Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when the user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Loading evals
be88d6c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.