions. Provide a complete example component that demonstrates multiple style elements working together.

## Context

**Project:** {{project-name}}

**Design direction:** {{design-direction}}

**Target audience and platform:** {{target-audience-and-platform}}

**Existing brand assets:** {{existing-brand-assets}}

The guide must enable new developers to maintain visual consistency without direct designer supervisi

Tailwind CSS Brand Style Guide Generator

Generates a complete Tailwind CSS brand style guide with colors, typography, spacing, components, shadows, and a working example component. Runs on ChatGPT, Claude, Gemini, and Grok.

164
You are an **AI configuration auditor** specializing in agent instruction design. Your task is to analyze AGENTS.md files and skill definitions to identify friction points that cause unnecessary pauses, redundant confirmations, or incomplete work.

## Analysis Scope

**Primary focus areas:**
- Autonomy boundaries (when the agent must stop vs. when it should proceed)
- Clarification triggers (vague language that forces questions on routine tasks)
- Approval gates (explicit vs. accidental confirmation requirements)
- Task completion signals (ambiguous conditions that leave work unfinished)
- Overlapping or conflicting directives across files

**Context to analyze:**
{{configuration-files}}

## Analysis Framework

### Step 1: Map the Instruction Landscape
For each file, extract:
- Explicit approval requirements ("must ask," "requires confirmation")
- Conditional autonomy rules ("if X, then 

AGENTS.md and Skills Conflict Audit

Audit AGENTS.md and skill files for conflicting or unclear instructions that hinder effective agent functionality. Produces a list of actionable edits for enhanced autonomy and clarity.

163

Bug Report Writer Prompt for Developers

Generates structured, developer-ready bug reports from incomplete user observations. Runs on ChatGPT, Claude, Gemini, and Grok to extract technical details and format them following software anomaly reporting standards.

162

Shopify App Development Prompt

Generates a complete development plan, tech stack, and TypeScript code scaffolds for building production-ready Shopify apps that pass App Store review. Runs on ChatGPT, Claude, and Cursor to deliver architecture, Polaris UI implementations, OAuth flows, webhook handlers, and deployment configs.

151

Code Quality Audit and Refactoring Recommendations

Generates a five-part code quality audit covering refactoring opportunities, configuration issues, dependency risks, automated quality gates, and documentation templates. Runs on ChatGPT, Claude, Gemini, and Grok.

150
## Role
You are a SQL query architect specializing in production-ready queries that follow Joe Celko's SQL Programming Style, prioritizing readability, maintainability, and performance optimization.

## Task
Generate SQL queries compliant with Celko's formatting standards. Before writing any query, analyze the schema, identify potential performance bottlenecks, choose appropriate join strategies, and structure for maximum readability.

## Context
{{database-requirements}}

*Provide your database schema, the desired output/results you need, and any performance constraints or compliance requirements.*

## Query Standards

**Formatting:**
- Each major clause (SELECT, FROM, WHERE, JOIN, GROUP BY, ORDER BY) starts on a new line
- Subqueries indented 4 spaces
- Column lists vertically aligned
- Logical operators (AND, OR) at the beginning of lines
- Uppercase SQL keywords, lowercase identifier

SQL Query Generator With Celko Style Standards

Generates production-ready SQL queries following Joe Celko's formatting standards, with schema analysis and performance optimization. Runs on ChatGPT, Claude, and Cursor to produce readable, maintainable database code.

147
## Role

You are a dashboard architecture specialist with quantitative trading experience building production financial interfaces. You understand how cognitive load affects decision-making under market pressure and design systems that combine institutional-grade data visualization with consumer-app simplicity.

## Task

Architect a production-ready investment tracking dashboard using React and modern JavaScript. Provide comprehensive technical specifications including:

- Complete component hierarchy and responsibility mapping
- State management approach optimized for financial data
- Data flow architecture and API integration patterns
- Core feature implementation: portfolio performance tracking, asset allocation visualization, multi-asset-type support, real-time data integration
- Charting library recommendations with integration code
- Security best practices for financial data prote

Investment Tracking Dashboard Builder Prompt

Generates production-ready React architecture for investment tracking dashboards with component hierarchies, state management, real-time data integration, and security patterns. Runs on ChatGPT, Claude, and Cursor.

141

E-Commerce Store Builder Prompt for React and TypeScript

Generates a complete technical implementation plan for a production-ready e-commerce store built with React, TypeScript, Supabase/Firebase, and Stripe. Runs on ChatGPT, Claude, and Cursor to deliver component architecture, database schema, payment integration, and admin dashboard code.

133

UI Modernization Prompt for Dashboard Refactoring

Generates production-ready React code that transforms legacy dashboard interfaces into modern, accessible, high-performing UIs while maintaining 100% feature parity. Runs on ChatGPT, Claude, and Cursor.

131
## Role

You are an expert full-stack developer specializing in Notion-embedded widgets with deep knowledge of iframe constraints, cross-origin messaging, responsive scaling, and performance optimization.

## Task

Create a complete, production-ready Notion widget that integrates seamlessly into Notion's ecosystem and works immediately when deployed and embedded.

## Context

{{widget-specification}}

Include: widget purpose and functionality, target users and needs, must-have vs. nice-to-have features, technical stack preferences or constraints, and preferred hosting platform (Vercel, Netlify, etc.).

## Technical Requirements

- React 18+ with TypeScript and Tailwind CSS
- Bundle size under 100KB with sub-500ms render time
- Notion color palette integration with light/dark mode support
- Responsive design optimized for 1-3 column Notion layouts
- LocalStorage persistence with export/im

Notion Widget Builder Prompt for ChatGPT and Claude

Generates production-ready Notion widgets with complete React/TypeScript code, iframe integration, and deployment instructions. Runs on ChatGPT, Claude, and Cursor to deliver responsive, performant widgets optimized for Notion's ecosystem.

130
## Role
You are a full-stack developer specializing in behavioral design and progressive web applications.

## Task
Build a complete, production-ready calorie tracking PWA that minimizes friction and maximizes retention through behavioral psychology principles. Prioritize effortless interaction over feature bloat.

## Context
Most diet apps fail within days due to overwhelming interfaces and complexity. This app must learn from those failures: make healthy habits feel natural, not burdensome.

{{app-specification}}
Provide the app name, core concept, target user demographics and behavior patterns, key features, and user flow priorities.

{{tech-stack}}
Specify your preferred technology stack, development constraints, design aesthetic, and brand identity direction.

## Output
Deliver a complete, runnable single-artifact application with:

**Architecture**
- Full file structure, dependenci

Diet Tracking App Development Prompt

Generates a complete, production-ready calorie tracking PWA built on behavioral psychology principles that minimize user friction and maximize retention. Outputs full-stack code for ChatGPT, Claude, or Cursor with TypeScript, state management, and progressive web app features.

130

Animated Screensaver Design and Development Prompt

Generates a complete implementation plan for building animated screensavers, including code frameworks, animation architecture, performance optimization, and platform deployment. Runs on ChatGPT, Claude, and Cursor.

129

Test Dataset Generator for SQL and Code Testing

Generates SQL INSERT statements with edge cases, boundary conditions, and referential complexity designed to expose bugs before production. Runs on ChatGPT, Claude, and Cursor for code testing workflows.

129

Habit Tracking App Builder for React and TypeScript

Generates production-ready React habit-tracking application code with behavioral psychology-driven gamification, streak calculation, and reward animations. Runs on ChatGPT, Claude, and Cursor for full-stack TypeScript development.

128

What are AI prompts for Coding?

AI prompts for Coding are engineered instructions that already work. These are not one-line questions. Each one fixes the role, the context, the task and the output format before you type a word, so you get a usable result on the first run instead of the fourth.

They cover the work Coding actually get asked for: research and briefs, copy and content, analysis and reporting, planning, outreach and the admin that eats the day. Open a card to see the full prompt and the output it returns.

The deepest areas here: App Development (111 prompts), Frontend & UI (86 prompts), Agentic Workflows (56 prompts), Documentation (50 prompts), APIs & Integrations (43 prompts).

Popular on this page right now: "Website Security Audit Checklist Generator", "Google Drive Add-On Development Prompt", "Standing Instruction for Unattended Agent Runs".

631 on this page, every one scoped to Coding. Free to read, free to copy.

Why these prompts work for Coding

A weak prompt costs you the hour you were trying to save: you rewrite it three times, get something generic, then finish the job by hand. An engineered prompt front-loads that thinking once.

In Coding that means first drafts you can send, analysis you can act on, and the repetitive work handed off, so the time goes into judgement instead of typing.

Every prompt here was written for a real job and tested against the models people actually use. Nothing scraped from a thread.

How to use these prompts

Open a prompt, copy it, and replace the [bracketed] variables with your own product, audience or topic. The structure around them stays as is. That structure is the part doing the work.

Paste it into ChatGPT, Claude, Gemini, Grok or the model you already use. If the output drifts, tighten the context line instead of rewriting the whole prompt.

No account needed to copy one. No setup, no extension, nothing to install.

Which AI tool works best for Coding prompts?

Text prompts here run well in ChatGPT, Claude, Gemini and Grok; image prompts target Midjourney and Nano Banana. Each card lists the models it was tested with.

Are these AI prompts free to use?

A big part of the library is free: open a prompt, copy it, use it. Premium packs and the Complete AI Bundle unlock the full collection with lifetime updates.

How do I adapt these prompts to my use case?

Start with the [variables]: niche, audience, constraints. If the result still misses, add one example of the output you want. A single good example beats three extra instructions.

For a prompt built from scratch, the Start Now card above opens the custom prompt generator.

Related resources

Get smarter on AI every week

One email a week with the best new prompts, tools, and model updates. Unsubscribe anytime.

Join 100,000+ subscribers. One email a week, real prompts, tools, and model updates. Unsubscribe anytime.

Frequently asked questions

What are vibe code prompts?

Vibe coding means describing the result you want and letting the model write and run the code, in a tool like Cursor, Claude Code or Lovable. Vibe code prompts in this library describe the app in plain words, the stack, what done looks like and what the agent must not touch. The ones that work give the model a way to check its own output, such as a test to pass or a page to open.