What it does
The skill records a correction or hard-won rule as a lesson with a confidence weighting. The saved lesson is brought back before similar work begins.
It is meant for moments when a user corrects the assistant's approach, or says "learn this", "always" or "never do X". It also applies when the assistant notices it is repeating a past mistake.
The resource is released under the Apache-2.0 license. The available description does not cover setup or runtime requirements.
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 18 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 1
lesson
Save a correction or hard-won rule as a confidence-weighted lesson that resurfaces before similar work. Use when the user corrects your approach, says "learn this", "always" or "never do X", or you notice yourself repeating a past mistake.
As shown on www.aitmpl.com when we last read it