AI says the bug is fixed. Here are three checks to run

A developer recommends three verification checks before accepting an AI coding assistant's claim that a bug is fixed: a reproduction of the bug, a regression test that failed before the patch, and fresh test output. The approach draws on three skills from the obra/superpowers repository—systematic-debugging, test-driven-development, and verification-before-completion—and suggests asking the assistant for the commands, exit status, and untested paths.

When an AI coding assistant says it fixed a bug, ask for three pieces of evidence: a reproduction, a regression test that failed before the patch, and fresh test output. Three skills from obra/superpowers https://github.com/obra/superpowers can help. systematic-debugging https://github.com/obra/superpowers/tree/main/skills/systematic-debugging starts with the error, reproduction steps, and recent changes. Ask the assistant where the actual behavior first diverges from what you expected. With test-driven-development https://github.com/obra/superpowers/tree/main/skills/test-driven-development , capture the expected behavior in a test. For a date parser, try rejecting February 29 in a non-leap year. Run it before the patch and confirm it fails for the expected reason. Apply the smallest fix and run it again. verification-before-completion https://github.com/obra/superpowers/tree/main/skills/verification-before-completion calls for running the relevant checks and inspecting their output. Ask for the commands, exit status, and untested paths. A regression test covers the behavior it asserts. You still need a runnable test environment and a review of the patch. Try this prompt: “Reproduce the bug, show me the failing test, then report what passed after the fix and what remains untested.” Original Chinese article on Juejin https://juejin.cn/post/7707143341481869366 · Skillπ https://skillpi.com/ · Infinite Skills. Infinite Possibilities. Carousel from the October 2026 editorial archive. This English adaptation was generated with AI.