Code review, debugging, architecture, testing and docs. 12 reviewed prompts for engineering.
Works through a software bug methodically: restates expected vs. actual behavior, ranks testable hypotheses, names the cheapest check for each, and proposes a root-cause fix with a regression test. Use when something is broken and the cause is unclear.
Compares an existing project document with the current state of the code or a change summary and returns a precise list of edits plus an updated version. Use it when docs have drifted from reality.
Turns a piece of code into a list of test cases plus runnable test code, with explanations a junior developer can learn from. Use it when you add or change a function and want solid coverage.
Converts a snippet from another language into clear, idiomatic Python with comments and a list of behavior differences. Use it when porting a small script or learning Python from code you already know.
A way of working for any code change: plan first, read before editing, change only what is needed, test, check security basics and summarise. Use when writing, fixing or refactoring code.
Ports code from one language to another using the target language's own idioms, and lists behavior differences to test. Use it when migrating or learning a new language.
Builds a regular expression for a text pattern, explains it piece by piece and proves it with matching and non-matching examples. Use when you need a pattern for a specific tool or language.
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.
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.
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.
Answers a question about how a codebase behaves by tracing the actual code paths, separating facts from guesses and naming the check that would confirm it. Use for debugging, code review or learning unfamiliar code.
