I turned Andrej Karpathy’s tips on understanding LLM output into an Open Source Agent Skill : 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 :
Clear writing in ASD-STE100 style (strict, 80%, or light)
Diagrams
Interactive HTML pages
Narrated explainer videos (3b1b style)
Bonus : an oversight mode for reviewing Agent work (what changed -> why -> risk -> what to check)
How to use:
1️⃣ Install (works with Claude Code, Copilot, Cursor, Codex and more):
npx skills add ajithraghavan/make-it-click
2️⃣ Then just ask: Explain how TCP works, 80% STE Make an interactive HTML explainer of Gradient Descent
MIT licensed. Works with Claude.ai and Claude Code
Feel free to use and ⭐️ the Repository
Inspired by @karpathy: [https://lnkd.in/gHGDd48Q]
Top comments (0)