Unlazy
Anti-laziness: splits a task N layers deep before answering.
Use it for
Tasks where the first answer is suspiciously easy
Skip it if
Anything time-critical
What it is
A depth-tree method that forces decomposition before output, aimed at the failure where an agent answers the easy version of a question. It works when the decomposition is visible; when it becomes internal reasoning, it is just a longer answer.
Install
Clone the repository, then copy the skill folder into your agent's skills directory — ~/.claude/skills/ for Claude Code. Skills are plain files: no build step, no daemon.
git clone https://github.com/Leonxlnx/unlazy.gitHow to judge it
Read the SKILL.md before you install. A good skill states when it applies, what it must not do, and how to verify the result. A skill that only lists adjectives will change the agent's tone without improving its output — skip those.
Other Productivity skills
- Agent Skills — The reference collection: document, spreadsheet, and slide skills from the team that defined the format.
- Claude Skills Collection — Hundreds of skills across engineering, marketing, product, and operations.
- Book to Skill — Turns a technical book PDF into a skill you can query later.