ModelRefs / Best AI Prompts: Library, Frameworks & Templates

Best AI Prompts: Library, Frameworks & Templates

The ModelRefs prompt library. Categorized prompts for writing, coding, analysis, marketing, and research — with frameworks, ratings, and model compatibility.

What this reference supports

Best AI Prompts: Library, Frameworks & Templates: This hub organizes related ModelRefs references into a crawlable starting point. Use it to narrow the problem, identify relevant profiles or guides, and continue into detailed evidence and implementation material.

Best AI Prompts: Library, Frameworks & Templates: Items are connected across models, providers, benchmarks, workflows, tools, and guides. Those relationships explain where an option fits, what it depends on, and which adjacent decisions still need validation.

Best AI Prompts: Library, Frameworks & Templates: Catalogue presence is not an endorsement or universal ranking. Compare candidates against your own requirements and review each page's sources, freshness notes, limitations, and coverage gaps.

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Best AI Prompts: Library, Frameworks & Templates.

Frequently asked questions

What makes a 'good' prompt?

Clarity of role, explicit format, concrete examples, and constraints that fail loudly. If a prompt only works on one model, it's not a prompt — it's a fragile incantation.

Do prompts transfer between models?

Mostly. Frontier models (GPT-5, Claude, Gemini) handle the same patterns, but system prompt placement and tool-calling syntax differ. Each prompt in our library is tagged with confirmed compatibility.

Should I use prompt frameworks like CRISPE?

Frameworks help beginners write structured prompts and help teams standardize. Once you're fluent, you'll mix techniques rather than follow one framework dogmatically.

How do you evaluate prompts?

Each canonical pattern is assessed against real use cases and model behavior. Status is Provisional — claims are honest about what's been tested and what remains under review.