80 Best AI Coding Prompts
for Claude, ChatGPT & Cursor

I have a bug. Here's what's happening: Expected behavior: [WHAT SHOULD HAPPEN] Actual behavior: [WHAT IS HAPPENING INSTEAD] Error message (if any): [PASTE ERROR] Steps to reproduce: [HOW TO TRIGGER IT] Code: [PASTE RELEVANT CODE] Find the root cause. Don't just fix the symptom — explain why this happens, then show the fix.Copy

I'm getting this error: [PASTE FULL ERROR MESSAGE AND STACK TRACE] Context: - Language/framework: [e.g., Python 3.12 / Next.js 15 / Go 1.22] - What I was doing when it happened: [DESCRIBE] - Relevant code: [PASTE] Explain: what this error means in plain English, what's causing it in my specific code, and how to fix it. If there are multiple possible causes, list them in order of most likely.Copy

This code is too slow. Help me find and fix the performance bottleneck. Observed performance: [e.g., "takes 8 seconds for 1000 records, should be under 500ms"] Environment: [language, database, any relevant infrastructure] Code: [PASTE CODE] Look for: N+1 queries, unnecessary loops or nested loops, missing indexes, synchronous calls that could be parallel, redundant computations, and memory allocation issues. For each problem found, show the fix and estimate the improvement.Copy

Review this code as a senior engineer. Find: 1. Bugs or logic errors 2. Security vulnerabilities (injection, auth issues, data exposure, insecure defaults) 3. Performance problems (N+1 queries, unnecessary loops, memory leaks) 4. Readability and maintainability issues 5. Missing error handling for failure cases that can happen For each issue: describe it, explain why it's a problem, and show the fix. Prioritize by severity: Critical → High → Medium → Low. Code: [PASTE CODE]Copy

Perform a security audit of this code. Focus on OWASP Top 10 vulnerabilities: 1. Injection (SQL, command, LDAP, XPath) 2. Broken authentication / session management 3. Sensitive data exposure 4. XML external entities (XXE) 5. Broken access control 6. Security misconfiguration 7. Cross-site scripting (XSS) 8. Insecure deserialization 9. Using components with known vulnerabilities 10. Insufficient logging/monitoring For each vulnerability found: severity (Critical/High/Medium/Low), where it is in the code, the attack vector, and the fix. Code: [PASTE CODE]Copy

Refactor this code to be cleaner and more maintainable. Preserve all existing behavior — no functionality changes. Goals: - Better variable and function names (self-documenting) - Reduce function length (aim for single responsibility) - Remove duplication (DRY) - Improve readability (anyone should understand it in 30 seconds) - Add error handling where it's obviously missing Show the refactored code with brief comments on the main changes you made. Code: [PASTE CODE]Copy

Refactor this code to use [PATTERN: async/await / repository pattern / dependency injection / factory pattern / observer pattern / CQRS]. Current code: [PASTE CODE] Language/framework: [SPECIFY] Show: 1. The refactored code 2. A brief explanation of what changed and why this pattern is better here 3. Any tradeoffs or things I should watch out forCopy

Write comprehensive unit tests for this function/module. Testing framework: [Jest / Pytest / Go testing / RSpec / etc.] Language: [SPECIFY] Code to test: [PASTE CODE] Cover: - Happy path (normal inputs → expected output) - Edge cases (empty input, zero, null, max values) - Error cases (invalid input, exceptions) - Boundary conditions Each test: descriptive name that states what it tests and what it expects. Group related tests. Mock external dependencies.Copy

Write integration test scenarios for [FEATURE/ENDPOINT/FLOW]. System description: [WHAT IT DOES, WHAT IT CONNECTS TO] Tech stack: [LANGUAGE, FRAMEWORK, DATABASE] Identify and write tests for: 1. The full success path from input to output 2. Authorization: what should be blocked for different user roles 3. Data validation: what invalid inputs should be rejected 4. Failure handling: what happens when dependencies (DB, external API) fail 5. Concurrency: any race conditions or locking issues Write test code, not just descriptions.Copy

Write API documentation for this endpoint/function. Code: [PASTE FUNCTION OR ENDPOINT] Documentation should include: - One-sentence description of what it does - Parameters: name, type, required/optional, description, example value - Returns: type, structure, example response - Errors: error codes/exceptions, when they occur, how to handle them - Example: a complete working example call with realistic data - Any rate limits, auth requirements, or side effects Format: [Markdown / OpenAPI YAML / JSDoc / Python docstring]Copy

Write a professional README for this project. Project name: [NAME] What it does: [ONE SENTENCE] Tech stack: [LANGUAGES, FRAMEWORKS, DATABASES] Target users: [WHO USES IT] README sections: 1. Project description (2-3 sentences, no marketing fluff) 2. Features list (what it actually does) 3. Installation (step-by-step, from clone to running) 4. Usage (basic usage with real code examples) 5. Configuration (environment variables, config options) 6. Contributing (brief) 7. License Write for a developer who has never seen this project before.Copy

Generate boilerplate code for [WHAT YOU'RE BUILDING]. Tech stack: [LANGUAGE + FRAMEWORK + DATABASE] Requirements: - [REQUIREMENT 1] - [REQUIREMENT 2] - [REQUIREMENT 3] Include: - Project structure (file tree) - Core files with proper boilerplate - Basic error handling patterns - Environment variable setup - Comments explaining where to add custom logic Do NOT include: placeholder TODO comments without explanation, hardcoded credentials, or unnecessary abstractions.Copy

Design a database schema for [APPLICATION/FEATURE]. Database: [PostgreSQL / MySQL / SQLite / MongoDB] What it needs to store: [DESCRIBE YOUR DATA AND RELATIONSHIPS IN PLAIN ENGLISH] Requirements: - [SCALE / QUERY PATTERNS / CONSTRAINTS] Provide: 1. Schema with table/collection definitions, field types, constraints, and indexes 2. Key relationships (foreign keys, references) with explanation 3. Indexes and why they're included 4. Any denormalization decisions and why 5. SQL to create the schema (or schema definition for document DBs)Copy