6215 Curated AI Prompts
Discover curated ChatGPT prompts, AI prompt templates, and prompt engineering examples for coding, writing, RAG, agents, safety, and evaluation workflows.
Editor-curated high-quality prompts
A prompt for generating a realistic studio portrait of a woman in a liquid metal silver gown using Nano Banana Pro, with specific negative prompts to avoid CGI artifacts.
Provides practical operating rules for LLM-assisted software development to reduce hallucinations, unnecessary complexity, uncontrolled modifications, architectural drift, and unsupported claims of completion.
Prompt from prompts.chat: Web Accessibility taste
Ranked by site-wide copy counts; falls back to editor picks when empty
Prompt Library
Checks and fixes structural, required property, date-time, timezone, and recurrence issues in iCalendar (.ics) files.
A test prompt created to verify API authentication. It is safe to delete.
Profiles CSV and spreadsheet data before trusting it for analysis, imports, or dashboards, infers column types, measures missing values, duplicates, mixed types, outliers, whitespace, and encoding issues, and generates a prioritized quality report with concrete fixes.
Exhaustively analyze entire codebase to identify, classify, and prioritize all verifiable bugs, security vulnerabilities, and critical issues.
As a QA engineer, review the algorithmic trading project for logic correctness, efficiency, historical data validation, and compliance, providing improvement recommendations.
Automatically generate comprehensive unit tests for a provided Django ViewSet class, covering CRUD operations, edge cases, and permission issues.
Build a fully-featured URL shortening service frontend with input validation, QR code generation, click tracking, custom aliases, expiration dates, password protection, and more.
Generate accurate regular expressions based on specified patterns, focusing solely on precision without explanations or examples.
Act as a Python interpreter, execute code and output only results.
Act as a plagiarism checker, replying only with 'undetected' for plagiarism checks.
Turn a coding task into the smallest, safest Claude Code loop primitive that runs until a verifiable stop condition is met.
Reconstruct prompt-heavy enterprise LLM prototypes into a traceable, auditable, code-owned agent architecture by moving behavior into manifests, schemas, validators, and runtime gates.
Showing 12 of 97