unlazy
SkillGitHubActiveJavaScript
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.
Description provenance: Original source
Measured: Oct 19, 2026 · 56 observations
Domains & Uses
- Domains
- AI / LLM
- Uses
- Agent skills, Code assistants
Installation
git clone https://github.com/Leonxlnx/unlazy ~/.claude/skills/unlazyCheck at the source
Compatibility and prerequisites must be checked in the official documentation.
https://github.com/Leonxlnx/unlazyClassifications
- Nature
- Tool
Measurement history
Comparable readings are grouped by signal and unit.
Stars
3,988stars · Oct 19, 2026
+70 (+1.8 %)since Oct 13, 2026
Exact values · 7 readings
| Measured | stars | Change |
|---|---|---|
| 3,988 | +4 | |
| 3,984 | +16 | |
| 3,968 | +19 | |
| 3,949 | +14 | |
| 3,935 | +15 | |
| 3,920 | +2 | |
| 3,918 | · |