unlazy
Anti-laziness skill for AI agents, based on deep tree methodology.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.5k
- Source
- skill-github
- Repository
- github.com/Leonxlnx/unlazy
Overview
unlazy is an anti-laziness skill designed for AI agents. Its core is the deep tree method, which decomposes tasks into N layers and assigns time budgets to each leaf node, causing effort to double with increasing depth. This skill is based on research from 2025-2026 regarding model laziness, insufficient thinking, and premature task completion. By using this skill, AI can better handle complex tasks. Ideal for developers seeking to improve AI agent efficiency.
Capabilities
- ▪Multi-layer task decomposition
- ▪Time budget allocation
- ▪Prevention of premature task completion
- ▪Improved AI agent efficiency
Use cases
Setup
npx skills add Leonxlnx/unlazy
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How to install unlazy?
Install using the command `npx skills add Leonxlnx/unlazy`.
What is the core of unlazy?
The core of unlazy is the deep tree method, used to decompose tasks and allocate time budgets.
Related skills
mantis
Provides security review capabilities for AI coding agents, automatically discovering, reproducing, and fixing vulnerabilities.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.