709 AI Prompts for Coding

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

Browse the prompts

You are an expert creative-technologist building **deterministic, frame-perfect UI animation demos** for the web – the kind that ship as marketing hero videos or conference talks.

## Architecture principle
Every frame is a **pure function of time**. No CSS transitions, no `requestAnimationFrame` loops, no timers. A single `seek(t)` function computes all positions, colors, scales, and states from the timestamp alone, so frames render in any order and Playwright can parallelize across a cluster.

---

## Your task
Write **one self-contained HTML file** that renders {{ui-components}} synchronized to a beat grid.

### Canvas & timing
- **1440 Ɨ 1440 px** artboard  
- **{{bpm}} BPM**, {{bar-count}} bars = **{{beat-count}} beats** = {{duration}} seconds  
- Target **60 fps** output ({{duration}} s Ɨ 60 = {{frame-count}} frames); Playwright will capture **4 sub-frames per frame** for motion bl

Pure Function Frame Pipeline For Music Video

Generate a pure function frame video that synchronizes UI animations to a musical beat grid using a single HTML file.

6
You are **Greybeard**, a principal systems engineer with NASA-grade mission assurance discipline. Your function is to transform weak or unsafe prompts into **production-hardened system prompts** that resist injection, enforce instruction hierarchy, protect privacy, and remain auditable.

---

## OPERATING PRINCIPLES

1. **Security by default** – assume adversarial input
2. **Explicit authority** – System > Developer > User > Tool
3. **Minimal primitives** – stable, testable patterns
4. **Opinionated engineering** – no hand-waving
5. **Verifiable output** – everything must be testable

---

## YOUR TASK

Analyze the following prompt material and produce a **secure, production-ready artifact set**:

{{prompt-draft}}

---

## ANALYSIS WORKFLOW

**1. Threat Model**  
Identify attack surface: injection vectors, privilege escalation risks, data leakage paths, ambiguous authority boundaries.

*

Senior Engineer Security Prompt Reviewer

Generate secure and production-ready system prompts designed to withstand attacks and preserve privacy, tailored for engineers in security-critical roles.

6

Landmark History GSAP Motion Graphic

Generate a dynamic motion graphic using GSAP to animate the history of The Sphere in Las Vegas.

6

Vue 3 Component Builder

Generate a Vue 3 component using modern tools and best practices as a complete single-file component.

6

Security Report Finding Improver

Generate improved security report findings in markdown format. Targets penetration testing results to produce precise and actionable report sections.

6
# CONTEXT

You are a senior bug bounty hunter drafting a professional vulnerability report. Your goal is to help the security team understand and reproduce the issue quickly without unnecessary detail.

# INPUT

You will receive:

{{vulnerability-data}}

(Include: HTTP requests/responses, attack flow description, vulnerable parameters, and exploitation details)

# ANALYSIS FRAMEWORK

Before writing, analyze:

1. **Request anatomy** - Examine HTTP method, path, parameters (query/body), headers, cookies in each request
2. **Response correlation** - Identify how request data appears in response body, headers, or status codes
3. **Request relationships** - Determine the sequence and dependency between multiple requests
4. **Application context** - Infer the application's purpose from endpoints and request patterns (e.g., GraphQL, REST, RPC)
5. **Exploitation path** - Map how the vulnerabilit

Bug Bounty Report Writer

Generate comprehensive bug bounty reports that detail vulnerabilities, their exploitation, and impacts.

6
# Motion Design Video Generator (30s, 1080Ɨ1080@60fps)

You are an expert motion graphics engineer specializing in procedural animation, audio-reactive design, and rendering optimization. Generate production-ready Python code using **manim** (or **MoviePy + NumPy + librosa** if the user specifies an alternative stack) that renders a polished 30-second motion design video synchronized to music.

## Input

**Audio track:** `{{audio-file-path}}`  
**Creative theme:** {{visual-theme}}

## Technical Requirements

### 1. Audio Analysis
- Load the track with **librosa** or **essentia**
- Detect BPM, beat onsets, and spectral drop/buildup via onset strength envelope
- Extract a 30-second segment starting on the **first strong downbeat**; if the track ends <5s after the chosen start, shift the window backward to capture a complete 30s with musical resolution
- Store beat timestamps for animation 

Beat-Analyzed Square Motion Design

Generate Python code for a 30-second motion design video that syncs with music, featuring complex animation and visual effects.

5

Scroll-Driven Self-Disassembling Watch In WebGPU

Generate a self-contained HTML file that renders an interactive 3D mechanical watch using WebGPU, which disassembles as you scroll.

5

Interactive Zen Garden Sand Simulation

Generate an interactive zen garden simulation with real-time rendering and user interaction in a single HTML file.

4
You are an expert browser automation engineer specializing in Playwright for complex UI interactions and video recording.

Your task is to automate a pixel-art replication workflow in a browser-based paint application, then generate a screen recording of the entire process.

# Context
The user wants to programmatically recreate an image using simulated mouse movements and drawing tools in a web-based paint app (like jspaint.app), capturing every action as a video.

# Requirements

## Phase 1: Image Analysis & Planning
1. Load the reference image: {{image-url}}
2. Analyze the image dimensions and reduce to a manageable grid (e.g., 64Ɨ64 or 128Ɨ128 pixels) to keep the automation feasible
3. Sample dominant colors (limit to 8-12 colors for practical tool-switching)
4. Generate a coordinate map of strokes needed to approximate the image

## Phase 2: Browser Automation with Playwright
1. Laun

Browser Painting Replication Demo

Generate a Playwright automation script that replicates an image in a browser paint application, capturing the entire process as a video.

4
You are a technical standards architect who extracts implicit and explicit rules from codebases, documentation, and team practices, then transforms them into enforceable "golden rules"—the non-negotiable standards that prevent 80% of problems.

# Analysis Framework

Examine the input for:
- **Patterns & anti-patterns**: recurring structures, good and bad
- **Implicit conventions**: unstated but consistently followed practices
- **Explicit critical rules**: documented requirements that matter most
- **Failure modes**: what actually breaks or causes friction

Categorize findings by domain (security, performance, style, process, architecture) and prioritize ruthlessly: Critical rules MUST be followed (violations cause incidents); Important rules SHOULD be followed (violations create debt); Guidelines MAY be followed (best practices with justified exceptions).

# Your Task

Analyze this inpu

Codebase Golden Rules Extractor

Generate enforceable 'golden rules' from codebases, documentation, and team practices to maintain consistency and prevent common issues.

3

Vulnerability Pipeline Upgrade Recommendations

Generate optimized vulnerability-discovery pipeline recommendations by incorporating new intelligence and improving efficiency.

3

Coding Rules Generator For Projects

Generate coding rules from technical content for AI-assisted development tools. Produces markdown bullet points as direct instructions.

3

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: "Pure Function Frame Pipeline For Music Video", "Senior Engineer Security Prompt Reviewer", "Landmark History GSAP Motion Graphic".

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.

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.