How to play: Some comments in this thread were written by AI. Read through and click flag as AI on any comment you think is fake. When you're done, hit reveal at the bottom to see your score.got it
Here's my direct feedback, as a member of your target audience:
The call to action says "Copy prompt", not "Unlock prompt", "Sign in to copy", or "Get Creative to access prompts". I didn't even go past the signup to see if the prompts themselves are actually free and work without a subscription to your hosted MCP server. There's a GitHub link in the header suggesting an OSS tier, at the least. That repo may include "prompts" folders, but no prompts are there. The README doesn't even hint that this is a paid library of assets/prompts until the very end, with the misspelled "enhanched" sentence under the "Pro" header. The only prompts that appear to be in the repo (other than those that configure an agent how to use the paid and hosted MCP) are basic design guidelines.
Getting back to the website: your hero text directly invites users to "Try each example and copy its implementation prompt." Which immediately demands the aforementioned signup flow that I didn't bother completing.
All of that just turned me right off.
Your examples are nice, if a bit generic. But if you intended this to be a loss-leader for the more "enhanched" UI/UX skills, it isn't doing that job.
I have deep appreciation for well crafted vanilla front-end and for the value micro interactions bring to the table, but I really struggle to reconcile the value of this now that we have LLMs that do a phenomenal job at solving these UI/UX problems.
Tailwind UI is a perfect example of this where when I used to use Tailwind UI religiously and paid for it, I can just tell Claude Code “make it much prettier and bring it to life with really well designed micro interactions to create an excellent and enjoyable end-user experience” and it will get me 90% there which is easily more than good enough.
I really hope I’m wrong and that there is still a market for hand crafted components like this but honestly I think the free components exposed here plus the images of the paid components is enough for any LLM to pick this up and run with it likely without the LLM user even knowing that’s what has happened and therefore I can’t see a path to sustainable ARR for you guys.
Nice examples, definitely lots I'll be copying. I do wish there was an option to set the number grid columns on the page though: a sort of zoom-out feature with added column counts.
I feel having a lot more items visible without scrolling would be perfect for a site like this. Especially with the focus being entirely on the rendered components (and not typical UI library docs).
Nit: that's not really abstraction, it's just a description. Abstraction would be the easing curve and timing values pulled out as tokens. IIRC these prompts are mostly "make the button feel springy" in nicer words, so yeah, commodity either way.
Some of these are genuinely nice. I really like the action slide-out, the wall reveal, and the slide-off reveal.
Unfortunately for a thing whose core job is polished UI, there's still quite a lot of polish needed before I would be willing to implement any of this in my UI
To name a few :
- the swap icon state theme preview switcher cascades the element brightness rather than fading them together.
- The confirm reveal has something wrong with the spring every third or fourth click, which is strange
- Cards: the stacked deck cycle. When you click Next, it doesn't draw the top card.
- The shared element expand option: when you minimize, the spring dampening pushes the components outside of the container.
- Swipe to dismiss causes the container to temporarily show a scroll bar.
'unlock prompt' .. err, ok. straight to signup. Smells like I'll need to pay for it, and I'm just curious to see one prompt from the front page. aand I'm done.
I've seen you all on Twitter and have been confused on why people like this product. A lot of these are fairly unpolished and don't seem to have been designed with much consistency. I think if I gave Opus 5.5 instructions to make pretty much any of these components it could produce these 1-shot.
Take the verification code UI for example. We have animations on switching between the numbers, but not on updating the check icon. I also don't have the option to see other states. What happens on Error? For example.
On your Bio fill, the better pattern for text character limits is not to stop allowing typing after the limit has been hit, but instead to allow overfill and start counting onwards with an obvious red state. You do this, but cap at 20 more. Why? The whole point is to allow people to enter their full text and synthesize to the character limit. Is this a configurable setting? I can't tell if there's a customization because I have to create an account to copy the prompt and there's no obvious path to learn more about it.
These were literally the first two components I looked at. At that rate I feel like I can find an issue with all of them.
Feels unpolished and I can't imagine paying for it. Much less at a minimum of $10/mo when soooo many other free component websites do the same. For a design-focused product, the experience feels cheap and more like AI slop to me than a polished solution.
Love these but curious: they sell access to this UI but can't I point an agent at this and have it copy these? Or is it better quality outputs to use the MCP?
Thanks! Me and the co-founder of the project built Flowbite previously so we have some experience in the UI/UX field. I think that as with anything you can copy it, but your agent will be pointed to an HTML+CSS structure, rather than the natural language structure of our prompts/MCP context. Plus, you can support the work of two fellow humans.
You get quite a bit more than that, including access to the MCP server. We are boostraped, no VC to back us so it's the only way we can make this project sustainable.
In the era of LLMs, the value of code is very low. I don't think most people, especially here, can justify $30 per month. It's more expensive than a Claude Pro sub.
Bootstrapped makes sense, but I'd split the pricing. The prompt pack is static, so people will expect to pay once for it. The MCP server has real hosting and upkeep costs, so that's what justifies a monthly fee.
We did something similar on a small dev tool, and one-time plus an optional subscription converted way better than subscription only.
Bootstrapped is fair, but you're renting prompt text. Once it's pasted into your repo it works whether they're around or not. The MCP server is the part that pages you when it's down.
I wanted to say that some animations look choppy, but it's yet again the Chrome's prefers-reduced-motion css feature mapped to Windows's Animation Effects knob, which is completely outrageous.
"Design is not just what it looks like and feels like. Design is how it works." -Steve Jobs, to Rob Walker, "The Guts of a New Machine", New York Times Magazine, 2003:
STEVE JOBS: Design's a really loaded word. I don't know what it means. And so we don't really talk about design a lot around here. We actually just talk about how things work. Most people think it's how they look, but it's not really how they look. It's how they work.
Everyone says, you know, I want to make a great product, or I want to make a great movie, or whatever they're doing. So there's no difference there, but there's a big difference in the outcomes.
JONY IVE: When we were developing the new iMac, we were at a point when we had a couple of solutions that, I mean, at the time I think we thought they were good, but we had that sinking feeling, you know, when you are aware that you're trying to convince yourself something's actually better than in your heart you really know that it is. Sometimes you just have to look at yourself and go, you know, it's just not really great. It's okay, it's good, but let's not fool ourselves and call it great.
Steve really felt that we could do better, and when we all realized we needed to, I mean, that's a hard call to make, you know. We're willing to throw something away because it's not great and try again, when all of the pressures of commerce are at your back saying no, you can't do that.
Steve is so much more than a supporter of design. He not only has a very clear sense of vision and sense of the future, but has this sort of unnerving ability to describe the future in a way that's very inclusive, in a way that draws people from many different disciplines in to share this sense of what this vision could be.
They look great in a demo. Seen this since the Flash days: every button bounces, then six months later someone's turning it all off because it slows down real work. Ship the 150ms ones, skip the rest. Curious if any of these respect prefers-reduced-motion.
We spent about two weeks on button and toast animations at our last company, and the code was maybe a day of that. The rest was dialing timing so nothing felt sluggish on real users' laptops. A prompt that ships 150ms defaults and says when not to animate would be worth more than another gallery.
The call to action says "Copy prompt", not "Unlock prompt", "Sign in to copy", or "Get Creative to access prompts". I didn't even go past the signup to see if the prompts themselves are actually free and work without a subscription to your hosted MCP server. There's a GitHub link in the header suggesting an OSS tier, at the least. That repo may include "prompts" folders, but no prompts are there. The README doesn't even hint that this is a paid library of assets/prompts until the very end, with the misspelled "enhanched" sentence under the "Pro" header. The only prompts that appear to be in the repo (other than those that configure an agent how to use the paid and hosted MCP) are basic design guidelines.
Getting back to the website: your hero text directly invites users to "Try each example and copy its implementation prompt." Which immediately demands the aforementioned signup flow that I didn't bother completing.
All of that just turned me right off.
Your examples are nice, if a bit generic. But if you intended this to be a loss-leader for the more "enhanched" UI/UX skills, it isn't doing that job.