Mike

@udayan_w Thanks, I will try!

quick context on the problem 🙏 i have a loop setup with claude code and codex: it builds something, takes a screenshot on it's own, compares it to the figma reference, keeps iterating until it's pixel perfect. but it never works the agent would screenshot its own output and somehow not see a completely broken button. i'm sitting there staring at it! but under isay "the button is broken" it wouldn't see it. i was like how are you so smart and dumb at the same time? that's when it clicked for me. the problem isn't that the model is dumb. the problem is that when you send a screenshot, the AI just... looks at it and describes the image in general sense. so you spend 3-5 rounds saying "no, the padding is wrong." "no, look at the nav again." "no, the border radius doesn't match." i started digging into how this is actually solved at companies that do it well. turns out replit, lovable, microsoft, all of them solved this already. they all run structured analysis first. spatial coordinates, component hierarchies, design tokens. then the model gets that as context. but this intelligence is locked inside their platforms. if you're using claude code or codex or anything general purpose, you get none of it. so i built clearshot 📸 open source skill for claude code/codex. every time you or the agent takes a screenshot, it doesn't just "look" at it. it tells the model exactly what's there. padding values in pixels. not "blue color" but the actual hex code. not "some spacing" but 8px gap between the label and the input. border radius, font weight, shadow values. everything the model was guessing at before, it now knows. very deterministic but... there's also a qualitative path. a taste layer. does the hierarchy feel clear. is the visual weight distributed right. is there enough breathing room. does this feel like a premium product or a hackathon project. because sometimes the question isn't "what are the pixel values" but "does this feel right." clearshot handles both. one thing i was careful about: it shouldn't fire when it's not needed. if you send a screenshot of a chart, or a meme, or an architecture diagram, and you're not building frontend, the skill stays quiet. it only activates when the image is a UI and the conversation is about building or critiquing that UI. and within the analysis itself, there are exit paths at every step. if a quick spatial scan is enough, it stops there. your agent isn't burning tokens running a full 5-step pipeline when you just asked "does this look right." this is the first version. will keep iterating. clearshot is open source and free. star it if you think AI needs to get better at seeing your UI. research this builds on: - microsoft omniparser - dcgen - google screenai

ai SUCKS at frontend!!! taking my first step towards solving it. launching clearshot 📸 if your org doesn't truly care about design, this thread isn't for you. but for companies that truly care about design? keep reading.

@PrajwalTomar_ Having problems with stitch as it hallucinate a lot with different button styling and menu items, check the screenshot ir more detail, buttons are off and menu bar differ screen to screen. Any way tackling this? Figma make on the other hand provides consistent style

This design was made inside Google Stitch in under 5 minutes. ONE prompt. That's it. If you're skipping the design phase for your MVP because it's too slow or expensive, this is a much faster way. Stop wasting weeks on Figma when you can ship clean designs in minutes.

@mattiapomelli @figma Sleek

We built the fastest way to vibe design mobile apps. From idea to screen designs in under 2 minutes. Export to code or @figma. Comment "sleek" for early access.

@PrajwalTomar_ Build

I designed this entire mobile app in under 10 minutes using AI. 
Want the exact workflow + prompts? 
→ Comment “Build” + follow 
I’ll DM you the full guide.

@Jacobsklug @lovable Build

After generating $250K (last 2 months) I built a playbook for @lovable apps—and I’m giving it away. In just two months, we cracked the code to building apps with AI. I’ve distilled everything we learned into this single document. Comment "Build" and drop a follow. I’ll DM it to you. P.S. This will likely blow up, so give me some time to reply.

@gregisenberg Garrden.app

it's business audit time drop your startup below and I'll tell you one thing you can improve i'll be replying to 40+ people

@rajivayyangar @ProductHunt Become a better lover, friend, parent or colleague. Visualize, track, and grow your most important relationships.

I’m the @ProductHunt CEO, I’ve launched 7 times on PH, and helped countless friends prep their launches. The most common mistake I see? a confusing tagline. Launching on @ProductHunt soon? Tell me your tagline and I’ll fix it for you :)

@codyschneider Garrden.app relationship management tool

show me your business and ill show you how to write 1000 articles using ai and make inbound print

The Big 5 personality traits strongly predict life satisfaction (r = .8 - one of the largest effects I’ve seen in a psychology paper). stevestewartwilliams.com/p/5-new-findin…

Apple Intelligence = AI, well played 🍎

The Best of Charlie Munger

@AlexHormozi The challenges: Tattooing is an art, machines must replicate artists' skills. Tattoos involve sensation and individuality. Safety, skin variability, ink absorption

Genuine question: Any reason we don’t have a printer that uses tattoo ink to make beautiful photo-realistic tattoos in a fraction of time and cost?

@TheCinesthetic That moment in "The Sixth Sense" when Dr. Crowe gets it... 🤯💡 Total game-changer!

What's the best moment where a character REALIZES something?

@JoshRaby Your take aligns with Scorsese's view on modern filmmaking. He's all about protecting cinema as an art form amidst the "content" craze. His message goes beyond "art vs. content" debates—it's about cherishing cinema's unique artistry in a commercial world

@5harath @shoutoutso_ @ramykhuffash Congrats!

Some news: After 2.2yrs of hustling, building in public, and putting in a lot of hrs, I'm delighted to announce that @shoutoutso_ has been acquired by Rocket Gems, a UK-based product studio founded by @ramykhuffash 🍾 Let me take you to where it all started 🧵

@DexterLabData something like that 🤣 I can't sleep thinking of what we can make available via API 😁

Team 5$ a month

@DexterLabData GM ⚒️

Gm 🤓 Bear market? We build 🫡

@Dexterlabdata GM ☕️

Gm data nerds 🤓

Panic led to lockdowns. Lockdowns led to fiscal stimulus. Stimulus led to inflation. Inflation led to monetary tightening. Tightening leads to recession. The panic wasn’t free - and the bill is coming due.