Code review, debugging, architecture, testing and docs. 88 reviewed prompts for engineering.
Reviews a web page or component's code for accessibility, loading speed, layout stability, missing states and mobile behavior, then gives prioritized fixes with code. Use before shipping a page or when users report it is slow or hard to use.
Reads a code diff and its commit message and produces a plain summary of what changed, why it matters, and what a reviewer should check. Use before opening a pull request or when reviewing someone else's change.
Produces a grounded plan for a code change: affected files, two or three options with trade-offs, a recommendation, ordered steps, tests and risks. Use it before anyone starts writing code.
Plans how to run an AI model on your own hardware: memory estimate, model size and compression level, runtime setup, expected speed, risks and a benchmark checklist. Use it when privacy or offline use rules out cloud services.
Explains how a codebase works in plain language for product managers, designers or new team members, with a guided tour, glossary and quiz questions. Use it for onboarding or before discussing changes with developers.
Reviews a list of dependencies and produces a prioritized plan to replace outdated or risky ones, with risks, testing and rollback. Use when planning dependency upgrades for a service.
Designs a pipeline strategy for building, testing and deploying multiple independent services from a single repository, with rollout and rollback rules. Use when starting or untangling a delivery pipeline.
Designs an internal cloud platform for your workloads: architecture, infrastructure-as-code module layout, reliability targets, cost model, security posture and runbook outline. Use it when setting up or reworking shared infrastructure.
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.
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.
Finds likely unused code in a codebase or module, rates how safe each item is to remove and orders the cleanup into phases. Use when a codebase feels heavy and you want to shrink it safely.
Reviews backend service code for layering, SOLID violations, API design and performance risks, and proposes small concrete refactors. Use it before merging a feature or when a codebase becomes hard to change.
