I turned Andrej Karpathy's tips on understanding LLM output into an Open Source Agent Skill

A developer released make-it-click, an MIT-licensed open-source agent skill that turns Andrej Karpathy's advice on understanding LLM output into a tool that selects the simplest format needed to make an idea click. The skill also includes an oversight mode for reviewing agent work by surfacing what changed, why, the risk, and what to check, and works with Claude.ai and Claude Code.

I turned Andrej Karpathy's tips on understanding LLM output into an Open Source Agent Skill : make-it-click https://github.com/ajithraghavan/make-it-click 🧠⚡ Inspired by his X post : as Models do more of the work, we spend more time understanding it. So the format of an answer matters The Skill picks the simplest format that makes an idea click, and moves up only when needed : Bonus : an oversight mode for reviewing Agent work what changed - why - risk - what to check MIT licensed. Works with Claude.ai and Claude Code 🔗 https://github.com/ajithraghavan/make-it-click https://github.com/ajithraghavan/make-it-click Feel free to use and ⭐️ the Repository Inspired by @karpathy: https://x.com/karpathy/status/2105819303471976479 https://x.com/karpathy/status/2105819303471976479 Thanks for Reading