Been working on marketing for Tabisto, my Chrome extension. Tried free directories first, Tiny Startups, Twelve Tools. Didn't move installs much. What actually worked was having Claude write comparison pages against tools people already used, Toby, Momentum, Raindrop. Gave it the real feature differences, let it draft the structure, edited from there. Each page took about 20 minutes instead of the half day I was expecting. Reminded me of Vincent's post on Claude Design for landing pages. Give it real context instead of a vague brief and it gets surprisingly close on the first pass. It's a free bookmark manager for Chrome, organizes links into named sections on the new tab. Grab it from the Chrome Web Store. Anyone else using Claude for the marketing side of a build and not just the code?

Built Tabisto, a Chrome extension, using Claude Code. Went from first message to live on the Chrome Web Store in 5 days. Wasn't trying to build anything ambitious, just fixing my own tab chaos. Didn't expect much beyond that. Then reviews started coming in. One person said they didn't realize how useful it would be until they actually started using it, now they open it constantly. Another called it the best new tab extension they've tried. 15 reviews in, still 5.0. It's a free bookmark manager for Chrome, organizes links into named sections right on the new tab. Site's at tabisto.app, or install from the Chrome Web Store if you want to see what a 5-day Claude Code build actually looks like in production. Anyone else here shipped something small with Claude Code that ended up getting real use?

4 days ago Anthropic just launched Claude Design (claude.ai/design). If you ship products but you're not a designer, this one's for you. Claude Design is a new surface built specifically for visual output (landing pages, UI, full page layouts) with a live preview and real iteration. So I pointed it at one of my own project. obikido.com my family calendar solution that lives inside WhatsApp. In 2 minutes I got the landing pages attached in the video 1. Went to claude.ai/design 2. Linked it to the related project in my Claude account — so it already had the full context: what Obikido is, who it's for, the tone of voice 3. One prompt: "improve the landing page" No brief. No reference sites. No screenshots. The project link did all the heavy lifting. You can judge the quality yourself, compare the live produciton site with the prototype in video. What I'm taking away: - Linking Claude Design to a project or repo is the unlock. I did zero prompt engineering and got something I'd ship. I will now pick some elements of the proposed design and deploy them later - It's fast enough that there's no excuse to ship a weak landing page anymore :) even for v1. - For solo founders and indie devs, this collapses a week of designer back-and-forth into one prompt. Honestly this could kill Figma. I'm going to run the same exercise on a couple more of my pages. If you try it on yours, drop the before/after in the comments. Vincent

I build WordPress plugins for a living. I had never touched a Chrome extension before this project. I had a personal problem I wanted to solve. My browser was a mess. 150+ open tabs, bookmarks I never opened, tab groups that turned into a pile within a week. I just wanted to save links into named sections and find them later. Nothing did that simply enough. So I used Claude Code to build it. Five days from nothing to live on the Chrome Web Store. What actually worked well with Claude Code: Describing the problem clearly before asking for code. When I explained what I wanted the user to feel, not just what the function should do, the output was much closer to right the first time. Pointing at the exact thing that was wrong. Not "this is broken." More like "this button saves the link but the section doesn't update until I refresh. I want it to update immediately." Specific inputs got specific fixes. What didn't work as well: Letting it run too far ahead. A few times, I didn't stop it early enough and ended up with code that technically worked but was more complex than the problem needed. Shorter loops were better. Adding features mid-build. Every time I introduced something new while something else was half done it created problems. Finishing one thing completely before starting the next made the whole process smoother. The extension is called Tabisto. Replaces your new tab with a visual bookmark dashboard. Named sections, workspaces, notes, and saved tab sessions. Free, no account needed. If you're learning Claude Code and thinking about a first project, a Chrome extension is a good one to try. The scope is contained, the feedback loop is fast, and you can see it working in your actual browser while you build. What patterns have you found that make Claude Code more reliable for your builds?

Update from Saturday: Amazon terminated my KDP account. Not for this book — an unrelated nostalgia title I had on KDP tripped their AI-content review. Lifetime ban, royalties forfeit, no reopening. The Amazon link in my last post above is dead. The book itself is fine. Just not on Amazon. Pivoted to direct sales on Payhip today. ~45 min to get there. PDF + EPUB bundle, DRM-free, EU VAT handled by the platform. ~90% margin vs Amazon's ~30% — which honestly works out better long-term. For this community — code SKOOL, 25% off, expires Sunday 11 May: https://payhip.com/b/VpTj3?coupon=SKOOL → €18 Free Chapter 9 (the same PDF I was DM'ing on request — now self-serve): https://payhip.com/b/9TWtN @Gareth Parkes — thank you for the KU offer. Book's no longer on KU but if you still want to read and review, DM me and I'll send a copy directly. @Ellie Davis — thank you. With Amazon gone, reader feedback (Goodreads, LinkedIn, even a sentence in this thread) is the social proof doing the heavy lifting now. ▎ Also live on the same store: The Claude Playbook — the hands-on guide to ▎ Claude from first prompt to production code. €19, same SKOOL code → ▎ €14.25. Built from the curriculum many of you already know. ▎ https://payhip.com/b/Dk3OB?coupon=SKOOL