Activity
Mon
Wed
Fri
Sun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
What is this?
Less
More
Memberships
NextGen AI
37.4k members • Free
AI Automation Society
391.4k members • Free
11 contributions to AI Automation Society
3h •
One piece of the AI OS that most people skip: the capture layer.🤖(Telegram bot)
Here's mine. I have a Telegram bot running on my phone. Any time I see something worth saving — a video from Youtube, an idea on social media, a thought mid-walk — I just forward it there. Takes 2 seconds. How it works: 1. Create a bot via @BotFather on Telegram — takes 2 minutes, gives you an API token 2. Write a small poller script (Node or Python) that calls getUpdates on the Telegram API every few seconds 3. Script writes every incoming message to a local file (inbox.jsonl) 4. Claude Code reads that file every morning as part of the daily brief skill 5. Actionable items land in Obsidian — as tasks, project notes, or ideas tied to active projects — and the inbox resets. Clean slate every day. No cloud service. No third-party app. Just a script running in the background on your machine. The insight: an AI OS is only as good as what you feed it. Most people spend weeks building the automation layer but never solve the input problem — so the system runs on stale context. The bot fixed that. Now wherever I am — away from my desk, walking, traveling — I can capture thoughts, interesting finds, and ideas on the go. Nothing gets lost. Curious how others are solving this — how are you feeding live context into your AI OS?
3h •
Best file structure for claude code?
Hi guys, This might be a totally noob question, so forgive me, but I'm wondering what the best file structure for Claude Code is? When do you use global instructions and when do you use project-based instructions? If I'm connecting into a specific project folder, will it still read the global claud MD information and the business context? is it better to save skills globally instead of repeating them per project? My thinking is that I want to have a global layer where all of my context around my business, what I'm working on, any references, skills and everything are just kept in one place, and I'm not repeating it in every single project. And then on the project folder, it's only things related to that project specifically. Where should I be pointing when I'm working on VS Code? Should I be pointing to the project folder? Will it still read the global instructions, or should I always point to the global folder? What are your best practices or the best ways of handling this guys? Thanks!!
0 likes • 3h
Honest answer: there's no "best" way — it depends on your project. What I'm describing is for a personal second brain or operating system, which is a very specific use case. Yours might be totally different. That said, here's what's worked for me: One main folder as your root. Open Claude Code pointing to that root folder, not to individual projects. This is where all your global instructions live. Structure: - Root level: CLAUDE.md (your business context, how you work, rules) - .claude/ folder: skills, rules, agents — everything reusable - projects/ folder: Each project gets its own subfolder with a README.md. Only project-specific stuff goes there. - references/ folder: Templates, SOPs, examples — things you reference but don't repeat How it works: - When you open any project subfolder, Claude still reads your root CLAUDE.md automatically. Both layers load at once. - Global instructions: Business context, how you work, rules, skills. Write once. - Project instructions: Only what's specific to that project — scope, status, decisions. Everything else references the global layer. Where to point: Always your main root folder in VS Code. Not the project subfolder. Does it work perfectly? Not yet. Is it the "right" way? Depends on what you're building. What's your situation? What are you trying to organize — teams, multiple clients, different types of projects?
💎
⭐
18h •
🚀New Video: The Skill That 10x’d My Claude Code Projects
The hardest part of building a good AI system isn't the prompts, it's getting everything out of your head and into the system. In this video I break down the grill-me skill, which relentlessly interviews you about a process and writes it all back to a knowledge doc so nothing gets lost. I show how I built this to checkpoint after every answer, why front-loading context gets your skills to 90% on the first try instead of grinding through 30 iterations, and how to start grilling yourself today.
2 likes • 3h
Thank you so much for sharing this skill, @Nate Herk One thing I also tried was asking my OS to interview me about more personal and psychological aspects: how I think, how I make decisions, how I react under pressure, what kind of communication helps me, and what kind of plans actually work for me. That helped a lot. Not only with the quality of the outputs, but also with the relationship I have with my OS: how it communicates with me, how it presents plans, how it helps me organize my thoughts, and how it adapts to the way I actually work. It made the system feel less generic and much more aligned with me.
15h •
Building a Personal OS as an AI Video Creator
Hi everyone, First of all, I just wanted to say thank you to Nate and to this community. My name is Franco. I’m a videographer and AI video/image creator based in Portugal, and lately I’ve been really immersed in building my own “Second Brain” / personal OS, as Nate calls it in VS. I’d love to see more videos from Nate around this kind of workflow: how to connect tools like Obsidian, ClickUp, social media planning, content creation, and AI systems into a practical personal OS. My main work is creating videos and images with AI, especially for advertising, social media, and visual storytelling. I’m constantly testing workflows for image generation, AI video, cinematic prompting, visual consistency, and creative production systems. If anyone here is working on something similar, or is interested in AI video/image workflows, I’d be happy to connect and share my workflow and what I’m building, testing, and learning. Thanks again to Nate and everyone here. Looking forward to learning more from the community. Vamos que se puede!
0 likes • 3h
@Chris Ecoms Nice to meet you!
21h •
You already have the skills — but you're stuck with no clients in a saturated market.
A lot of people forget something important: businesses were hiring developers long before AI automation existed. Many of them already have their tech locked down with existing relationships. The good news? The winners right now are the ones creating their own unique plan and niche instead of copying what everyone else is doing. Most people default to cold DMs, generic emails, and spammy outreach. It rarely works. My approach was completely different. I printed professional business cards on thick card stock, branded them properly, and added a QR code that led straight to my services. Then, while I was out doing deliveries for my other work, I started placing them strategically on doors and handing them out in person. That one simple offline move brought in extra cash and real leads. This is just one example of thinking outside the box. In today’s world, we have to be **doers** — not just scrollers. I get multiple messages in my business inbox every week with the exact same copy-paste lines. They all blend together and get ignored. Instead, try this: Get up, print some solid cards, and start handing them out. Grocery store, gas station, convenience store — it doesn’t matter. Strike up real conversations and give your card with confidence. You’d be surprised how well this works when most of your competition is hiding behind a screen.
0 likes • 16h
Real conversations still work, and doing something different from everyone sending the same DMs can make a big difference.
1-10 of 11
@franco-sanguinetti-4179
Aprendiendo Claude Code para mejorar mis procesos.
Active 2h ago
Joined May 4, 2026
Powered by