Hey everyone! 👋 Excited to join the community. I am already active in a few other AI and automation Skool groups, but the focus here on building 24/7 AI employees really lines up with what I am going after... My main interest lies in building local, on-premises solutions using OpenClaw, Hermes, Claude Code, and other recursively self-improving agents. one of my goals is to build secure, private research platforms and fully automate the mundane, day-to-day processes. I am working with a multi-box setup consisting of two Mac Minis (M4 Pro with 24GB RAM each). (Side note: if anyone happens to have an M4 Ultra Mac Studio with 512GB RAM they are just itching to get rid of... DM me! 😉) I am currently in the initial research and staging phase, getting ready to install and trying to decide whether to deploy OpenClaw, Hermes, or both for my initial architecture. I would absolutely love to connect and collaborate with anyone else here who is building out their own multi-box on-prem setups. What direction did you go with your local builds, and what have you learned along the way? Please comment and share your thoughts. Looking forward to chatting and collaborating with you all. Cheers!

New OpenClaw skill for the community members: 𝗪𝗵𝗮𝘁 𝗧𝗵𝗶𝘀 𝗦𝗸𝗶𝗹𝗹 𝗗𝗼𝗲𝘀 You give it a URL. It gives you: {domain}.md — the complete Design Map (exact colors, type scale, spacing, shadows, radii, grid) + Taste DNA (WHY the designer made each choice and what they rejected) {domain}.json — machine-parseable version for downstream tools Not vibes. Not "clean and modern." Actual px values, hex codes, and design trade-offs. Example: Run /taste https://linear.app and you'll get the exact font hierarchy, the 8px spacing rhythm, the shadow layering strategy, and WHY Linear chose monochrome icons over colorful ones. 𝗪𝗵𝘆 𝗧𝗵𝗶𝘀 𝗘𝘅𝗶𝘀𝘁𝘀 AI coding agents are terrible at design. They default to Inter font, blue buttons, 8px border-radius, and a card grid. Every AI-generated landing page looks the same because the agent has no taste — it just picks defaults. The Taste skill fixes this. Instead of "make it look good," you say "use the design DNA from stripe.com." The agent gets exact tokens AND understands the design philosophy behind them. Core insight: Design tokens alone are useless. "Spacing is 8px" means nothing. "Spacing is 8px because the designer chose readable rhythm over data density" — that's what makes an AI generate good design for a DIFFERENT page. 𝗛𝗼𝘄 𝗜𝘁 𝗪𝗼𝗿𝗸𝘀 Phase 1 — Capture: Playwright browser loads the URL, takes viewport + full-page screenshots, runs DOM extraction (colors, typography, spacing, cards, grids, effects). Phase 2 — 4-Step Analysis Pipeline: Step 1 (Measure): 20 categories of precise measurements from the screenshot + DOM Step 2 (Pattern): Detect systematic rules (8px grid? 1.25× type scale? accent used only on CTAs?) Step 3 (Taste): 4 design trade-offs — what they chose AND what they rejected. At least one must be a restraint trade-off (something they deliberately didn't do) Step 4 (Observer): Critique everything. Delete generic claims. Converge to 3-4 bulletproof principles. Anti-Slop Enforcement: The pipeline actively rejects "clean," "modern," "sleek," "elegant" — banned at the grep level. If it passes through, the file fails audit.

Hey all, Peter pointed me here so dropping a quick intro. I run OneClickClaw, managed OpenClaw hosting based in the EU, for people who want their agent up 24/7 without babysitting the infra. Updates, security hardening, and the token-auth refresh that breaks silently always seem to eat people's time. Our angle is EU/GDPR plus security-hardened instances, so I'm mostly here to help on the hosting and security side and trade notes with other builders. If you're stuck on setup, a gateway you've exposed publicly, or updates breaking your install, happy to help, that's the day job. What's everyone working on?