Complete Website JSON-LD Schema Markup Generator
Generate connected @graph JSON-LD schema (Organization, WebSite, BreadcrumbList, Article, HowTo, Product, Speakable) for any webpage.
Search prompts, categories, platforms and repositories
This library holds 520 original prompts for 25 AI platforms, grouped into 20 job-based categories. Use the filters to narrow by tool, category and difficulty, then open any prompt to fill in its variables and copy a version tuned for the model you use. Every page includes a worked example and the mistakes to avoid.
Generate connected @graph JSON-LD schema (Organization, WebSite, BreadcrumbList, Article, HowTo, Product, Speakable) for any webpage.
Generate spec-compliant /llms.txt and /llms-full.txt Markdown files so AI models accurately summarize and cite your entire website.
A system prompts prompt for write a system prompt for a coding assistant. It gives Claude and ChatGPT a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
A data analysis prompt for write Python to explore a CSV. It gives ChatGPT and DeepSeek a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
This copy-ready coding prompt helps you write a seed script for a database with fewer blank-page decisions. Paste it into ChatGPT and Cursor, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
A coding prompt for convert a class component to hooks. It gives Cursor and ChatGPT a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Optimise an N+1 query with a prompt built for Claude and Cursor. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
A coding prompt for create a TypeScript type from messy JSON. It gives ChatGPT and Cursor a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
This copy-ready coding prompt helps you fix a flaky test with fewer blank-page decisions. Paste it into Cursor and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
A coding prompt for convert a design into accessible components. It gives v0 and Cursor a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Add authentication to an existing app with a prompt built for Cursor and Claude. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
A coding prompt for hunt a performance bottleneck. It gives Cursor and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
A coding prompt for explain an unfamiliar codebase. It gives Claude and Cursor a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Generate unit tests that fail before the fix with a prompt built for Cursor and Claude. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
This copy-ready coding prompt helps you refactor for readability without changing behaviour with fewer blank-page decisions. Paste it into Cursor and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
A coding prompt for review a pull request by severity. It gives Claude and Cursor a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
This copy-ready coding prompt helps you debug an error with a minimal reproduction with fewer blank-page decisions. Paste it into Cursor and Claude, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.