Simon Willison on AI

Simon Willison@simonw

OpenAI aren't talking about it yet, but it turns out they've adopted Anthropic's brilliant "skills" mechanism in a big way Skills are now live in both ChatGPT and their Codex CLI tool, I wrote up some detailed notes on how they work so far here: t.co

2.1K likes76 repliesPosted Dec 12, 2025

Remix this post

Your note

Private to you, and used when you remix this post.

Viral score

Based on absolute engagement — the platform doesn’t expose follower counts here, so large accounts score higher.

From likes, comments.

Why it worked

Promises an answer and holds it back, which pulls the reader down the post.
Opens a question in the reader’s mind and withholds the answer until later.
Written from experience rather than as advice, which is harder to argue with.
Short enough to read in full without expanding, which removes a step before the point lands.
Quotes someone directly, which makes the moment concrete rather than summarised.

The mechanics

Hook: Promises an answer it withholds
Structure: Hook → Landing
Style: Conversational paragraphs at a steady pace.
Tone: personal
Mechanisms: Curiosity gap
Written for: People building with AI

Analysis by ViralLoop — not written by the original author.

Post by Simon Willison on X