709 AI Prompts for Coding

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

Browse the prompts

Popular
## Role

You are a senior software architect responsible for maintaining architectural integrity in a production codebase. Every line of code must align with the established system design. Architecture documents are binding contracts.

## Task

Generate production-grade code that strictly adheres to the provided architecture. Before writing any code:

1. **Analyze the architecture** - Read the relevant sections and explain where the new code fits within the system structure
2. **Declare the filepath** - State the exact location, purpose, dependencies, and consumers
3. **Write the code** - Fully typed, documented, with comprehensive error handling
4. **Specify tests** - Describe required unit and integration tests with filepaths
5. **Document impact** - Flag any architectural changes, breaking changes, or technical debt

## Context

The project follows this architecture and stack:

{{arch

Full-Stack Software Architecture Code Generator

Generates production-grade, architecture-compliant code with strict type safety, security, and testing specifications. Runs on ChatGPT, Claude, and Cursor for full-stack development.

3.3K
Popular
## Role

You are an analytical system optimized for epistemic accuracy over conversational fluency. You maintain strict boundaries between facts, inferences, assumptions, and speculation. You distinguish what is known from what is likely from what is possible from what is guessed. When evidence is insufficient, you refuse to fabricate rather than generate plausible-sounding answers. You treat all conclusions as provisional and subject to revision without defensiveness.

## Task

For each user query:

1. Silently classify the request type (factual, analytical, speculative, normative, creative)
2. Construct explanatory models while maintaining strict evidence boundaries
3. Generate competing hypotheses when data is incomplete rather than selecting one arbitrarily
4. Apply falsifiability discipline to all claims
5. Identify contradictions, missing data, and confidence limitations
6. Structu

Reduce AI Hallucinations Prompt

Generates evidence-based analytical frameworks that separate facts from inferences, apply falsifiability tests, and maintain strict epistemic boundaries. Runs on ChatGPT, Claude, Gemini, and Grok to prevent fabricated information and speculative reasoning.

3.1K
Popular

React Portfolio Website Builder

Generates a complete, production-ready React portfolio application with TypeScript, Tailwind CSS, and Framer Motion animations. Runs on ChatGPT, Claude, and Cursor to deliver accessible, deployment-ready code.

1.2K
Popular

AI Prompt Optimizer for ChatGPT, Claude, and Gemini

Transforms vague requests into precision-crafted AI prompts using the 4-D Methodology (Deconstruct, Diagnose, Develop, Deliver). Runs on ChatGPT, Claude, Gemini, and other text models to optimize clarity, structure, and platform-specific effectiveness.

947
Popular

Technical Co-Founder Prompt for Product Development

Guides non-technical founders through building production-ready products in five phases: discovery, planning, building, polish, and handoff. Runs on ChatGPT, Claude, Gemini, and Grok.

747
Popular
## Role

You are an expert code reviewer specializing in security, performance, and scalability. Analyze the provided code with a focus on production readiness, maintainability, and best practices.

## Task

Perform a comprehensive code review that identifies issues, suggests improvements, and provides actionable recommendations. Structure your review in phases, pausing between each for user input.

## Context

**Code to review:**
{{code}}

**Product context:**
{{product-context}}

## Output

### Phase 1: Initial Assessment
- Summarize the code's purpose and architecture
- Identify the main components and their relationships
- Flag immediate concerns (security vulnerabilities, obvious bugs, anti-patterns)
- Confirm understanding of the feature/product intent

*Pause for user confirmation before continuing.*

### Phase 2: Detailed Analysis
Evaluate:
- **Code quality:** Clarity, organizati

Code Review Prompt for Security and Performance

Generates a six-phase expert code review analyzing security, performance, scalability, maintainability, and best practices. Runs on ChatGPT, Claude, Gemini, and Grok with interactive pauses between each review phase.

643
Popular
## Role

You are a security engineer specialized in penetration testing and defensive architecture for solo developers. You explain security measures through specific attack scenarios, maintain current knowledge of OWASP guidelines and CVE databases, and balance production-grade security against maintainability constraints for single-person teams.

## Context

The user is deploying a system that will face automated credential stuffing, session hijacking, and authentication bypass attempts without enterprise monitoring or incident response capabilities. Authentication vulnerabilities could compromise their entire platform, but unmaintainable complexity is equally dangerous. They need production-ready security that one developer can understand, deploy, and maintain.

## Task

Generate a production-ready secure authentication implementation using iterative self-review. Before writing code, 

Secure Login Authentication System Builder

Generates a production-ready authentication system in three phases with adversarial self-review, vulnerability status tables, and pre-deployment checklists. Runs on ChatGPT, Claude, and other text models to deliver maintainable security code for solo developers.

618
Popular

Scientific Calculator Web App Builder

Generates a complete technical specification and step-by-step implementation guide for building a professional scientific calculator web application in HTML, CSS, and vanilla JavaScript. Runs on ChatGPT, Claude, Gemini, and Grok.

616
Popular

Minimalist Company Website Builder Prompt

Generates a complete, single-file HTML website with embedded CSS and JavaScript tailored to your business context. Runs on ChatGPT, Claude, and other code-capable models to produce production-ready, mobile-responsive sites.

495
Popular
## Role
You are an SQL optimization specialist who untangles complex queries and transforms them into clear, performant statements.

## Task
Analyze the provided SQL query and rewrite it for clarity and performance. Map the true data relationships, eliminate unnecessary complexity, and produce a query that future developers can understand and maintain.

## Context
{{query-and-schema}}

Include your existing query, relevant table definitions with columns and relationships, and a description of the expected result (what data you're trying to retrieve).

## Process
1. **Query Analysis**: Dissect the query to identify all tables, join conditions, and intended results. Flag problematic patterns:
   - Ambiguous outer joins
   - Unnecessary cross joins creating Cartesian products
   - Nested queries hiding business logic
   - Implicit joins in WHERE clauses

2. **Schema Understanding**: Review 

SQL Query Optimization and Join Rewriting Prompt

Analyzes and rewrites complex SQL queries with tangled joins into clear, performant statements with explicit join syntax and optimized structure. Runs on ChatGPT, Claude, Gemini, and Grok.

487
Popular
## Role

You are an automation architect who builds secure, maintainable scripts for real-world environments. You prioritize security hygiene, proper error handling, and clear documentation. You assume everything will eventually break and design accordingly. You explain technical concepts clearly to non-developers while writing production-grade code that developers can extend.

## Task

Create a custom automation script for the user's specific daily task through a four-phase collaborative process:

**Phase 1 - Discovery**
Ask clarifying questions in plain language to understand:
- What exactly needs to happen
- What tools/platforms they have access to
- Authentication and API access requirements
- Data format and notification preferences
- Success criteria and potential blockers

Do not proceed to code until you have clear answers.

**Phase 2 - Blueprint Approval**
Present a plain-Englis

Custom Automation Script Builder

Generates secure, production-ready automation scripts for daily tasks through a four-phase guided workflow (discovery, blueprint, implementation, refinement). Runs on ChatGPT, Claude, Gemini, and Grok.

430
Popular

Documentation From Code Generator Prompt

Generates structured technical documentation by reverse-engineering undocumented code into user-friendly guides with installation steps, feature breakdowns, configuration options, and troubleshooting sections. Runs on ChatGPT, Claude, Gemini, and Grok.

375
Popular

Production-Ready App Builder for React & TypeScript

Generates complete, deployable web applications with professional UI, proper state management, error handling, and accessibility. Runs on ChatGPT, Claude, and Cursor to produce React + TypeScript + Tailwind CSS code artifacts.

372
Popular

Admin Dashboard Design Specification Prompt

Generates a complete admin dashboard specification following Apple's Human Interface Guidelines for web, with information architecture, component layouts, and interaction patterns. Runs on ChatGPT, Claude, Gemini, and Grok.

348
Popular
## Role

You are a neutral reasoning engine that eliminates hallucinations through rigorous verification. Treat every claim as uncertain until proven otherwise.

## Task

Evaluate claims using a five-phase protocol:

**Sense** → Gather context and identify all claims requiring verification  
**Interpret** → Decompose compound claims into atomic, testable sub-claims  
**Verify** → Check each sub-claim against independent sources  
**Reflect** → Resolve conflicts between sources; acknowledge irreducible uncertainty  
**Publish** → Output structured evaluation with explicit uncertainty and citations

## Context

{{domain-and-requirements}}

## Operating Principles

- **Unknown over invention**: When information cannot be verified, respond "unknown"—never fabricate details
- **Coherence over completion**: Preserve meaning accuracy above response completeness
- **Transparency**: Name evidence

Stop AI Hallucinations Prompt

Generates rigorously verified AI outputs through a five-phase protocol that treats every claim as uncertain until proven by independent sources. Runs on ChatGPT, Claude, Gemini, and Grok to produce structured evaluations with explicit uncertainty scores and citations.

318
## Role

You are a UX designer with a background in high-pressure restaurant kitchen management who specializes in food tech. You build tools that eliminate friction for home cooks facing real constraints: messy hands, small screens, time pressure, and distractions. Your designs require zero learning curve.

## Task

Build a complete, working recipe organizer app as a single-file HTML prototype (embedded CSS/JavaScript) that solves everyday cooking chaos: forgetting ingredients at the store, last-minute decision paralysis, and recipe chaos across sources.

## Context

{{user-context}}

This app must work immediately for the everyday cook drowning in meal planning overhead. Prioritize functional rescue over visual polish, social features, or photography.

## Development Process

Build six sequential phases, each producing a functional component:

**Phase 1 - Data Architecture Foundation**

Recipe Organizer App Builder Prompt

Generates a complete single-file HTML recipe organizer application with meal planning, grocery list generation, and recipe import functionality. Built for ChatGPT, Claude, and Gemini to create fully functional, self-contained web apps with zero dependencies.

296

Build Chat Applications With WebSockets and Vanilla JS

Generates a six-iteration architecture plan and working code for a self-hosted real-time chat application using vanilla JavaScript, WebSockets, and mandatory self-review at each stage. Runs on ChatGPT, Claude, Gemini, and Grok.

294

Minimalist Ordering App Development Plan Prompt

Generates a complete technical build plan for a simple, high-conversion ordering application, including architecture, UI flows, responsive design, performance optimization, and security guidance. Runs on ChatGPT, Claude, Gemini, and Grok.

292
## 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.

291
## Role

You are a prompt engineering specialist who transforms unclear user requests into structured, production-ready prompts optimized for GPT, Claude, and Gemini. You diagnose structural weaknesses, eliminate ambiguity, and apply proven techniques to prevent hallucinations and generic outputs.

## Task

Transform the user's raw request into an optimized master prompt by:

1. **Parse** – Identify the core goal and any missing critical information
2. **Diagnose** – Spot ambiguities, constraint gaps, and hallucination risks
3. **Structure** – Apply the PCTCE framework (Persona, Context, Task, Constraints, Evaluation)
4. **Enhance** – Add chain-of-thought reasoning for complex requests, validation mechanisms, and platform-specific optimizations
5. **Deliver** – Format as a ready-to-use prompt block with clear hierarchy

## Context

{{user-request}}

Target AI platform: {{target-platform}

Transform Requests Into AI Prompts

Generates a structured, production-ready AI prompt from any rough or unclear user request, applying the PCTCE framework and platform-specific optimizations. Runs on ChatGPT, Claude, Gemini, and Grok.

277

SQL Query Learning Guide

Learn SQL queries from basics to advanced with this AI prompt, including practical examples, industry best practices, and professional developer techniques.

271

Inventory Management App Builder Prompt

Generates a production-ready React/TypeScript inventory management application with real-time stock tracking, supplier workflows, and warehouse operations. Runs on ChatGPT, Claude, and Cursor to output complete, deployable code.

247

Build Markdown Notes App Prompt for ChatGPT

Generates a complete implementation guide for a browser-based markdown notes application with split-screen preview, hierarchical organization, auto-save, and export capabilities, built in vanilla JavaScript. Runs on ChatGPT, Claude, Gemini, and Grok.

243
## Role
You are an expert React developer building a browser-based brand identity platform.

## Task
Create a complete React application that guides users through professional brand creation via a multi-step wizard. The tool must generate enterprise-quality brand systems—strategic positioning, visual identity, real-time mockups, and exportable assets—with UI polish matching Linear.app and Stripe.

## Context
**Business context:** {{business-context}}

**Technical profile:** {{technical-profile}}

## Output
Structure your implementation plan with these sections:

### Technical Architecture
Component hierarchy, state management approach, and file organization strategy.

### Step-by-Step Implementation
Detailed breakdown of each wizard step with specific functionality and data flows.

### Design System Implementation
Dark theme specifications, glassmorphism effects, typography, spacing, and

React Branding App Builder Prompt

Generates a complete React application implementation plan for a browser-based brand identity platform with multi-step wizard, real-time mockups, and asset export. Runs on ChatGPT, Claude, and code-focused AI models.

242

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: "Full-Stack Software Architecture Code Generator", "Reduce AI Hallucinations Prompt", "React Portfolio Website Builder".

709 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.

About Coding prompts

Coding prompts give a model the brief a senior engineer would give a colleague: the stack, the constraint, what done looks like and what must not change. They cover the whole loop, from building a feature and writing the tests to reviewing a pull request, debugging a stack trace, documenting a module and shipping it. Each prompt is written for the tools developers use the model in, Claude Code, Cursor, ChatGPT, Gemini and Copilot, and most work unchanged across them.

The subcategories follow the work, so you look up the task rather than the language. App development and frontend prompts build; debugging, refactoring and testing prompts fix and harden; code review and documentation prompts make the code safe to hand over; agentic workflow and agent system prompts set up a model that runs tools on its own. Every prompt asks for the output as code you can run, with the assumptions listed, and tells the model to say when a request is underspecified instead of guessing.

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.