Tag
A good code review catches more than syntax errors — it flags readability, performance, and edge cases before they ship. These prompts turn any diff into a structured review, ranked by what actually matters.
30 prompts · page 2 of 4
Describe the issue you've spotted in plain English along with the specific lines and fuller details, and get back a ready-to-paste GitHub review comment instead of staring at a blank comment box. The output is specific, explains why the issue matters, includes a concrete suggested fix, and skips filler openers like "Great work, but..." — also useful as a template for junior reviewers learning to write good comments.
Paste a diff to get a review that stays narrowly focused on logic errors, null dereferences, race conditions, and off-by-one bugs — the kind that actually reach production — while ignoring formatting and naming entirely. Each bug found comes with the exact line, why it's a bug, and a suggested fix, and it says so explicitly if nothing turns up rather than padding the review with style notes.
Paste a diff to catch the error-handling bugs that trigger 2am incidents — the ones that don't throw or log, just quietly corrupt state or return wrong data. It scans for swallowed exceptions, unchecked error returns, missing error paths, and logged-but-ignored failures, then rates overall error handling 1-10 with the reasoning behind the score so you know whether to approve or request changes.
A broad first-pass review for a pasted code block that hasn't been looked at by anyone else yet, no special setup or context required beyond the code itself. It checks quality and best practices, likely bugs and edge cases, performance, readability, and security in one sweep, then explains the reasoning behind every suggestion so it teaches as much as it fixes.
Scores a pull request on long-term maintenance cost rather than just correctness, useful for code that works today but already smells expensive to keep. - Rates readability, complexity, dependency risk, and change isolation from 1-10 - Surfaces the top 3 maintainability concerns behind those scores - Suggests concrete ways to simplify each one before merge
Reads a pasted diff and writes the unit tests it's missing, in your stated test framework, as runnable code rather than a bulleted test plan. - Covers the happy path, the top 3 edge cases, and at least one failure scenario - Uses realistic sample data instead of placeholder strings like "foo" - Tip: ask it to also write a test that would have caught the bug, if the diff is a fix
Explains a pasted code block the way you'd brief a competent new hire who has zero context on this codebase: what it does, why it exists, and any non-obvious decisions or gotchas baked into it. The output is formatted as a comment block ready to paste directly above the function, making it useful as living documentation and not just a one-off explanation.
Reviews a pasted diff through the lens of a senior engineer who has owned this codebase for two years and has strong opinions about pragmatic architecture. Instead of hedged, generic notes, it calls out whether abstractions sit at the right level, flags trade-offs that will bite in six months, and says so directly rather than diplomatically. Swap in your real stack and values for a sharper persona.
Profiles a pasted code block for real performance issues, using its execution frequency, typical data size, and your current pain point to prioritize what actually matters. - Flags O(n²) loops, N+1 queries, missing indexes, and memory/caching gaps - Ranks each finding High/Medium/Low impact with a suggested fix and expected gain - Focuses on the 20% of changes likely to deliver 80% of the speedup - Confirm suggestions with real profiling before shipping