Tag
Thorough tests catch the bugs manual checking misses. These prompts help you generate unit tests that cover happy paths, edge cases, and failure modes for any function.
12 prompts · page 1 of 2
Reads a two-variant test — descriptions, results, sample size, and duration — and delivers a fast verdict: statistical significance, which variant won, confidence level, key learnings, and a rollout recommendation with suggested follow-up tests. A lighter-weight companion to the rigorous version, meant for everyday test readouts rather than high-stakes ship decisions.
A statistics-first review of an A/B test that goes past a single p-value before you ship the result. - Inputs: control and treatment group results, primary metric, test duration, and optional segments - Checks: post-hoc power, statistical significance with confidence interval, absolute and relative effect size - Flags: novelty-effect risk, sample ratio mismatch, peeking problems, and multiple-comparison issues - Output: a ship/kill/keep-testing call with the reasoning behind it
Give it the PR's stated goal and your repo's architecture and conventions to get a review that avoids both rubber-stamping and nitpicking. It checks correctness, readability, maintainability, test coverage, and backward compatibility in one pass, then sorts findings into Confirmed Issues, Possible Risks, and Nice-to-Haves, closing with three ready-to-paste GitHub review comments.
Paste a diff or function to get a systematic sweep of the edge cases it doesn't handle, before you sit down to write tests. - Covers empty inputs, nil/null values, boundary values (0, -1, MaxInt), concurrent access, timeouts, and malformed data - For each gap, shows what currently happens versus what should happen instead - Follow up with "write a test for the three most dangerous ones" to get code immediately
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
Reviews a PR the way a strict test reviewer would when the code looks fine but the test coverage feels shaky. It calls out missing negative and boundary tests, gaps in integration coverage, flaky test risks, and spots where implementation changed but the matching tests didn't. Returns the critical missing tests first, then useful additional ones, described as sample test cases in plain English.
Generates unit tests for a single pasted function in whatever test framework you name, without needing a full diff or surrounding file for context. Covers three buckets specifically: normal expected inputs, edge cases, and invalid inputs, written in your framework's syntax so the output can be dropped straight into a test file. A good default when you just have one function and need a quick, focused test pass.
Generates a structured batch of email subject lines for testing, grouped by psychological angle rather than random variation. - Inputs: email topic, audience, main message, desired action, brand voice, and words to avoid - Produces: 20 subject lines grouped by angle, preview text for the 5 strongest, and a testing hypothesis per group - Flags: spam-risk wording and recommends one A/B test pair to run first - Built for email marketers who want a defensible reason behind every subject line, not just volume
Feed in a stack trace, expected versus actual behavior, the relevant code, environment, recent changes, and what you've already tried when you can't tell which layer is actually failing. Returns ranked hypotheses weighed with evidence for and against each one, a step-by-step debugging plan, and both a quick fix and a proper fix so you can unblock now while scheduling the real solution.