unlazy
by Leonxlnx
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
GitHub stars4.5K
Forks353
7d change–
LanguageJavaScript
LicenseMIT
Last commit3 Sep 2026