Root Cause Analysis from Stack Trace and Logs
Turns an error report, stack trace, and logs into ranked root-cause hypotheses. Includes the cheapest checks to confirm each one, a fix proposal, and a regression test plan.
25 prompts
Prompts for Cursor, the AI code editor. They are written for its agent and chat, and name the files, the change and the checks, so the edit lands where you expect it.
2 results
Turns an error report, stack trace, and logs into ranked root-cause hypotheses. Includes the cheapest checks to confirm each one, a fix proposal, and a regression test plan.
Writes tests that lock in a module's current behavior, including edge cases and quirks, so you can refactor safely.
Open the chat panel, choose Agent when the task changes several files, and paste the prompt. Mention files with @ so Cursor reads them before it plans the edit.
Only the parts that apply to every task. Project rules live in the repository's .cursor/rules folder; one-off task prompts belong in the chat.
No. Cursor lets you choose the model, and the prompts are plain instructions that any capable model can follow. A stronger model helps most on changes across many files.