I am working in both Claude Code and Openclaw. Both have skills and can't see each other's info. SO --- I created a skills directory where they can both access. In windows this was rather easy. Create your skills directory (not on a network drive - the same drive as your app installations). From that point copy the skills that is being used by either Claude Code or Openclaw to this new directory. Then create "junction links (JL)" to the directory of the skill. If it is a new skill you only need to create the junction link from both apps to use with both. I do both even when the skill does not make sense for a specific app. That way I don't have to remember if I created the junction for that particular skill. Now when you edit the skill, you only have one place to edit.

Day 1 done and I learned something I wasn't expecting. I did Nate's newsletter build in the morning. Solid. Worked as advertised. VERSION 1. Then I ran it on my actual target audience (home service business owners) in the afternoon. The output sounded like a Silicon Valley tech blog trying to explain plumbing. "Growth blocker." "Leverage." "Revenue." Words my audience doesn't use. So I ended up building something bigger than I planned: - Got ai-humanizer running to strip AI patterns - Built voice-service-business as a layer on top - teaches Claude to write like someone who actually knows the trades - Installed direct-response-copy (Ogilvy, Schwartz, Halbert frameworks) - Built two adapter skills (headlines-newsletter and headlines-sales) so the same copywriting library can serve editorial AND conversion contexts - Set up a shared .skills directory that junctions into Claude Code and OpenClaw, so I don't have to maintain two copies of anything The voice jump from draft to final was massive. A tired shop owner reading the final version actually sounds like someone who gets their world. VERSION 2 (need to work on info graphics - not my focus today) Biggest lesson: the challenge build is a starting point, not the finish line. What's different about your audience is where the work is. On to Day 2.

In for the challenge - not quite a beginner (experience is one or two workflows in n8n, build a program in Bolt during their Hackathon, and built my own openclaw home network - took 18 days to build with claude). Since everything was done hand in hand with claude or some other tool, I still am a beginner but not a novice. (update - I will be doing the challenge plus applying the learned techniques to my own build) For my own build, I will be using the same WAT framework, same Claude Code build process, but along with the newsletter I'm building a lead-generation tool for my business. It's a task-cost calculator for home service business owners - walks them through a handful of their tasks, shows what those tasks are actually costing them, and delivers a branded summary. Goal: ship it live on tristacks.com by day 7 as a real lead-gen where the end result is booking a call. Website rebuild is on deck for week 2 with a blog (using the newsletter concept above and extending it with skills). We will see if this will happen or it might turn into another 18 day process... 😃

Hey everyone. I'm posting the newsletter I built for the 7 Day AIS Challenge. - What I built: a real estate investment newsletter for Chile - One thing I learned: this is easier than I thought. Even though there is a learning curve, It is much shorter than I expected. Before this I thought v1 would be unusable and would need a lot of tweaking, but with just a few minor changes it would be ready to go. - One thing I'd improve: add TLDR bulletpoints, set brand guidelines If you're not level 2 yet (and ca't post yours), feel free to share here so you can check that box 😁 Cheers

Today I completed my first workflow on the N8 automation platform , after installing docker container on my modest computer and using the Ngrok program. I installed a version of Llama 3.2 on my computer. Then I set up some simple chat node and simple memory node.. The result was fantastic.