Sabitlenmiş Tweet
Serudda
140 posts

Serudda
@serudda
Product Engineer, UI Component Handcrafter, Indie Creator. Built → @uiguideline · https://t.co/VlVwflXjtv Español → @serudda_es
Portland, OR Katılım Aralık 2023
146 Takip Edilen201 Takipçiler

80% of slop UI comes from prompting "add a dropdown" when you meant a Combobox.
built a POC: paste any UI screenshot → every component identified with standardized names from @uiguideline's research across 20 design systems.
Identify every component name without memorizing a single one.
andrew gao@itsandrewgao
you can instantly 10x your vibecoded frontends by just learning what different ui components are called ofc opus is creating generic slop, the only words you know are menu and button.
English

@ningunaparte Thanks. But why a year ago? Did you launch something at that time?
English

I’m burning a lot of tokens with @openclaw and couldn’t find a native way to switch models.
So I created a SKILL.md to quickly change OpenClaw’s thinking mode:
eco mode → summaries, quick questions
balanced mode → daily driver
smart mode → complex work
max mode → critical tasks
github.com/serudda/switch…
English

I felt overloaded with ideas, most of them disappearing into the void.
That’s why I build my own Second Brain:
- Grounded in the Zettelkasten methodology
- Capture, connect, and compound my thinking instead of losing it
Check it out
↓
github.com/serudda/zettel…
English

Coding quite hard rewriting the screen.studio rendering core from scratch.
It unlocks a lot of new possibilities, like fully fully dynamic layouts, split-screen mode, and many more.
Also polishing it to cultivate our philosophy - "never let users create ugly videos."
English

@ryancarson It feels strange to me that not many people are talking about Agents + cron jobs… two amazing worlds, and combining them is absolutely insane.
English

I’ve figured out a new way of working that’s unlocked my speed of iteration massively.
Here’s how it works:
I have a simple cron job that runs every night at midnight.
It gathers information from my database on user activity, marketing stats, and a couple other data points that are important.
It then feeds that data into Opus 4.5 and asks for one important action item that I should take based on this data, and then emails me.
It also creates a markdown file with the recommendation, which is then stored in my reports folder in the GitHub repo. (This means I can fire up Amp anytime and chat either all of the historical recommendations whenever I want - learning about patterns.)
I then look at this email every morning and decide whether or not to take action on it.
Almost every time it surfaces something really valuable for me to iterate.
So I just open Amp, tell it to action idea, and then ship it.
Obviously, the next iteration of this is just to have Amp autonomously implement the suggestion by itself, and then I'll wake up to a PR instead of an email.
Right now, though, I like the Human-In-The-Loop version of this.
And as soon as we iterate enough like that, I'll probably just set it up to automatically take the suggestion, create the PR, and then I'll have a look at it.
Obviously, you can take this loop even further by having many parts of your business evaluated this way.
What's interesting to me is that this is what I used to rely on my VP of Marketing, my VP of Engineering, or my VP of Sales to do, but it happens automatically for about $0.15 per day.
English
Serudda retweetledi




