Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →rshankras/tdd-bug-fix
Fix bugs using red-green-refactor — reproduce the bug as a failing test first, then fix it.
Passed 15 of 22 test cases with the skill, and 12 of 22 without it.
and 2 more in the full report
3 fixed13 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our Swift app's `CartManager.applyPromoCode` is calculating a 20% discount twice when applying promotional vouchers, returning $64 on a $100 item instead of $80. I need you to address this using a test-driven approach. Please provide a full markdown report that outlines the expected vs actual behavior, includes the failing test code, shows the file diff for the fix, and confirms verification and regression test details.
| Checked | Without skill | With skill |
|---|---|---|
| Formats the main heading using the standard bug fix description format. | Missed | Passed |
| Uses `#expect` assertions instead of XCTest assertions. | Missed | Passed |
| Includes a verification checklist confirming test failure prior to code modifications. | Missed | Passed |
The instructions your model reads when the skill loads.
Fix bugs the right way: reproduce first, fix second, verify always. Especially critical when using AI to generate fixes — the test ensures the AI actually solved the problem.
Use this skill when the user:
Without TDD: With TDD:
Bug reported Bug reported
→ AI generates fix → Write failing test (RED)
→ Deploy → AI generates fix (GREEN)
→ Hope it works → Test passes — confirmed fixed
→ Bug returns later → Test prevents regression forever
Gather information:
Grep: "[relevant keyword]" to find the source
Read: the suspected file(s)
test cases passed, vs 12 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.