What it does
The skill guides debugging through four phases: investigate, compare, test one hypothesis, and fix with a failing test written first. The aim is to find the root cause rather than guess at a fix. After three failed fixes, it stops and questions the underlying design.
It applies when something is broken: a bug, a failing or red test, a build or CI failure, a crash, a performance problem or unexpected behaviour. The publisher's description says it should be used before any fix is proposed or made, including quick fixes and urgent cases.
The skill is released under the MIT license. Running it means working through its phased sequence on the broken behaviour at hand; the source describes no separate setup steps.
Limitations and requirements
The source states the skill is not intended for writing new features.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 19 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 2342
systematic-debugging
You MUST use this whenever something is broken, before proposing or making any fix, including quick fixes and when the user is in a hurry: a bug, a failing or red test, a build or CI failure, a crash, a performance problem, unexpected behavior. Finds the root cause in four phases (investigate, compare, test one hypothesis, fix with a failing test first) instead of guessing, and stops after three failed fixes to question the design. Not for writing new features.
v2.0.0As shown on www.aitmpl.com when we last read it