Code review, debugging, architecture, testing and docs. 100 reviewed prompts for engineering.
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.
Explains a security finding from a code scanner, fixes it in the context of your code, and proposes tests that prove nothing broke. Use when a scan flags unsafe handling of user input.
Produces a technical plan for a new mobile app: native vs cross-platform choice, offline and sync design, device features, performance budgets, testing and store release. Use it at the start of a mobile project or before hiring.
Designs how to test an AI-powered feature before and after launch: success metrics, a balanced test set, a 1-5 scoring rubric with examples, pass criteria and a failure log. Use when you need to know whether an AI feature is good enough to ship.
Creates a preliminary design outline for a solar plus battery site: components, sizing logic, protection, controls and open questions for the engineers. Use it at concept stage before detailed design.
Writes a safe, documented Bash script for an automation task, with option handling, error checks and usage notes. Use when you need a script that others can run and maintain.
Translates cron expressions into plain English, shows upcoming run times and flags common mistakes. Use when someone shares a cron line or asks for a schedule to be written or reviewed.
Recommends the simplest workable approach for an AI-powered feature (better prompts, retrieval over your documents, fine-tuning or a mix) with trade-offs, an evaluation plan and cost notes. Use at the start of an AI project.
Designs a normalized relational schema from an app description and its most common queries, with table definitions, keys, indexes tied to real access patterns, and migration order. Use when starting a new data model or reviewing one.
