ChatGPT Prompts

Puts the model in the role of a campaign strategist that picks a target audience, key message, channels, and supporting activity for a product you name. Good for generating a first campaign skeleton you can argue with, rather than starting from an empty brief.

Frames the model as an experienced Ethereum developer writing Solidity contracts with the access rules and state handling spelled out. Useful for scaffolding a contract and understanding the trade-offs, though any output needs a real audit before deployment.

Asks the model to produce SVG markup for a described graphic, returning code you can paste directly into a page. Handy for simple icons, diagrams, and placeholder artwork when you want scalable output with no binary asset or build step.

Turns the model into a QA engineer that writes test cases and reproducible bug reports for a described feature. Useful for building a regression checklist, or for turning a vague complaint into a report a developer can actually act on.

Produces commit messages that follow the Conventional Commits specification, with the right type prefix and a scoped subject line. Keeps a shared history readable and makes automated changelog and semantic-version tooling work properly across a team.

Casts the model as an ML engineer who explains approaches, data preparation, and evaluation in practical terms rather than academic notation. Useful when you need to choose between techniques or understand why a training run is behaving badly.

Converts a written description of a matching rule into a regular expression, returning the pattern without a lecture attached. Best used for validation rules, log parsing, and find-and-replace work where you know the intent but not the syntax. Always test the output against edge cases.

Acts as a bare Python interpreter that prints output and nothing else. Useful for verifying comprehensions, string formatting, and standard-library behaviour when you do not have a REPL open. Because it suppresses prose, it is also a fast way to quiz yourself on semantics.

Makes the model behave like a browser console: you type an expression, it returns only what the console would print. Handy for reasoning about coercion, array methods, and async ordering without opening devtools. Keeps replies free of explanation unless you ask.

Turns the model into a sandboxed Linux shell that replies only with terminal output and no commentary. Useful for rehearsing commands, checking expected output, or teaching shell basics without touching a real machine. Wrap anything you want said in plain English in braces.

Builds a responsive search ad the way the format actually works: interchangeable lines across four angles with pin candidates marked. The any-combination rule prevents the mismatched headline salad RSAs are famous for.

Moves testing from example-listing to property thinking: the prompt asks which algebraic laws the code must obey, then encodes them with hostile generators. Finds the edge cases table-driven tests always miss.

A hook-generation prompt with enforced format variety so you get a real test matrix instead of twelve rephrasings of one idea. The self-selection step at the end doubles as a quality filter you can argue with.

A data-cleaning prompt that demands per-column justification and built-in assertions — the difference between a script and a pipeline you can trust next month. Method chaining keeps the result readable in review.