The AI Prompt Library for Creators.
Hundreds of tested prompts for image gen, video gen, and text AI. Copy, paste, create. New prompts added weekly.
Mar27, 2026
How Claude Code Works: Complete Guide with Diagrams (2026)
How Claude Code works: the complete guide (2026) Claude Code is an AI coding agent that lives in your terminal. Unlike chatbots where you copy-paste code back and forth, Claude Code operates directly inside your development environment — it reads your files, understands your project structure, writes code, runs tests, handles git workflows, and even submits pull requests. All through natural language commands. Think of it as having a senior developer sitting beside you who can see your entire codebase, execute commands, and make changes — but you stay in control of what gets approved. This guide covers everything from installation to advanced features like auto mode, voice control, agent teams, and scheduled tasks with /loop. Whether you're a beginner or an experienced developer, you'll understand exactly how Claude Code works by the end. What is Claude Code? Claude Code is Anthropic's command-line AI coding agent. It uses Claude's language models (Opus 4.6 and Sonnet 4.6 as of March 2026) to understand your codebase and perform development tasks autonomously. It's not a code completion tool like GitHub Copilot — it's a full agent that can plan, execute, test, and iterate on complex multi-file changes. The core difference is agency. Code completion tools suggest the next line. Claude Code understands the entire project and executes complete workflows: "Add a user authentication system with OAuth, write tests, and submit a PR" — and it does all of it. How Claude Code works: the core loop [INFOGRAPHIC: Create a flowchart showing the Claude Code workflow loop] Step 1: You type a natural language command in the terminal Step 2: Claude Code scans your codebase using agentic search Step 3: It creates a plan and starts executing (reading files, writing code, running commands) Step 4: It asks for your permission before making changes (unless auto mode is on) Step 5: It runs tests, checks for errors, and iterates Step 6: You approve, and it commits via git Every interaction follows this pattern. You describe what you want, Claude Code figures out how to do it, and you approve the changes. The permission system ensures nothing happens to your code without your knowledge. Installation (all platforms) Getting Claude Code running takes under 5 minutes. Here are the commands for each platform: macOS and Linux: curl -fsSL https://claude.ai/install.sh | bash Windows (PowerShell): irm https://claude.ai/install.ps1 | iex Alternative (npm — any platform): npm install -g @anthropic-ai/claude-code After installation, open a new terminal and type claude to start. You'll be prompted to log in with your Claude account (Pro, Max, Team, or Enterprise) or an Anthropic API key. Verify installation: claude --version The native installer doesn't require Node.js — it downloads a self-contained binary. Only the npm method requires Node.js 18+. Your first session Navigate to your project folder and launch Claude Code: cd ~/my-project claude You'll see an interactive prompt where you can type natural language commands. Here are some starter examples: What does this project do? Explain the main architecture. Add a user settings page where users can update their email and password. Follow the existing patterns in this codebase. Write unit tests for the OrderProcessor class covering success and failure scenarios. Find and fix the bug where the checkout page crashes when the cart is empty. Claude Code reads your files, understands the relationships between them, and executes changes across multiple files simultaneously. CLAUDE.md — teaching Claude about your project The single most impactful thing you can do is create a CLAUDE.md file in your project root. This gives Claude persistent context about your codebase that it can't infer from code alone — build commands, conventions, architecture decisions, and testing instructions. Generate one automatically: /init This analyzes your codebase and creates a starter CLAUDE.md. Here's an example of what a good one looks like: markdown # CLAUDE.md ## Commands - `npm run dev` - Start dev server on port 3000 - `npm run build` - Production build - `npm test` - Run Jest tests - `npm run lint` - ESLint check ## Architecture - Next.js 15 with App Router - PostgreSQL with Drizzle ORM - Authentication via Clerk - All API routes in src/app/api/ ## Conventions - Server components by default; use "use client" only when needed - TypeScript strict mode; no any types - Commit messages: imperative mood, under 72 chars Keep it concise — aim for 50 to 100 lines. For monorepos, add a CLAUDE.md in each subdirectory. Claude loads them hierarchically. Key features of Claude Code in 2026 [INFOGRAPHIC: Create a feature map / capability grid showing all 12 features] Core: Terminal CLI, Codebase understanding, Multi-file editing, Git integration Interfaces: VS Code extension, JetBrains plugin, Web interface, Desktop app Advanced: Voice mode, Auto mode, Agent Teams, /loop scheduled tasks, Remote Control, Computer Use Configuration: CLAUDE.md, MCP servers, Hooks, Skills Claude Code has evolved from a simple terminal tool into a full autonomous coding agent platform. Here's what each major feature does: Permission modes Claude Code offers three permission modes that control how much autonomy it has: Default mode asks for approval on every file write and bash command. Safe but requires constant attention. Auto mode (launched March 2026) lets Claude make low-risk permission decisions on its own. A dedicated AI safety classifier reviews every tool call before execution, blocking dangerous actions like mass file deletion or sensitive data access. Enable it with: claude --enable-auto-mode Then cycle to it with Shift+Tab during a session. Auto mode is the recommended middle ground for most development work. Skip permissions (--dangerously-skip-permissions) bypasses all checks. Only use this in isolated containers or sandboxes — never on a real codebase. Voice mode Activated with the /voice command, voice mode uses push-to-talk — hold the spacebar to speak, release to send. It supports 20 languages as of March 2026 and is great for dictating complex requirements or working hands-free. /voice The key is customizable through keybindings.json. Voice mode isn't "always listening" — it only records while you hold the key, making it precise and privacy-respecting. Agent teams (research preview) Agent Teams let you spawn multiple Claude Code instances that collaborate on a task. A team lead coordinates teammates, each working on different parts of the codebase simultaneously. Enable it with: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 claude This is particularly powerful for large refactors or feature implementations that span many files. /loop — scheduled recurring tasks The /loop command turns Claude Code into a background worker that runs on a schedule, similar to cron jobs. Use it for automated PR reviews, deployment monitoring, or periodic code quality checks. This is one of the most practical new features — it transforms Claude Code from an interactive tool into an always-on development assistant. Remote control Start Claude Code on your local machine, then control it from anywhere — your phone, tablet, or another computer — through the claude.ai/code web interface or the iOS/Android apps. Your code never leaves your local machine; only chat messages are transmitted through an encrypted channel. 1 million token context window Available on Max, Team, and Enterprise plans, the 1M token context window lets Claude Code hold your entire codebase in context at once. For large projects, this eliminates the need for repeated context-setting. Thinking levels Claude Code supports different "thinking" depths for complex problems: /effort high For the deepest reasoning, use "ultrathink" — Claude spends more time planning before acting, producing better results on complex architectural decisions. MCP (Model Context Protocol) servers MCP servers extend Claude Code's capabilities by connecting it to external tools and data sources — GitHub, databases, deployment platforms, monitoring dashboards, and more. Claude Code can then read issues, query databases, check deployment status, and take actions across your entire development stack. Available interfaces [INFOGRAPHIC: Show the 4 ways to use Claude Code] Terminal CLI: Most features, maximum flexibility VS Code extension: Visual diffs alongside your code (also works in Cursor and Windsurf) JetBrains plugin: For IntelliJ, WebStorm, RubyMine users Web interface: Quick access from any browser, works with GitHub repos Desktop app: Skip the terminal entirely (macOS and Windows) Pricing plans Claude Code is included in your Claude subscription. Here's what each plan offers: Pro ($20/month): Basic Claude Code access. Good for learning and small-to-medium projects. Rate limits apply during heavy use. Max 5x ($100/month): Approximately 88,000 tokens per 5-hour window. Priority access during peak times. Best for developers using Claude Code regularly. Max 20x ($200/month): Approximately 220,000 tokens per 5-hour window. Rate limits are rarely a concern. For power users and full-time AI-assisted development. Team and Enterprise: Higher limits, admin controls, auto mode management, and organization-wide settings. API (pay-per-use): Direct token billing through the Anthropic Console. Can be cost-efficient for light usage but expensive for heavy daily use. Common use cases Here are real workflows where Claude Code excels: Understanding a new codebase: "Explain this project's architecture. What are the main modules and how do they interact?" Feature development: "Add a notification system with email and in-app channels. Follow the existing patterns." Bug fixing: "Users report that search results are empty after filtering by date. Find and fix this." Refactoring: "Refactor the UserController to use service objects instead of putting business logic in the controller." Writing tests: "Write comprehensive unit tests for the payment processing module covering edge cases." Git workflows: "Review my changes, create a meaningful commit message, and open a PR." Code review: "Review the latest PR and flag any security concerns or performance issues." Claude Code vs other AI coding tools Claude Code vs Cursor: Cursor is an IDE (VS Code fork) with AI built in. Claude Code is an agent that works alongside any IDE. Cursor is better for inline completions; Claude Code is better for complex multi-file changes and autonomous workflows. Claude Code vs GitHub Copilot: Copilot suggests code as you type. Claude Code executes entire tasks autonomously — reading issues, writing code, running tests, and submitting PRs without you touching the keyboard (in auto mode). Claude Code vs Gemini CLI: Google's Gemini CLI is free (1,000 requests/day) and good for lighter tasks. Claude Code with Opus 4.6 produces better results on complex multi-file reasoning tasks and large codebase navigation. Tips for getting the best results Getting consistently good output from Claude Code comes down to a few habits. Be specific about what you want — "add authentication" is vague while "add Google OAuth login using the existing Clerk setup, following the pattern in src/auth" gives Claude precise context. Always create a CLAUDE.md file. Start with /init and refine it over time. The better Claude understands your project conventions, the better its code matches your style. Use thinking levels for complex decisions. Quick fixes work fine with default effort, but architectural changes benefit from /effort high or ultrathink mode. Review changes before approving. Even in auto mode, periodically check what Claude has done. The safety classifier catches dangerous actions, but code quality review is still your responsibility. Break large tasks into smaller ones. "Build an e-commerce platform" will produce mediocre results. "Add the product listing page with filters, using the existing database schema" gives Claude a clear, bounded task. Frequently asked questions Is Claude Code free? No. Claude Code requires a paid Claude subscription (Pro at $20/month minimum) or an Anthropic API key with credits. There's no free tier, but Google's Gemini CLI is a free alternative for lighter workloads. Does Claude Code work on Windows? Yes. As of 2026, Claude Code has native Windows support through PowerShell. You can also use it through WSL (Windows Subsystem for Linux) or Git Bash. Can Claude Code access the internet? Claude Code can run any command-line tool available on your system, including curl, wget, and git. Through MCP servers, it can connect to APIs, databases, and external services. It doesn't browse the web by default, but it can be configured to access external resources. Is my code sent to Anthropic's servers? Claude Code sends your code context to Anthropic's API for processing, similar to how any AI coding tool works. For remote control sessions, only chat messages are transmitted — files stay on your local machine. Enterprise plans offer additional data handling controls. What programming languages does Claude Code support? Claude Code works with any programming language. It's particularly strong with Python, JavaScript/TypeScript, Go, Rust, Java, C++, Ruby, PHP, and Swift, but it can handle any language it encounters in your codebase. What is the CLAUDE.md file? CLAUDE.md is a markdown file in your project root that gives Claude persistent context about your codebase — build commands, architecture decisions, coding conventions, and testing instructions. It's the single most impactful optimization for getting better results from Claude Code. What is auto mode in Claude Code? Auto mode (launched March 2026) lets Claude approve and execute file edits and bash commands without asking for permission each time. An AI safety classifier monitors every action, blocking dangerous operations like mass file deletion or data exfiltration. Getting started today The fastest path from zero to productive with Claude Code: Install it: curl -fsSL https://claude.ai/install.sh | bash Navigate to your project: cd ~/my-project Start Claude Code: claude Generate your CLAUDE.md: /init Ask your first question: "What does this project do? Explain the architecture." Try a real task: "Write unit tests for the main module." From there, explore voice mode (/voice), try auto mode for longer tasks, and connect MCP servers for your development stack. Claude Code is one of those tools where the more you use it, the more you discover what it can do.
Read More
Mar27, 2026
5 AI Watch Photography Prompts for Stunning Product Shots
5 AI Prompts for Jaw-Dropping Watch Product Photography (Copy & Paste) Luxury watch photography used to require a studio, a photographer, and a budget that could buy the watch itself. Not anymore. With AI image generators like Google AI Studio (Gemini), you can create commercial-grade watch product shots in minutes — no camera, no lighting rig, no retouching. All you need is the right prompt. Below are 5 tested prompts that produce stunning watch photography across different styles: action, underwater, cosmic, studio, and luxury. Each prompt is ready to copy and paste directly into Google AI Studio or any AI image generator. What makes a great AI watch photography prompt? Before diving into the prompts, here's what separates a mediocre AI product shot from one that looks like a real ad campaign. Your prompt needs to specify five things clearly: the subject and its material details, the environment or scene, the camera angle and composition, the lighting setup, and the mood or atmosphere you want to convey. Miss any of these and the AI fills in the blanks with generic choices. The prompts below follow this exact structure, which is why they consistently produce professional results. Prompt 1: Explosion action shot This prompt creates a dramatic, high-energy scene that conveys durability and resilience — perfect for rugged or adventure watch brands. Best for: Action watches, sports brands, social media ads A close-up, low-angle shot captures a watch suspended in mid-air amidst an explosion. The watch, a metallic brown with a dark face, is positioned slightly off-center to the right, with its band extending downwards. The explosion behind it is a chaotic blend of fiery orange and yellow light, with debris and smoke filling the background. Rocks and fragments of various sizes are scattered around the watch, some appearing to be in motion, adding to the dynamic and destructive atmosphere of the scene. The lighting is dramatic, with the bright explosion illuminating the watch and casting shadows, creating a sense of intense action and resilience. Why it works: The low-angle perspective makes the watch look powerful and dominant. The explosion backdrop creates visual tension that grabs attention on social media feeds. The specific mention of "metallic brown with a dark face" gives the AI a clear material reference to work with. Customization tips: Replace "metallic brown" with your watch color (silver, gold, black). Swap "explosion" with "avalanche," "sandstorm," or "lightning strike" for different action vibes. Prompt 2: Underwater deep sea shot This one places the watch in an underwater coral reef scene — ideal for dive watches or waterproof product marketing. Best for: Dive watches, waterproof products, lifestyle brands A watch with a black dial is submerged underwater, surrounded by coral and seaweed. The light filters down from the surface, creating a shimmering effect on the water and illuminating the watch. The composition is centered on the watch, with the natural elements framing it. Why it works: The underwater setting instantly communicates water resistance without saying the words. Natural light filtering from above creates beautiful caustic patterns that add realism. Coral and seaweed framing the watch adds organic texture that contrasts beautifully with the metallic surface. Customization tips: Add "tropical fish swimming in the background" for more life. Specify "deep ocean blue tones" or "turquoise shallow water" to control the color mood. Mention "bubbles rising from the watch" for extra realism. Prompt 3: Milky Way galaxy night shot A dramatic night sky composition that positions the watch against the cosmos — great for premium or aspirational branding. Best for: Luxury watches, premium brands, editorial content A close-up, low-angle shot features a black-faced band resting on rough, dark rocks. Behind the watch, the night sky is visible, with the Milky Way galaxy stretching across the frame and numerous stars twinkling. The horizon line, where the sky meets the distant landscape, shows a faint glow of sunset or sunrise. The lighting is dramatic, with the watch illuminated from the front and the background softly lit by the celestial display. Why it works: The contrast between the rugged rock foreground and the infinite galaxy background creates a powerful visual metaphor: precision engineering meets the vastness of nature. The sunset/sunrise glow on the horizon adds warmth and depth to an otherwise cold scene. Customization tips: Replace "Milky Way" with "northern lights" or "meteor shower" for seasonal variations. Add "reflection of stars on the watch crystal" for extra detail. Specify "warm amber front lighting" or "cool blue moonlight" to shift the mood. Prompt 4: Premium studio driftwood shot A classic luxury product photography setup — the watch on natural driftwood with premium studio lighting. This is the closest to what a real commercial shoot would produce. Best for: E-commerce product pages, brand websites, print ads Studio product photography of an elegant product replacing the watch, placed on a rugged, textured driftwood sculpture. Background is a smooth, dark chocolate-brown gradient with soft fall-off lighting. The product is centered, hero-style, with dramatic spotlight from above creating subtle highlights and deep shadows. Lighting: premium studio lighting, crisp reflections, soft rim light, rich contrast, glossy highlights. Mood: luxury, masculine, earthy, sophisticated. Foreground: natural driftwood base with rich organic texture, high detail, matte finish. Composition: product perfectly balanced on the driftwood peak, clean minimal layout, negative space around. Typography area should be clean and unobstructed. Style: ultra-realistic, high-end commercial watch advertisement, premium color grading, 8K detail, sharp focus. Why it works: This prompt is structured like a real creative brief with separate sections for lighting, mood, foreground, and composition. The "typography area should be clean and unobstructed" instruction is a smart addition — it leaves space for adding text in post-production, making the image immediately usable for ads. Customization tips: Swap "driftwood" with "marble slab," "raw concrete block," or "polished obsidian" for different textures. Change "chocolate-brown gradient" to "deep navy" or "charcoal black" for cooler tones. Pro tip: If you're using Google AI Studio with image references, add @img1 at the end and upload your actual watch photo. The AI will integrate your real product into the scene. Prompt 5: Gold dust luxury flat lay A top-down luxury composition with dark rocks and gold dust — moody, atmospheric, and perfect for premium social media content. Best for: Instagram posts, luxury branding, dark-mode aesthetics A top-down shot features a watch with black accents, placed centrally on a bed of dark, rough-textured rocks. The rocks are interspersed with shimmering gold dust, creating a dramatic and luxurious contrast. The lighting is moody and atmospheric, with subtle smoke or mist effects adding to the overall dramatic composition. Why it works: The top-down angle is the classic flat lay composition that performs extremely well on Instagram. Gold dust against dark rocks creates a luxury palette without any other props needed. The smoke/mist adds atmosphere and makes the image feel more cinematic than a standard product photo. Customization tips: Replace "gold dust" with "rose gold flakes," "silver particles," or "crushed gemstone dust" for color variations. Add "single spotlight from the top left" for more directional drama. Try "volcanic black sand" instead of rocks for a smoother texture. How to use these prompts These prompts work best with Google AI Studio (Gemini), but you can also use them in Midjourney, DALL-E, or Stable Diffusion with minor adjustments. For Google AI Studio specifically, open aistudio.google.com, select an image generation model, paste the prompt, and generate. If you want to use your own watch product image, upload it and add @img1 at the end of the prompt — the AI will integrate your real product into the generated scene. For Midjourney, add --ar 4:5 --v 6 --style raw at the end. For DALL-E through ChatGPT, paste the prompt as-is. For Stable Diffusion via ComfyUI, use these as the positive prompt and add "blurry, low quality, distorted" as the negative prompt. Tips for better AI watch photography Getting consistently great results from AI product photography comes down to a few principles. Always specify the watch material (stainless steel, titanium, ceramic, gold) because it dramatically affects how the AI renders reflections and highlights. Mention the dial color explicitly — "black sunburst dial" produces very different results from just "black dial." Include camera terminology in your prompts. Phrases like "shot on Hasselblad H6D," "85mm f/1.4," or "macro lens detail" push the AI toward photorealistic rendering. Finally, describe the lighting direction, not just the type — "spotlight from upper right" gives the AI much more precise information than just "dramatic lighting." Frequently asked questions Can I use AI-generated watch photos commercially? Images generated through Google AI Studio, Midjourney, and DALL-E are generally cleared for commercial use under their respective terms of service. However, if your AI-generated image closely resembles a specific real watch brand's trademarked design, exercise caution. These prompts create generic watch designs, not replicas of existing brands. Which AI tool produces the best watch product photos? As of 2026, Google AI Studio (Gemini) produces the most photorealistic product shots, especially when you upload a reference image. Midjourney v6 excels at artistic and atmospheric compositions. DALL-E 3 is the most accessible option through ChatGPT. Can I use my own watch photo with these prompts? Yes. In Google AI Studio, upload your product image and add @img1 at the end of the prompt. The AI will place your real watch into the generated scene while matching lighting and reflections. Prompt 4 (the driftwood studio shot) already includes this instruction. Do I need to edit the AI images afterward? For social media content, the raw AI output is usually good enough. For e-commerce product pages or print ads, minor touch-ups in Photoshop or Canva (color correction, sharpening, adding your logo) will make the images look fully professional.
Read More