When production breaks and Sentry lights up, this walks you through the full debugging cycle: discovering issues, pulling stack traces and breadcrumbs, forming hypotheses, finding the code, and shipping a fix. The standout bit is the security constraints section, which treats all Sentry data as untrusted input and explicitly warns against following instructions embedded in error messages or copying attacker-controlled strings into your codebase. It integrates Sentry's AI root cause analysis and distributed tracing, gives you a verification checklist before you commit, and includes a structured reporting format. Opinionated about process but in a way that keeps you from rushing past the evidence gathering step.
npx skills add https://github.com/getsentry/sentry-for-ai --skill sentry-fix-issues