Machine learning system design plan
Turns a business problem and the data you have into a practical production ML design: metrics, data risks, model options, rollout and monitoring. Use it before committing a team to an ML project.
780 reviewed prompts.
Turns a business problem and the data you have into a practical production ML design: metrics, data risks, model options, rollout and monitoring. Use it before committing a team to an ML project.
Generates genuinely different ideas by exploring several deliberate angles, then scores and narrows them to the best few. Use when asked to brainstorm or decide an open-ended question such as naming, strategy, or design.
Checks an invoice's line totals, subtotals, discounts, tax amounts, dates and missing details, and lists discrepancies. Use before sending an invoice or paying one you received.
Turns a plain-language description of a system, process or data model into a clean diagram (SVG, diagram code or ASCII) with consistent shapes, labelled arrows and a legend. Use it for docs, proposals and slides.
Reviews a contract from one party's side: key terms summary, clause-by-clause risk ratings, unusual or missing terms, and suggested redlines and negotiation points. Use before signing or negotiating an agreement.
Describes an interface screenshot as a precise written spec a developer can build from, covering layout, styles, states and responsive behavior. Use when handing a design to engineering without a design file.
Creates a design system specification with the reasoning behind it: color, type, spacing and radius tokens, component state rules, contrast checks and do/don't pairs. Use when starting a product's visual system or making an inconsistent UI coherent.
Reads an attached image, chart, screenshot or scanned document and returns what is visible, extracted values with confidence, an interpretation and open ambiguities. Use it when you need reliable data out of a picture.
Builds a realistic weekly schedule and habits that protect focused time around meetings, messages, and energy levels. Use when your calendar is fragmented and important work keeps slipping.
Reviews how an existing web app works on phones, tablets and desktops and produces a prioritized plan of fixes and improvements. Use when users complain about layout, speed or confusing screens.
Plans and builds a presentation as a single HTML file with keyboard navigation, one consistent theme and optional speaker notes. Use when you need a deck that runs in any browser without slide software.
Writes a short, accurate instructions file that tells AI coding assistants how to set up, build, test and safely change a repository. Use when assistants keep repeating the same mistakes in your codebase.