Topic
Writing a good prompt for a coding assistant takes more than "fix my code." This collection gives developers ready-to-use prompts for the tasks that come up every day: finding bugs and explaining their root cause, writing unit tests that cover edge cases, reviewing a diff for readability and performance, and breaking down unfamiliar code line by line. Every prompt is free, works with any language or framework, and uses {{variable}} placeholders so you can drop in your own code and get a useful answer immediately — no prompt engineering required. Whether you're debugging a production issue, prepping a pull request, or just want a second pair of eyes on a function, start here.
53 prompts · page 6 of 6
Turns a raw diff and a short context note into a PR description reviewers can actually use, grounded in the real file and function names pulled from the diff rather than generic phrasing. Outputs a three-bullet what/why/risk summary, testing notes, the files that most deserve attention, migration or compatibility concerns, and a suggested PR title — and says so if the diff is too large to summarize well.
Turns a messy file or module you want to clean up into a step-by-step refactoring plan, built around your stated goal, available tests, and time budget rather than a full rewrite. Each step comes with a risk level and a way to verify it before moving on, plus tests to add, a rollback plan, and an explicit list of what not to touch yet. Meant for code that already works but is getting harder to change safely.
Reviews code that touches auth, user input, file handling, or payments, using the data it handles and its auth model as context for a targeted rather than generic pass. Returns a severity-ranked findings table, a plain-language exploit scenario for each issue, a concrete fix, a safer pattern to use instead, and tests to add. Strictly defensive: it won't write exploit code, only flag and remediate.
Generates a full test suite for a pasted code block, matched to your stated framework, test type, and existing test style so the output fits straight into the project. Delivers a test plan table, happy-path and edge-case tests, error-case tests, mock setup for external dependencies, realistic test data, and a list of remaining coverage gaps — plus the runnable test code itself.
Paste a diff to get a fast, senior-engineer-style pass that prioritizes what actually matters — correctness bugs, regressions, security issues, missing tests, and maintainability risks — over style nitpicks. Each finding comes with severity, evidence pulled directly from the diff, and a concrete suggested change, making it a solid gate to run before opening a pull request.
Takes a single function plus its test framework (or "unknown" if you're not sure) and writes a practical test suite covering the main happy path, boundary cases, invalid inputs, and expected failure modes. It matches the project's existing test style when one is visible in the pasted context, and states any assumptions it made before showing the actual test code.
Feed in a suspicious snippet along with the error message and expected behavior, and get back a ranked list of likely bugs instead of a vague hunch. Each finding names the observable symptom, the probable root cause, the exact lines or functions responsible, and a concrete fix to apply. When the pasted context isn't enough to be confident, it says exactly what extra detail is missing instead of guessing at a diagnosis.
Paste any unfamiliar snippet and get a statement-by-statement walkthrough instead of a single high-level summary. Each line is explained in plain language: what it does, why it's there, and any assumption it quietly depends on, with jargon defined inline as it comes up. Built for developers who already know how to code but are new to this particular codebase, library, or language idiom.