Dean

I spent weeks confused by Claude Code's feature ecosystem. Skills? Subagents? Plugins? Commands? Agent Teams? The mental model that finally made it click: Skills are knowledge. Subagents and Agent Teams are workers. Plugins are how you package and share all of it. Wrote the article I wish I had from the start. tinyurl.com/3xv324m5

@theo This is likely the result of bad planning and not giving it a test harness while it worked on your feature

Just let Opus go for over an hour on a new feature. When it was done, I asked how I can test it. 20 minutes later, it realized I can't test it because it did the whole thing entirely wrong. Idk how you guys use this model every day for real work 🙃

Most people still use AI the way they did in the ChatGPT era. Type a question. Get an answer. Copy-paste it somewhere. That's how it worked when ChatGPT came out in 2022, and most people haven't updated their mental model since. Starting in 2024, we entered the agentic AI era. Tools stopped just answering questions and started doing work. Claude Code is at the center of that shift. It's an agent that reads your files, runs commands, makes decisions, and operates inside your actual codebase. Even out of the box, it's powerful. @bcherny, the person who built it, has said his own setup is "surprisingly vanilla." But there's a gap between "it works" and "it works the way I want." Without the right habits, you end up generating "AI slop" you'll eventually rewrite anyway. I learned that the hard way. So I built a simple two-part framework: compounding habits you set up once that make every session smarter, and session habits that keep each task on track. If you want to get reliable, quality output from Claude Code, this one is for you. Link in comments. 👇

@daviddorg @superpower @ouraring can't be possible. how will you use twitter to provide updates? how will you file for your taxes or view your blood work results without a computer? Also, what kind of phone will you be using that does not have a screen?

Hi, my name is literally David And I’m going a year without screens in 22 days (down from 10h+ per day) While tracking: - Neuroimaging (fMRI + MRI) - Cognitive + motor tests (very comprehensive) - 131 blood-based biomarkers (@superpower) - Sleep and activity data (@ouraring) - Vision exam - Hearing exam - And more I’m excited to see what the data show We all deserve to know more about how our devices in their current form are affecting us

@bcherny @cvaartjes More powerful in what sense?

@cvaartjes This one is much more powerful. Existing skill is a great reference and will remain open source

New in Claude Code: Code Review. A team of agents runs a deep review on every PR. We built it for ourselves first. Code output per Anthropic engineer is up 200% this year and reviews were the bottleneck Personally, I’ve been using it for a few weeks and have found it catches many real bugs that I would not have noticed otherwise

I often catch myself typing full English sentences into a terminal, forgetting I'm not talking to an LLM

@bcherny thanks for making Claude code. It's by far my favorite agentic tool and my whole team prefers it over others. Have a highly useful feature request for Agent Skills if you happen to see this. We have shared skills across our organization. Many skills are tied to usage of specific internal libraries on GitHub. If these libraries update, the skills may become stale (outdated method interface, etc). Can your team incorporate a mechanism natively to keep skills updated (e.g. pull latest git tag and read latest code) if skill is falling behind?

Hot take: the era of dual monitors and ultrawide setups is ending. Agentic AI handles the multitasking now, so what's the point of having massive screens anymore? You just need one clean screen to supervise it. Get yourself a single 27 inch monitor and call it a day.

Claude Code is coming for your job

Dropping $600 on Mac mini just to setup OpenClaw is a rookie move. Especially if you're just experimenting. Just use a cloud server instead. Tons of cloud providers offering free credits right now

I've been using AI Agents (Claude code + Windsurf) every day for the past 3 months as a Senior MLOps Engineer. I thought I would be working less with these tools. Turns out I'm working harder than ever before. I'm producing 5x output, it has become addicting.

@DorianDevelops You forgot the s

Who decided K8 was a good nickname for Kubernetes? I don't get it...

@WorkaholicDavid Buttons are both faster and more reliable

Let's end the debate. Gestures or buttons?

@KevinNaughtonJr Nice! I like the concept LinkedIn content style is different than Twitter. And has different character limits. So why would one want to sync their tweets to a LinkedIn post? Assuming that's how it works

pls try my new product (below) it's not as bad as you think